Add files using upload-large-folder tool

LICENSE

@@ -0,0 +1,84 @@
+MiniMax H3 COMMUNITY LICENSE AGREEMENT
+MiniMax H3 release date/License date: August 2, 2026.
+The scope of this License Agreement (this “Agreement”) is expressly limited to the “Applicable Territory” as defined below.
+By clicking to accept, or by using, reproducing, modifying, distributing, running, or displaying any portion or element of the MiniMax H3 Works (including through any Hosted Services) in any manner, you acknowledge and accept the terms of this Agreement, and this Agreement shall take immediate effect upon the occurrence of such act.
+I.  Definitions
+1. “Acceptable Use Policy” means the policy published by MiniMax in Exhibit A.
+2. “Agreement” means the terms and conditions set forth herein that govern the use, reproduction, distribution, modification, running, and display of the MiniMax H3 Works or any portion or element thereof.
+3. “Applicable Territory” means worldwide, excluding the Excluded Territories.
+4. “Documentation” means the specifications, manuals, and documentation concerning MiniMax H3 that are publicly released by MiniMax.
+5. “Excluded Territories” means the European Union, the United Kingdom, the Republic of Korea and the United States of America.  
+6. “MiniMax H3” means the video generation model, together with its software and algorithms, including trained model weights, parameters (including optimizer states), machine-learning model code, inference-supporting code, and other elements thereof made publicly available by Us, as released at https://huggingface.co/MiniMaxAI/MiniMax-H3.
+7. “MiniMax H3 Works” means (i) the Materials, (ii) the Model Derivatives, and (iii) all derivatives thereof.
+8. “Hosted Services” means hosted services provided via application programming interfaces (APIs), web access, or any other electronic or remote means.
+9. “Licensee,” “you,” or “your” means the natural or legal person exercising rights and/or using the MiniMax H3 Works for any purpose in any field of use under this Agreement.
+10. “Materials” means, collectively, MiniMax H3 and the Documentation (and any portion thereof), in each case as made available by MiniMax under this Agreement and proprietary to MiniMax.
+11. “Model Derivatives” means all of the following: (i) any modification of MiniMax H3 or any Model Derivative thereof; (ii) any work based on MiniMax H3 or any Model Derivative thereof; or (iii) any other machine learning model created by transferring the patterns of the weights, parameters, operational patterns, or Outputs of MiniMax H3 or any Model Derivative thereof to another model, such that the latter model exhibits behavior similar to MiniMax H3 or its Model Derivatives, including by distillation methods, methods using intermediate data representations, or methods based on training using synthetic-data Outputs generated by MiniMax H3 or its Model Derivatives. For the avoidance of doubt, Outputs are not deemed Model Derivatives.
+12. “Output” means any result of operating or otherwise using MiniMax H3 or any Model Derivatives (including through Hosted Services).
+13. “Third Party” means any natural or legal person that is not under common control with us or with you.
+14. “Including” means “including but not limited to.”
+15. “We,” “Us”  or  “MiniMax” means Nanonoble Pte. Ltd..
+II.  Grant of Rights
+Solely within the Applicable Territory, we grant you a non-exclusive, non-transferable, royalty-free, limited license to use, reproduce, distribute, create derivative works (including Model Derivatives), and modify the Materials in accordance with the terms of this Agreement and the Acceptable Use Policy, based on the intellectual property and other rights owned by MiniMax that are embodied in or used by the Materials. You shall not violate (or encourage or permit any person to violate) any term of this Agreement or the Acceptable Use Policy.
+We will continuously evaluate the applicable laws, regulations and compliance requirements for the Excluded Territories. In the meantime, should any person in such Excluded Territories be interested in deploying our models, you are welcome to contact us about obtaining a license, which will be granted based on robust controls and guardrails for purposes of complying with the laws, regulations and compliance requirements of the Excluded Territories.
+III.  Distribution and Redistribution
+Subject to and conditioned on your continuing compliance with this Agreement, including its territorial restrictions and the Acceptable Use Policy, and solely within the Applicable Territory, you may distribute or make available the MiniMax H3 Works to Third Parties within the Applicable Territory; provided, that all of the following conditions are met:
+1. You must provide a copy of this Agreement to all such Third Parties who receive the MiniMax H3 Works or use your products or services related thereto;
+2. You must cause any modified files to carry prominent notices stating that you have modified such files;
+3. You are encouraged to:
+  a. display a notice on any product or service developed using MiniMax H3 indicating that the product or service is “Powered by MiniMax H3”; 
+  b. add an AI-generation identifier to files produced using generative AI models including MiniMax H3; and
+  c. publish at least one technical blog post or a public statement describing your experience using MiniMax H3 Works;
+4. All distributions to Third Parties (other than through Hosted Services) must be accompanied by a “NOTICE” text file containing the following notice:
+  “MiniMax H3 is licensed under the MiniMax H3 Community License Agreement, Copyright © 2026 MiniMax. All Rights Reserved.”
+You may add your own copyright notices on your modifications; except as provided in this Section and in Section V, however, you may not impose additional or different terms and conditions on the use, reproduction, or distribution of your modifications or of any aggregate Model Derivatives, and your use, reproduction, modification, distribution, running, and display of the work must otherwise comply with the terms and conditions of this Agreement (including the provisions concerning the Applicable Territory). If you receive the MiniMax H3 Works from a Licensee as part of an integrated end-user product, the provisions of Section III of this Agreement do not apply to you, but Section V and Exhibit A remain applicable.
+IV.  Additional Commercial Terms
+1. You shall obtain a separate, prior written authorization from MiniMax by contacting api@minimax.io with the subject line “MiniMax H3 licensing - authorization request”, if your commercial products and services generate more than 20 million US dollars (or equivalent in other currencies) in yearly revenue.
+2. You shall prominently display “MiniMax H3”on the user interface of commercial product or service that uses MiniMax H3 or MiniMax H3 Works.
+V. Use Restrictions
+1. Your use of the MiniMax H3 Works must comply with applicable laws and regulations (including trade-compliance laws and regulations) and must comply with the Acceptable Use Policy for the MiniMax H3 Works, which is incorporated into this Agreement by reference. 
+2. Before providing access to the MiniMax H3 Works or any product, service, or Hosted Service incorporating them, you must bind each recipient or user to enforceable terms at least as protective as the use restrictions in this Section V and Exhibit A, and you must notify each recipient or user that those restrictions apply.
+3. You may not use the MiniMax H3 Works or any of their Outputs or results to improve any other artificial intelligence model (other than MiniMax H3 or its Model Derivatives).
+4. You may not use, reproduce, modify, distribute, or display the MiniMax H3 Works or any of their Outputs or results outside the Applicable Territory. Any such use outside the Applicable Territory is not authorized by this Agreement.
+5. If you provide or make available to any Third Party a product, service, or Hosted Service that permits the generation of Outputs using MiniMax H3 or any Model Derivative, you must, before making that product or service available and throughout its operation, implement, maintain, test, and periodically review reasonable and proportionate technical and organizational safeguards designed to prevent and mitigate access, uses, and Outputs that violate this Section V or Exhibit A, including uses or Outputs that infringe, misappropriate, or otherwise violate any Third Party’s intellectual-property or other rights. You must not knowingly disable, materially weaken, or permit the circumvention of those safeguards. You must maintain a reasonably accessible mechanism for reporting suspected violations. Upon receiving a good-faith report or otherwise obtaining actual knowledge of a violation, you must promptly investigate and take reasonable steps within your control to stop or mitigate the violation, including removing or disabling access to offending content or services and suspending or terminating repeat violators where appropriate. You are responsible for implementing and enforcing these requirements with respect to your products, services, systems, users, and downstream recipients.
+VI.  Intellectual Property
+1. Subject to MiniMax’s rights in the MiniMax H3 Works (and the intellectual property therein), and to your compliance with the terms and conditions of this Agreement, as between you and MiniMax, you will own the derivative works and modifications of the Materials that you have created or had created, as well as any Model Derivatives.
+2. Except for the limited license expressly granted in this paragraph, no trademark license is granted under this Agreement; with respect to MiniMax H3 Works, the Licensee may not use any name or mark owned by or associated with MiniMax or any of its affiliates, except as reasonably and customarily necessary to describe and distribute the MiniMax H3 Works. MiniMax hereby grants you a license to use the “MiniMax H3” mark (the “Mark”) within the Applicable Territory solely for the purpose of complying with Section III.3; provided, that you comply with all applicable trademark-protection laws. All goodwill arising from your use of the Mark shall inure to the benefit of MiniMax.
+3. If you bring or assert any suit or other legal proceeding (including a cross-claim or counterclaim in any action) against us or any other natural or legal person alleging that the Materials, any Output, or any portion of the foregoing infringes any intellectual property right or other right owned by you or for which you can obtain a license, all licenses granted to you under this Agreement will terminate as of the date such suit or proceeding is filed. You shall defend, indemnify, and hold us harmless against any Third-Party claim arising out of or related to the use or distribution of the MiniMax H3 Works by you or by any Third Party.
+4. MiniMax claims no rights over the Outputs you generate. You and your users are entirely responsible for the Outputs and any subsequent use thereof.
+VII.  Disclaimers and Limitations of Liability
+1. We have no obligation to support, update, provide training for, or develop any further version of the MiniMax H3 Works, or to grant any license with respect thereto.
+2. UNLESS AND ONLY TO THE EXTENT REQUIRED BY APPLICABLE LAW, THE MINIMAX H3 WORKS AND ANY OUTPUT AND RESULTS THEREFROM ARE PROVIDED “AS IS” WITHOUT ANY EXPRESS OR IMPLIED WARRANTIES OF ANY KIND INCLUDING ANY WARRANTIES OF TITLE, MERCHANTABILITY, NONINFRINGEMENT, COURSE OF DEALING, USAGE OF TRADE, OR FITNESS FOR A PARTICULAR PURPOSE. YOU ARE SOLELY RESPONSIBLE FOR DETERMINING THE APPROPRIATENESS OF USING, REPRODUCING, MODIFYING, PERFORMING, DISPLAYING OR DISTRIBUTING ANY OF THE MINIMAX H3 WORKS OR OUTPUTS AND ASSUME ANY AND ALL RISKS ASSOCIATED WITH YOUR OR A THIRD PARTY’S USE OR DISTRIBUTION OF ANY OF THE MINIMAX H3 WORKS OR OUTPUTS AND YOUR EXERCISE OF RIGHTS AND PERMISSIONS UNDER THIS AGREEMENT.
+3. TO THE FULLEST EXTENT PERMITTED BY APPLICABLE LAW, IN NO EVENT SHALL MINIMAX OR ITS AFFILIATES BE LIABLE UNDER ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, TORT, NEGLIGENCE, PRODUCTS LIABILITY, OR OTHERWISE, FOR ANY DAMAGES, INCLUDING ANY DIRECT, INDIRECT, SPECIAL, INCIDENTAL, EXEMPLARY, CONSEQUENTIAL OR PUNITIVE DAMAGES, OR LOST PROFITS OF ANY KIND ARISING FROM THIS AGREEMENT OR RELATED TO ANY OF THE MINIMAX H3 WORKS OR OUTPUTS, EVEN IF MINIMAX OR ITS AFFILIATES HAVE BEEN ADVISED OF THE POSSIBILITY OF ANY OF THE FOREGOING.
+VIII.  Term and Termination
+1. This Agreement is effective from the moment you accept this Agreement or begin accessing the Materials, and, subject to your compliance with its terms and conditions, will remain in effect until terminated as provided herein.
+2. If you breach any term or condition of this Agreement, we have the right to terminate this Agreement. Upon termination, you must immediately cease accessing, using, and distributing the MiniMax H3 Works; delete or destroy all copies within your possession or control; and notify each downstream recipient that your authorization has ended. The obligations in the preceding sentence and Sections VI.1, VI.3, VII, and IX survive termination.
+IX.  Governing Law and Jurisdiction
+1. This Agreement, and any dispute arising out of or related to this Agreement, shall be governed by the laws of the Hong Kong Special Administrative Region of the People’s Republic of China, without regard to its conflict-of-laws rules. The United Nations Convention on Contracts for the International Sale of Goods does not apply to this Agreement.
+2. Any dispute arising out of or related to this Agreement shall be subject to the exclusive jurisdiction of the courts of the Hong Kong Special Administrative Region of the People’s Republic of China with competent jurisdiction. Both MiniMax and the Licensee hereby consent to the exclusive jurisdiction of such courts for any such dispute.
+Additional Note: Please note that the encoder of MiniMax H3 uses Qwen3-VL-32B, which is licensed under Apache 2.0 License: https://github.com/QwenLM/Qwen3-VL/blob/main/LICENSE.
+
+Exhibit A — Acceptable Use Policy
+MiniMax reserves the right to update this Acceptable Use Policy from time to time. 
+Last revised: August 2, 2026.
+MiniMax is committed to promoting the safe and fair use of its tools and features, including MiniMax H3. You agree not to use MiniMax H3, any Model Derivatives, or any Output in any of the following ways:
+1. Use outside the Applicable Territory;
+2. Use in any manner that violates any applicable national, federal, state, local, or international law, regulation, or other legal requirement, or that infringes, misappropriates, or otherwise violates any Third Party’s intellectual-property or other proprietary rights, including through unauthorized reproduction, distribution, public display, public performance, or creation of derivative works;
+3. Use in any manner that may harm yourself or others;
+4. Use to repurpose or distribute the Outputs of MiniMax H3 or any Model Derivatives in order to harm yourself or others;
+5. Use to circumvent or bypass any safety guardrails or safeguards we have implemented;
+6. Use in any manner that exploits or harms, or intends to exploit or harm, minors;
+7. Use to generate or disseminate verifiably false information and/or content for the purpose of harming others or influencing elections;
+8. Use to manufacture or facilitate false online engagement, including fake reviews and other means of false online engagement;
+9. Use to intentionally defame, disparage, or otherwise harass others;
+10. Use to generate and/or disseminate malware (including ransomware) or any other content intended to damage electronic systems;
+11. Use to generate or disseminate personally identifiable information for the purpose of harming others;
+12. Use to generate or disseminate information (including images, code, posts, or articles) in or to any public environment (including via bot tweets or similar means) without clearly and prominently disclosing that such information and/or content is machine-generated;
+13. Use to impersonate another person without that person’s consent, authorization, or lawful right to do so;
+14. Use to make high-risk automated decisions in critical domains that affect individual safety, rights, or well-being (such as law enforcement, immigration, healthcare or medical services, critical-infrastructure management, product-safety components, essential services, credit, employment, housing, education, social scoring, or insurance);
+15. Use in any manner that violates or disregards the social, ethical, or moral standards of other countries or regions;
+16. Use to carry out, assist, threaten, incite, plan, advocate for, or encourage violent extremism or terrorism;
+17. Use for any purpose intended to discriminate against, or harm, individuals or groups based on protected characteristics or categories, online or offline social behavior, or known or predicted personality traits;
+18. Use to intentionally exploit the vulnerabilities of specific populations based on age, social, physical, or psychological characteristics, so as to materially distort the behavior of a member of that group in a manner that causes, or is likely to cause, physical or psychological harm to that person or to others;
+19. Use for military purposes;
+20. Use to engage in any unauthorized or unlicensed professional activity, including but not limited to financial, legal, medical or healthcare, or other professional practice.

LICENSE-Qwen3-VL

@@ -0,0 +1,201 @@
+                                 Apache License
+                           Version 2.0, January 2004
+                        http://www.apache.org/licenses/
+
+   TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
+
+   1. Definitions.
+
+      "License" shall mean the terms and conditions for use, reproduction,
+      and distribution as defined by Sections 1 through 9 of this document.
+
+      "Licensor" shall mean the copyright owner or entity authorized by
+      the copyright owner that is granting the License.
+
+      "Legal Entity" shall mean the union of the acting entity and all
+      other entities that control, are controlled by, or are under common
+      control with that entity. For the purposes of this definition,
+      "control" means (i) the power, direct or indirect, to cause the
+      direction or management of such entity, whether by contract or
+      otherwise, or (ii) ownership of fifty percent (50%) or more of the
+      outstanding shares, or (iii) beneficial ownership of such entity.
+
+      "You" (or "Your") shall mean an individual or Legal Entity
+      exercising permissions granted by this License.
+
+      "Source" form shall mean the preferred form for making modifications,
+      including but not limited to software source code, documentation
+      source, and configuration files.
+
+      "Object" form shall mean any form resulting from mechanical
+      transformation or translation of a Source form, including but
+      not limited to compiled object code, generated documentation,
+      and conversions to other media types.
+
+      "Work" shall mean the work of authorship, whether in Source or
+      Object form, made available under the License, as indicated by a
+      copyright notice that is included in or attached to the work
+      (an example is provided in the Appendix below).
+
+      "Derivative Works" shall mean any work, whether in Source or Object
+      form, that is based on (or derived from) the Work and for which the
+      editorial revisions, annotations, elaborations, or other modifications
+      represent, as a whole, an original work of authorship. For the purposes
+      of this License, Derivative Works shall not include works that remain
+      separable from, or merely link (or bind by name) to the interfaces of,
+      the Work and Derivative Works thereof.
+
+      "Contribution" shall mean any work of authorship, including
+      the original version of the Work and any modifications or additions
+      to that Work or Derivative Works thereof, that is intentionally
+      submitted to Licensor for inclusion in the Work by the copyright owner
+      or by an individual or Legal Entity authorized to submit on behalf of
+      the copyright owner. For the purposes of this definition, "submitted"
+      means any form of electronic, verbal, or written communication sent
+      to the Licensor or its representatives, including but not limited to
+      communication on electronic mailing lists, source code control systems,
+      and issue tracking systems that are managed by, or on behalf of, the
+      Licensor for the purpose of discussing and improving the Work, but
+      excluding communication that is conspicuously marked or otherwise
+      designated in writing by the copyright owner as "Not a Contribution."
+
+      "Contributor" shall mean Licensor and any individual or Legal Entity
+      on behalf of whom a Contribution has been received by Licensor and
+      subsequently incorporated within the Work.
+
+   2. Grant of Copyright License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      copyright license to reproduce, prepare Derivative Works of,
+      publicly display, publicly perform, sublicense, and distribute the
+      Work and such Derivative Works in Source or Object form.
+
+   3. Grant of Patent License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      (except as stated in this section) patent license to make, have made,
+      use, offer to sell, sell, import, and otherwise transfer the Work,
+      where such license applies only to those patent claims licensable
+      by such Contributor that are necessarily infringed by their
+      Contribution(s) alone or by combination of their Contribution(s)
+      with the Work to which such Contribution(s) was submitted. If You
+      institute patent litigation against any entity (including a
+      cross-claim or counterclaim in a lawsuit) alleging that the Work
+      or a Contribution incorporated within the Work constitutes direct
+      or contributory patent infringement, then any patent licenses
+      granted to You under this License for that Work shall terminate
+      as of the date such litigation is filed.
+
+   4. Redistribution. You may reproduce and distribute copies of the
+      Work or Derivative Works thereof in any medium, with or without
+      modifications, and in Source or Object form, provided that You
+      meet the following conditions:
+
+      (a) You must give any other recipients of the Work or
+          Derivative Works a copy of this License; and
+
+      (b) You must cause any modified files to carry prominent notices
+          stating that You changed the files; and
+
+      (c) You must retain, in the Source form of any Derivative Works
+          that You distribute, all copyright, patent, trademark, and
+          attribution notices from the Source form of the Work,
+          excluding those notices that do not pertain to any part of
+          the Derivative Works; and
+
+      (d) If the Work includes a "NOTICE" text file as part of its
+          distribution, then any Derivative Works that You distribute must
+          include a readable copy of the attribution notices contained
+          within such NOTICE file, excluding those notices that do not
+          pertain to any part of the Derivative Works, in at least one
+          of the following places: within a NOTICE text file distributed
+          as part of the Derivative Works; within the Source form or
+          documentation, if provided along with the Derivative Works; or,
+          within a display generated by the Derivative Works, if and
+          wherever such third-party notices normally appear. The contents
+          of the NOTICE file are for informational purposes only and
+          do not modify the License. You may add Your own attribution
+          notices within Derivative Works that You distribute, alongside
+          or as an addendum to the NOTICE text from the Work, provided
+          that such additional attribution notices cannot be construed
+          as modifying the License.
+
+      You may add Your own copyright statement to Your modifications and
+      may provide additional or different license terms and conditions
+      for use, reproduction, or distribution of Your modifications, or
+      for any such Derivative Works as a whole, provided Your use,
+      reproduction, and distribution of the Work otherwise complies with
+      the conditions stated in this License.
+
+   5. Submission of Contributions. Unless You explicitly state otherwise,
+      any Contribution intentionally submitted for inclusion in the Work
+      by You to the Licensor shall be under the terms and conditions of
+      this License, without any additional terms or conditions.
+      Notwithstanding the above, nothing herein shall supersede or modify
+      the terms of any separate license agreement you may have executed
+      with Licensor regarding such Contributions.
+
+   6. Trademarks. This License does not grant permission to use the trade
+      names, trademarks, service marks, or product names of the Licensor,
+      except as required for reasonable and customary use in describing the
+      origin of the Work and reproducing the content of the NOTICE file.
+
+   7. Disclaimer of Warranty. Unless required by applicable law or
+      agreed to in writing, Licensor provides the Work (and each
+      Contributor provides its Contributions) on an "AS IS" BASIS,
+      WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
+      implied, including, without limitation, any warranties or conditions
+      of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
+      PARTICULAR PURPOSE. You are solely responsible for determining the
+      appropriateness of using or redistributing the Work and assume any
+      risks associated with Your exercise of permissions under this License.
+
+   8. Limitation of Liability. In no event and under no legal theory,
+      whether in tort (including negligence), contract, or otherwise,
+      unless required by applicable law (such as deliberate and grossly
+      negligent acts) or agreed to in writing, shall any Contributor be
+      liable to You for damages, including any direct, indirect, special,
+      incidental, or consequential damages of any character arising as a
+      result of this License or out of the use or inability to use the
+      Work (including but not limited to damages for loss of goodwill,
+      work stoppage, computer failure or malfunction, or any and all
+      other commercial damages or losses), even if such Contributor
+      has been advised of the possibility of such damages.
+
+   9. Accepting Warranty or Additional Liability. While redistributing
+      the Work or Derivative Works thereof, You may choose to offer,
+      and charge a fee for, acceptance of support, warranty, indemnity,
+      or other liability obligations and/or rights consistent with this
+      License. However, in accepting such obligations, You may act only
+      on Your own behalf and on Your sole responsibility, not on behalf
+      of any other Contributor, and only if You agree to indemnify,
+      defend, and hold each Contributor harmless for any liability
+      incurred by, or claims asserted against, such Contributor by reason
+      of your accepting any such warranty or additional liability.
+
+   END OF TERMS AND CONDITIONS
+
+   APPENDIX: How to apply the Apache License to your work.
+
+      To apply the Apache License to your work, attach the following
+      boilerplate notice, with the fields enclosed by brackets "[]"
+      replaced with your own identifying information. (Don't include
+      the brackets!)  The text should be enclosed in the appropriate
+      comment syntax for the file format. We also recommend that a
+      file or class name and description of purpose be included on the
+      same "printed page" as the copyright notice for easier
+      identification within third-party archives.
+
+   Copyright [yyyy] [name of copyright owner]
+
+   Licensed under the Apache License, Version 2.0 (the "License");
+   you may not use this file except in compliance with the License.
+   You may obtain a copy of the License at
+
+       http://www.apache.org/licenses/LICENSE-2.0
+
+   Unless required by applicable law or agreed to in writing, software
+   distributed under the License is distributed on an "AS IS" BASIS,
+   WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+   See the License for the specific language governing permissions and
+   limitations under the License.

NOTICE

@@ -0,0 +1,18 @@
+MiniMax H3 is licensed under the MiniMax H3 Community License Agreement, Copyright © 2026 MiniMax. All Rights Reserved.
+
+FastVideo-FastH3-8-Step-V2 is a modified MiniMax H3 model from the FastVideo team.
+The transformer/*.safetensors files contain the DMD2-distilled, VSA-H3 student
+at training step 1300, not the original MiniMax H3 transformer weights.
+The accompanying transformer configuration and index describe that student.
+The scheduler configurations and fastvideo_inference.json describe its trained
+eight-forward schedule, video/audio shifts 10/3, and 80% tile-64 VSA policy.
+The modular model index, model card, and release/provenance documentation were
+prepared by FastVideo for this derivative.
+
+The bundled text encoder, tokenizer, processor, video VAE and audio VAE weights
+are unmodified MiniMax H3 components. The Qwen3-VL encoder is licensed under
+Apache License 2.0; a copy is included as LICENSE-Qwen3-VL.
+Source: https://github.com/QwenLM/Qwen3-VL
+
+The model license is provided in LICENSE. These notices do not replace or
+modify its terms.

README.md

@@ -0,0 +1,44 @@
+---
+license: other
+license_name: minimax-h3-community
+license_link: LICENSE
+base_model: FastVideo/FastVideo-FastH3-8-Step-V2
+library_name: uniserve
+pipeline_tag: text-to-video
+tags:
+- text-to-video
+- text-to-audio-video
+- fastvideo
+- fasth3
+- nvfp4
+- modelopt
+- quantized
+---
+
+# FastVideo-FastH3-8-Step-V2-NVFP4
+
+> This UniServe deployment checkpoint applies calibrated NVIDIA Model Optimizer NVFP4 W4A4 only to the fused gate/up and down projections in all 50 H3 denoiser gated MLPs; denoiser attention, the BF16 text encoder, token refiner, modulation, normalization, latent and conditioning boundaries, the complete BF16 Video VAE, and audio decoder remain BF16/FP32. Calibration used 1,000 prompts with complete eight-forward denoising trajectories, ModelOpt commit `6a4b3f147e14a6fec690fedbced8df402344085d`, E2M1 values, K16 FP8 E4M3 block scales, FP32 tensor scales, and calibration-derived activation tensor scales; no Phase-B VAE calibration or VAE quantization is included.
+
+This repository is a packed UniServe checkpoint derived from [FastVideo/FastVideo-FastH3-8-Step-V2](https://huggingface.co/FastVideo/FastVideo-FastH3-8-Step-V2). It generates synchronized video and audio with eight transformer forwards and retains the source checkpoint's VSA-H3 execution contract, including video scheduler shift 10 and VSA sparsity 0.8.
+
+## Run with UniServe
+
+UniServe detects `modelopt_manifest.json` automatically and selects the only valid precision, `calibrated`. The packed checkpoint does not require NVIDIA Model Optimizer at deployment time.
+
+```bash
+uniserve serve skx618/FastVideo-FastH3-8-Step-V2-NVFP4 \
+  --model-description minimax-h3 \
+  --served-model-name MiniMax-H3 \
+  --dtype bfloat16 \
+  --quantization-config '{"mode":"calibrated"}'
+```
+
+The checkpoint targets the source model's four-B200 execution contract. The GPU count must divide H3's 56 attention heads.
+
+## Validation status
+
+The denoiser component was exported after the complete 1,000-record Phase A calibration. This assembled 8-step repository has not yet undergone the separate projection-conformance, end-to-end performance, or held-out perceptual evaluation performed for the 4-step checkpoint; no corresponding quality or speedup claim is made here.
+
+## License
+
+This derivative inherits the [MiniMax H3 Community License](LICENSE) and the source checkpoint's usage conditions.

audio_scheduler/scheduler_config.json

@@ -0,0 +1,5 @@
+{
+  "_class_name": "MiniMaxH3Scheduler",
+  "_diffusers_version": "0.36.0.dev0",
+  "shift": 3.0
+}

audio_vae/config.json

@@ -0,0 +1,125 @@
+{
+  "_class_name": "AutoencoderKLMiniMaxH3Audio",
+  "_diffusers_version": "0.36.0.dev0",
+  "encoder_dim": 64,
+  "encoder_rates": [
+    2,
+    4,
+    4,
+    5,
+    5
+  ],
+  "latent_dim": 2048,
+  "latent_channels": 32,
+  "decoder_dim": 1024,
+  "decoder_rates": [
+    5,
+    5,
+    2,
+    2,
+    2,
+    2,
+    2
+  ],
+  "decoder_kernel_sizes": [
+    9,
+    9,
+    4,
+    4,
+    4,
+    4,
+    4
+  ],
+  "num_attention_heads": 8,
+  "resblock_kernel_sizes": [
+    3,
+    7,
+    11
+  ],
+  "resblock_dilation_sizes": [
+    [
+      1,
+      3,
+      5
+    ],
+    [
+      1,
+      3,
+      5
+    ],
+    [
+      1,
+      3,
+      5
+    ]
+  ],
+  "sampling_rate": 32000,
+  "latents_mean": [
+    -0.020211687488382354,
+    0.3876466479950502,
+    -0.04398279799186767,
+    -0.28591514936373,
+    0.08179686214561671,
+    -0.35782641352446604,
+    0.040623809960919084,
+    -0.01552534501956604,
+    -0.223362481667332,
+    0.1821006842509091,
+    0.2941778783780663,
+    -0.07901167601970885,
+    -0.056815072777201,
+    -0.3699028221860095,
+    -0.31616315591624855,
+    0.5905951377425391,
+    -0.052139568068853864,
+    0.013673160263486295,
+    -0.03691647864630577,
+    0.09732660653298163,
+    -0.3394662328788498,
+    -0.30685677538541667,
+    -0.24504598907458763,
+    -0.034698524462007344,
+    0.02868032184767538,
+    -0.21217779266454084,
+    -0.1678263169941987,
+    0.3221287889040614,
+    -0.1223055851554907,
+    0.4356604928128464,
+    -0.0502599202236253,
+    0.3979258376211797
+  ],
+  "latents_std": [
+    1.6895524230479284,
+    2.76263727217653,
+    1.7945344281264435,
+    1.6801681847309828,
+    1.6390226546605453,
+    2.7788298348882177,
+    1.7659090095747236,
+    1.6199757612137327,
+    2.6336525640336896,
+    1.8539356672817833,
+    2.5056497896915633,
+    1.811019237886178,
+    1.9579657790720237,
+    1.6685498243529284,
+    1.4922469314453364,
+    3.298670198067373,
+    1.9491804496832168,
+    1.8720003270431442,
+    1.8334080103291832,
+    1.6488070416529093,
+    1.6176957696319716,
+    1.9131449234774398,
+    1.5695245398428617,
+    1.6943659940415912,
+    1.8318420762504692,
+    1.5540637421583379,
+    1.9344930328968526,
+    1.599198216109855,
+    1.718045989838149,
+    1.6307219190837705,
+    1.8661226051202384,
+    1.5613768203168363
+  ]
+}

checkpoint_content.json

@@ -0,0 +1,99 @@
+{
+  "aggregate_sha256": "516323fa396fa5dff4e82669d4e9a08a5791692a3d3b98ff6bc3de3fc6a33d11",
+  "checkpoint_root": "/mnt/lustre/vlm-wlsaidhi/fastvideo/outputs/minimax_h3_dmd2_sp4_fsdp64_v14_datafree_mixed_vsa80_8step_vshift10/inference/checkpoint-1300",
+  "file_count": 18,
+  "files": [
+    {
+      "bytes": 9,
+      "path": ".complete",
+      "sha256": "37a40f08d8548dba289b9b0bb35bcf63b359f6d37ee86044ebc6b6da080b9ec1"
+    },
+    {
+      "bytes": 6561,
+      "path": "metadata.json",
+      "sha256": "ca9f2d609c05742ba465d24989981ec02cca26acb6ca2f163dc0f6dc8d11c27b"
+    },
+    {
+      "bytes": 546,
+      "path": "transformer/config.json",
+      "sha256": "74c11bff524336576096993cbfcdcdc2ef4fa2fa4409df693bdcbc6c666282ae"
+    },
+    {
+      "bytes": 5331008552,
+      "path": "transformer/diffusion_pytorch_model-00001-of-00014.safetensors",
+      "sha256": "b82974a058b58c586279df78d146b3e20915765d87f404dc82a0efda3a955c8f"
+    },
+    {
+      "bytes": 5318721256,
+      "path": "transformer/diffusion_pytorch_model-00002-of-00014.safetensors",
+      "sha256": "05568fca94d81e382546e9a6ae8633a97fb10981fdc5e4aac34c28ef7f14d3b2"
+    },
+    {
+      "bytes": 5318721248,
+      "path": "transformer/diffusion_pytorch_model-00003-of-00014.safetensors",
+      "sha256": "ec8885fa237d7475e343b40de460d70adb8b5d0eeb3e2df176eb6af9c49610fb"
+    },
+    {
+      "bytes": 4875566048,
+      "path": "transformer/diffusion_pytorch_model-00004-of-00014.safetensors",
+      "sha256": "70dcbf6d3efb8d26f2dd4b20cd4f5c7564d6b9c6c1685c53cde24421cb151d56"
+    },
+    {
+      "bytes": 5318505992,
+      "path": "transformer/diffusion_pytorch_model-00005-of-00014.safetensors",
+      "sha256": "cabab8f1b8d57dc6de42de220dcf5ccbb754222741c5bc70d294ebd6e02d82eb"
+    },
+    {
+      "bytes": 5164580688,
+      "path": "transformer/diffusion_pytorch_model-00006-of-00014.safetensors",
+      "sha256": "9bb11d605a7c42372e8f206c2d47967d3b70db736aca68910a19aacebeeadfc6"
+    },
+    {
+      "bytes": 5318721240,
+      "path": "transformer/diffusion_pytorch_model-00007-of-00014.safetensors",
+      "sha256": "bcb3ac18457582de135b576eedad84626d54e29220a540016d2b2b385e9ac5f9"
+    },
+    {
+      "bytes": 5318721248,
+      "path": "transformer/diffusion_pytorch_model-00008-of-00014.safetensors",
+      "sha256": "845041576ed28ff8c419751a89ae87fe26ffac3df15f9890bc4241f671e7e5e2"
+    },
+    {
+      "bytes": 4875566056,
+      "path": "transformer/diffusion_pytorch_model-00009-of-00014.safetensors",
+      "sha256": "ad34ff06d42a9d90938d888a58ac0315087c3cbfde9676cf83e5f11199571430"
+    },
+    {
+      "bytes": 5318505984,
+      "path": "transformer/diffusion_pytorch_model-00010-of-00014.safetensors",
+      "sha256": "0efb2a0fd04d955dfa475508d28562fa596edb1ec4f8e4c62bae4ba9fb112d80"
+    },
+    {
+      "bytes": 5164580688,
+      "path": "transformer/diffusion_pytorch_model-00011-of-00014.safetensors",
+      "sha256": "32f04fe4184564b146f6214af8e80fb4b783a9dc1a9743282d61ef21745d3d3d"
+    },
+    {
+      "bytes": 5318721256,
+      "path": "transformer/diffusion_pytorch_model-00012-of-00014.safetensors",
+      "sha256": "903eccb1a1098e32f16a6979c27cbe87bf1dc304832173fc22e101b8ae3f8490"
+    },
+    {
+      "bytes": 5318721208,
+      "path": "transformer/diffusion_pytorch_model-00013-of-00014.safetensors",
+      "sha256": "018db4d6d8fe97c0e560d850ba5c275792ce0bfd33c8918caf6d198d758225ff"
+    },
+    {
+      "bytes": 2138941296,
+      "path": "transformer/diffusion_pytorch_model-00014-of-00014.safetensors",
+      "sha256": "160b0f5a830b332fb61be18c45e4d4ebab7829db7d8cb18302714c145819b8da"
+    },
+    {
+      "bytes": 70079,
+      "path": "transformer/diffusion_pytorch_model.safetensors.index.json",
+      "sha256": "5be1367650e2faf79edf1f106a8354d1a7ef2e3ff45df40c4514b4ae97e1136b"
+    }
+  ],
+  "schema_version": "fastvideo-checkpoint-content-identity-v1",
+  "shard_count": 14
+}

checkpoint_metadata.json

@@ -0,0 +1,222 @@
+{
+  "base_model_dir": "/mnt/lustre/vlm-k1kong/models/MiniMax-H3",
+  "config": {
+    "callbacks": {
+      "grad_clip": {
+        "_target_": "fastvideo.train.callbacks.grad_clip.GradNormClipCallback",
+        "max_grad_norm": 1.0
+      },
+      "latent_vis": {
+        "_target_": "fastvideo.train.callbacks.latent_vis.LatentVisCallback",
+        "every_steps": 100,
+        "fps": 24
+      },
+      "validation": {
+        "_target_": "fastvideo.train.callbacks.validation.ValidationCallback",
+        "dataset_file": "/mnt/lustre/vlm-shared/h3_t2av_preprocessed/v10_mixed_native_v3/validation/heldout60.json",
+        "every_steps": 100,
+        "guidance_scale": 1.0,
+        "max_record_num_frames": 345,
+        "num_videos_per_prompt": 1,
+        "offload_training_state": true,
+        "pipeline_target": "fastvideo.pipelines.basic.minimax_h3.minimax_h3_pipeline.MiniMaxH3Pipeline",
+        "run_at_start": true,
+        "sampling_steps": [
+          8
+        ],
+        "sampling_timesteps": [
+          999,
+          874,
+          749,
+          624,
+          500,
+          375,
+          250,
+          125
+        ],
+        "text_encoder_cpu_offload": true,
+        "use_record_dimensions": true,
+        "use_validation_media_conditioning": false,
+        "vae_cpu_offload": true
+      }
+    },
+    "method": {
+      "_target_": "fastvideo.train.methods.distribution_matching.dmd2.DMD2Method",
+      "cfg_uncond": {
+        "text": "zero"
+      },
+      "dmd_denoising_steps": [
+        999,
+        874,
+        749,
+        624,
+        500,
+        375,
+        250,
+        125
+      ],
+      "fake_score_betas": [
+        0.9,
+        0.999
+      ],
+      "fake_score_learning_rate": 2e-06,
+      "fake_score_loss_space": "x0",
+      "fake_score_lr_scheduler": "constant",
+      "generator_update_interval": 5,
+      "max_timestep_ratio": 0.999,
+      "min_timestep_ratio": 0.001,
+      "real_score_guidance_scale": 1.0,
+      "rollout_carry": true,
+      "rollout_carry_slots": 4,
+      "rollout_mode": "simulate",
+      "rollout_sample_type": "ode",
+      "score_timestep_continuous": true,
+      "score_timestep_shift": 2.4,
+      "score_timestep_warp_max": 0.999
+    },
+    "models": {
+      "critic": {
+        "_target_": "fastvideo.train.models.minimax_h3.MiniMaxH3DMDModel",
+        "attention_backend": "FLASH_ATTN",
+        "disable_custom_init_weights": true,
+        "enable_gradient_checkpointing_type": "full",
+        "init_from": "/mnt/lustre/vlm-k1kong/models/MiniMax-H3",
+        "trainable": true
+      },
+      "student": {
+        "_target_": "fastvideo.train.models.minimax_h3.MiniMaxH3DMDModel",
+        "attention_backend": "VIDEO_SPARSE_ATTN_H3",
+        "enable_gradient_checkpointing_type": "full",
+        "init_from": "/mnt/lustre/vlm-k1kong/models/MiniMax-H3",
+        "trainable": true
+      },
+      "teacher": {
+        "_target_": "fastvideo.train.models.minimax_h3.MiniMaxH3DMDModel",
+        "attention_backend": "FLASH_ATTN",
+        "disable_custom_init_weights": true,
+        "init_from": "/mnt/lustre/vlm-k1kong/models/MiniMax-H3",
+        "trainable": false
+      }
+    },
+    "pipeline": {
+      "audio_scheduler_shift": 3.0,
+      "dit_config": {
+        "uniform_parameter_dtype": false
+      },
+      "video_scheduler_shift": 10.0
+    },
+    "training": {
+      "checkpoint": {
+        "checkpointing_start_step": 100,
+        "checkpoints_total_limit": 3,
+        "inference_checkpoint_dtype": "bfloat16",
+        "inference_checkpoint_role": "student",
+        "output_dir": "/mnt/lustre/vlm-wlsaidhi/fastvideo/outputs/minimax_h3_dmd2_sp4_fsdp64_v14_datafree_mixed_vsa80_8step_vshift10",
+        "require_complete_training_checkpoint": true,
+        "resume_from_checkpoint": "latest",
+        "save_inference_checkpoint_on_validation": true,
+        "training_state_checkpointing_steps": 100
+      },
+      "data": {
+        "data_path": [
+          "/mnt/lustre/vlm-shared/h3_t2av_preprocessed/v10_mixed_native_v3/h3_t2av_video_nuva_50k_720_mixed_len/data",
+          "/mnt/lustre/vlm-shared/h3_t2av_preprocessed/v10_mixed_native_v3/h3_t2av_video_5s_768p/data",
+          "/mnt/lustre/vlm-shared/h3_t2av_preprocessed/v10_mixed_native_v3/h3_t2av_video_nuva_10k_720_mixed_len/data",
+          "/mnt/lustre/vlm-shared/h3_t2av_preprocessed/v10_mixed_native_v3/h3_t2av_video_nuva_10k_mixed_res_len/data",
+          "/mnt/lustre/vlm-shared/h3_t2av_preprocessed/v10_mixed_native_v3/h3_t2av_fastgen_vidprom_150k/data"
+        ],
+        "dataloader_num_workers": 0,
+        "native_shape_bucketing": true,
+        "num_frames": 124,
+        "num_height": 768,
+        "num_latent_t": 37,
+        "num_width": 1344,
+        "preprocessed_data_type": "text_only",
+        "seed": 42,
+        "train_batch_size": 1,
+        "training_cfg_rate": 0.0
+      },
+      "distributed": {
+        "hsdp_replicate_dim": 1,
+        "hsdp_shard_dim": 64,
+        "num_gpus": 64,
+        "sp_size": 4,
+        "tp_size": 1
+      },
+      "dit_precision": "fp32",
+      "loop": {
+        "gradient_accumulation_steps": 4,
+        "max_train_steps": 4000
+      },
+      "model": {
+        "enable_gradient_checkpointing_type": "full",
+        "enable_torch_compile": true,
+        "precondition_outputs": false,
+        "torch_compile_kwargs": {
+          "dynamic": true,
+          "recompile_limit": 32
+        }
+      },
+      "optimizer": {
+        "betas": [
+          0.9,
+          0.999
+        ],
+        "learning_rate": 2e-06,
+        "lr_scheduler": "constant",
+        "lr_warmup_steps": 0,
+        "weight_decay": 0.01
+      },
+      "tracker": {
+        "project_name": "h3-dmd2-vsa",
+        "run_name": "dmd2_sp4_fsdp64_v14_datafree_mixed_vsa80_8step_vshift10"
+      },
+      "vsa": {
+        "sparsity": 0.8,
+        "tile_size": 64
+      }
+    }
+  },
+  "dtype": "bfloat16",
+  "format_version": 1,
+  "kind": "inference",
+  "max_shard_size_bytes": 5368709120,
+  "module": "transformer",
+  "role": "student",
+  "shard_count": 14,
+  "shard_file_sizes": [
+    5331008552,
+    5318721256,
+    5318721248,
+    4875566048,
+    5318505992,
+    5164580688,
+    5318721240,
+    5318721248,
+    4875566056,
+    5318505984,
+    5164580688,
+    5318721256,
+    5318721208,
+    2138941296
+  ],
+  "shard_sizes": [
+    5331000320,
+    5318715392,
+    5318715392,
+    4875560448,
+    5318500352,
+    5164574720,
+    5318715392,
+    5318715392,
+    4875560448,
+    5318500352,
+    5164574720,
+    5318715392,
+    5318715392,
+    2138938880
+  ],
+  "step": 1300,
+  "tensor_count": 688,
+  "total_size": 70099502592
+}

fastvideo_inference.json

@@ -0,0 +1,33 @@
+{
+  "attention_backend": "VIDEO_SPARSE_ATTN_H3",
+  "audio_scheduler_shift": 3.0,
+  "checkpoint_content_sha256": "516323fa396fa5dff4e82669d4e9a08a5791692a3d3b98ff6bc3de3fc6a33d11",
+  "checkpoint_metadata_sha256": "ca9f2d609c05742ba465d24989981ec02cca26acb6ca2f163dc0f6dc8d11c27b",
+  "checkpoint_step": 1300,
+  "dmd_denoising_steps": [
+    999,
+    874,
+    749,
+    624,
+    500,
+    375,
+    250,
+    125
+  ],
+  "fastvideo_commit": "24bbe7fddd05ca6f2c34b3dbed06ac1c75b72086",
+  "guidance_scale": 1.0,
+  "model_id": "FastVideo/FastVideo-FastH3-8-Step-V2",
+  "num_gpus": 4,
+  "num_inference_steps": 9,
+  "schema_version": "fasth3-inference-contract-v1",
+  "sequence_parallel_size": 4,
+  "task": "t2av",
+  "torch_compile": false,
+  "training_parent_run_id": "20260829T210445Z-h3-v14-8step-datafree-vsa80-vshift10",
+  "transformer_forwards": 8,
+  "use_fsdp_inference": true,
+  "video_scheduler_shift": 10.0,
+  "vsa_kernel": "sm100a",
+  "vsa_sparsity": 0.8,
+  "vsa_tile_size": 64
+}

modelopt_manifest.json

@@ -0,0 +1,523 @@
+{
+  "calibration": {
+    "activation_block_scale": "runtime dynamic K16 encoding",
+    "activation_global_scale": "ModelOpt NVFP4 activation headroom calibration",
+    "denoising_forwards_per_record": 8,
+    "records": 1000,
+    "sample_sha256": "5baf06f8a8a811d4021efd4b372e984d3a8a5ea71912b150d80ace804046dd90",
+    "weight_scale": "static MSE, complete E4M3 scale sweep"
+  },
+  "components": {
+    "denoiser": {
+      "enabled": true,
+      "excluded_patterns": [
+        "attention",
+        "token_refiner",
+        "adaln",
+        "norm",
+        "latent_heads"
+      ],
+      "modules": {
+        "denoiser.transformer.layers.0.mlp.down": {
+          "activation_amax": 2462.01708984375
+        },
+        "denoiser.transformer.layers.0.mlp.gate_up.projections.gate": {
+          "activation_amax": 747.9899291992188
+        },
+        "denoiser.transformer.layers.0.mlp.gate_up.projections.up": {
+          "activation_amax": 747.9899291992188
+        },
+        "denoiser.transformer.layers.1.mlp.down": {
+          "activation_amax": 1285.5098876953125
+        },
+        "denoiser.transformer.layers.1.mlp.gate_up.projections.gate": {
+          "activation_amax": 671.212158203125
+        },
+        "denoiser.transformer.layers.1.mlp.gate_up.projections.up": {
+          "activation_amax": 671.212158203125
+        },
+        "denoiser.transformer.layers.10.mlp.down": {
+          "activation_amax": 5855.6962890625
+        },
+        "denoiser.transformer.layers.10.mlp.gate_up.projections.gate": {
+          "activation_amax": 2743.63916015625
+        },
+        "denoiser.transformer.layers.10.mlp.gate_up.projections.up": {
+          "activation_amax": 2743.63916015625
+        },
+        "denoiser.transformer.layers.11.mlp.down": {
+          "activation_amax": 6525.51025390625
+        },
+        "denoiser.transformer.layers.11.mlp.gate_up.projections.gate": {
+          "activation_amax": 2743.63916015625
+        },
+        "denoiser.transformer.layers.11.mlp.gate_up.projections.up": {
+          "activation_amax": 2743.63916015625
+        },
+        "denoiser.transformer.layers.12.mlp.down": {
+          "activation_amax": 6525.51025390625
+        },
+        "denoiser.transformer.layers.12.mlp.gate_up.projections.gate": {
+          "activation_amax": 2743.63916015625
+        },
+        "denoiser.transformer.layers.12.mlp.gate_up.projections.up": {
+          "activation_amax": 2743.63916015625
+        },
+        "denoiser.transformer.layers.13.mlp.down": {
+          "activation_amax": 6525.51025390625
+        },
+        "denoiser.transformer.layers.13.mlp.gate_up.projections.gate": {
+          "activation_amax": 3057.47509765625
+        },
+        "denoiser.transformer.layers.13.mlp.gate_up.projections.up": {
+          "activation_amax": 3057.47509765625
+        },
+        "denoiser.transformer.layers.14.mlp.down": {
+          "activation_amax": 6525.51025390625
+        },
+        "denoiser.transformer.layers.14.mlp.gate_up.projections.gate": {
+          "activation_amax": 2743.63916015625
+        },
+        "denoiser.transformer.layers.14.mlp.gate_up.projections.up": {
+          "activation_amax": 2743.63916015625
+        },
+        "denoiser.transformer.layers.15.mlp.down": {
+          "activation_amax": 6525.51025390625
+        },
+        "denoiser.transformer.layers.15.mlp.gate_up.projections.gate": {
+          "activation_amax": 2743.63916015625
+        },
+        "denoiser.transformer.layers.15.mlp.gate_up.projections.up": {
+          "activation_amax": 2743.63916015625
+        },
+        "denoiser.transformer.layers.16.mlp.down": {
+          "activation_amax": 6525.51025390625
+        },
+        "denoiser.transformer.layers.16.mlp.gate_up.projections.gate": {
+          "activation_amax": 3407.209716796875
+        },
+        "denoiser.transformer.layers.16.mlp.gate_up.projections.up": {
+          "activation_amax": 3407.209716796875
+        },
+        "denoiser.transformer.layers.17.mlp.down": {
+          "activation_amax": 9030.7177734375
+        },
+        "denoiser.transformer.layers.17.mlp.gate_up.projections.gate": {
+          "activation_amax": 3057.47509765625
+        },
+        "denoiser.transformer.layers.17.mlp.gate_up.projections.up": {
+          "activation_amax": 3057.47509765625
+        },
+        "denoiser.transformer.layers.18.mlp.down": {
+          "activation_amax": 9030.7177734375
+        },
+        "denoiser.transformer.layers.18.mlp.gate_up.projections.gate": {
+          "activation_amax": 2743.63916015625
+        },
+        "denoiser.transformer.layers.18.mlp.gate_up.projections.up": {
+          "activation_amax": 2743.63916015625
+        },
+        "denoiser.transformer.layers.19.mlp.down": {
+          "activation_amax": 9030.7177734375
+        },
+        "denoiser.transformer.layers.19.mlp.gate_up.projections.gate": {
+          "activation_amax": 2743.63916015625
+        },
+        "denoiser.transformer.layers.19.mlp.gate_up.projections.up": {
+          "activation_amax": 2743.63916015625
+        },
+        "denoiser.transformer.layers.2.mlp.down": {
+          "activation_amax": 3796.94921875
+        },
+        "denoiser.transformer.layers.2.mlp.gate_up.projections.gate": {
+          "activation_amax": 1153.55810546875
+        },
+        "denoiser.transformer.layers.2.mlp.gate_up.projections.up": {
+          "activation_amax": 1153.55810546875
+        },
+        "denoiser.transformer.layers.20.mlp.down": {
+          "activation_amax": 10063.712890625
+        },
+        "denoiser.transformer.layers.20.mlp.gate_up.projections.gate": {
+          "activation_amax": 3057.47509765625
+        },
+        "denoiser.transformer.layers.20.mlp.gate_up.projections.up": {
+          "activation_amax": 3057.47509765625
+        },
+        "denoiser.transformer.layers.21.mlp.down": {
+          "activation_amax": 10063.712890625
+        },
+        "denoiser.transformer.layers.21.mlp.gate_up.projections.gate": {
+          "activation_amax": 3057.47509765625
+        },
+        "denoiser.transformer.layers.21.mlp.gate_up.projections.up": {
+          "activation_amax": 3057.47509765625
+        },
+        "denoiser.transformer.layers.22.mlp.down": {
+          "activation_amax": 10063.712890625
+        },
+        "denoiser.transformer.layers.22.mlp.gate_up.projections.gate": {
+          "activation_amax": 3407.209716796875
+        },
+        "denoiser.transformer.layers.22.mlp.gate_up.projections.up": {
+          "activation_amax": 3407.209716796875
+        },
+        "denoiser.transformer.layers.23.mlp.down": {
+          "activation_amax": 12497.7001953125
+        },
+        "denoiser.transformer.layers.23.mlp.gate_up.projections.gate": {
+          "activation_amax": 3407.209716796875
+        },
+        "denoiser.transformer.layers.23.mlp.gate_up.projections.up": {
+          "activation_amax": 3407.209716796875
+        },
+        "denoiser.transformer.layers.24.mlp.down": {
+          "activation_amax": 13927.271484375
+        },
+        "denoiser.transformer.layers.24.mlp.gate_up.projections.gate": {
+          "activation_amax": 3796.94921875
+        },
+        "denoiser.transformer.layers.24.mlp.gate_up.projections.up": {
+          "activation_amax": 3796.94921875
+        },
+        "denoiser.transformer.layers.25.mlp.down": {
+          "activation_amax": 19274.087890625
+        },
+        "denoiser.transformer.layers.25.mlp.gate_up.projections.gate": {
+          "activation_amax": 3796.94921875
+        },
+        "denoiser.transformer.layers.25.mlp.gate_up.projections.up": {
+          "activation_amax": 3796.94921875
+        },
+        "denoiser.transformer.layers.26.mlp.down": {
+          "activation_amax": 21478.7890625
+        },
+        "denoiser.transformer.layers.26.mlp.gate_up.projections.gate": {
+          "activation_amax": 4231.27001953125
+        },
+        "denoiser.transformer.layers.26.mlp.gate_up.projections.up": {
+          "activation_amax": 4231.27001953125
+        },
+        "denoiser.transformer.layers.27.mlp.down": {
+          "activation_amax": 29724.70703125
+        },
+        "denoiser.transformer.layers.27.mlp.gate_up.projections.gate": {
+          "activation_amax": 4715.27099609375
+        },
+        "denoiser.transformer.layers.27.mlp.gate_up.projections.up": {
+          "activation_amax": 4715.27099609375
+        },
+        "denoiser.transformer.layers.28.mlp.down": {
+          "activation_amax": 45841.765625
+        },
+        "denoiser.transformer.layers.28.mlp.gate_up.projections.gate": {
+          "activation_amax": 4715.27099609375
+        },
+        "denoiser.transformer.layers.28.mlp.gate_up.projections.up": {
+          "activation_amax": 4715.27099609375
+        },
+        "denoiser.transformer.layers.29.mlp.down": {
+          "activation_amax": 56928.95703125
+        },
+        "denoiser.transformer.layers.29.mlp.gate_up.projections.gate": {
+          "activation_amax": 4715.27099609375
+        },
+        "denoiser.transformer.layers.29.mlp.gate_up.projections.up": {
+          "activation_amax": 4715.27099609375
+        },
+        "denoiser.transformer.layers.3.mlp.down": {
+          "activation_amax": 4715.27099609375
+        },
+        "denoiser.transformer.layers.3.mlp.gate_up.projections.gate": {
+          "activation_amax": 1153.55810546875
+        },
+        "denoiser.transformer.layers.3.mlp.gate_up.projections.up": {
+          "activation_amax": 1153.55810546875
+        },
+        "denoiser.transformer.layers.30.mlp.down": {
+          "activation_amax": 78784.546875
+        },
+        "denoiser.transformer.layers.30.mlp.gate_up.projections.gate": {
+          "activation_amax": 5254.6357421875
+        },
+        "denoiser.transformer.layers.30.mlp.gate_up.projections.up": {
+          "activation_amax": 5254.6357421875
+        },
+        "denoiser.transformer.layers.31.mlp.down": {
+          "activation_amax": 109030.7109375
+        },
+        "denoiser.transformer.layers.31.mlp.gate_up.projections.gate": {
+          "activation_amax": 5254.6357421875
+        },
+        "denoiser.transformer.layers.31.mlp.gate_up.projections.up": {
+          "activation_amax": 5254.6357421875
+        },
+        "denoiser.transformer.layers.32.mlp.down": {
+          "activation_amax": 135400.640625
+        },
+        "denoiser.transformer.layers.32.mlp.gate_up.projections.gate": {
+          "activation_amax": 5855.6962890625
+        },
+        "denoiser.transformer.layers.32.mlp.gate_up.projections.up": {
+          "activation_amax": 5855.6962890625
+        },
+        "denoiser.transformer.layers.33.mlp.down": {
+          "activation_amax": 168148.34375
+        },
+        "denoiser.transformer.layers.33.mlp.gate_up.projections.gate": {
+          "activation_amax": 5855.6962890625
+        },
+        "denoiser.transformer.layers.33.mlp.gate_up.projections.up": {
+          "activation_amax": 5855.6962890625
+        },
+        "denoiser.transformer.layers.34.mlp.down": {
+          "activation_amax": 168148.34375
+        },
+        "denoiser.transformer.layers.34.mlp.gate_up.projections.gate": {
+          "activation_amax": 6525.51025390625
+        },
+        "denoiser.transformer.layers.34.mlp.gate_up.projections.up": {
+          "activation_amax": 6525.51025390625
+        },
+        "denoiser.transformer.layers.35.mlp.down": {
+          "activation_amax": 232702.140625
+        },
+        "denoiser.transformer.layers.35.mlp.gate_up.projections.gate": {
+          "activation_amax": 6525.51025390625
+        },
+        "denoiser.transformer.layers.35.mlp.gate_up.projections.up": {
+          "activation_amax": 6525.51025390625
+        },
+        "denoiser.transformer.layers.36.mlp.down": {
+          "activation_amax": 232702.140625
+        },
+        "denoiser.transformer.layers.36.mlp.gate_up.projections.gate": {
+          "activation_amax": 6525.51025390625
+        },
+        "denoiser.transformer.layers.36.mlp.gate_up.projections.up": {
+          "activation_amax": 6525.51025390625
+        },
+        "denoiser.transformer.layers.37.mlp.down": {
+          "activation_amax": 208816.328125
+        },
+        "denoiser.transformer.layers.37.mlp.gate_up.projections.gate": {
+          "activation_amax": 6525.51025390625
+        },
+        "denoiser.transformer.layers.37.mlp.gate_up.projections.up": {
+          "activation_amax": 6525.51025390625
+        },
+        "denoiser.transformer.layers.38.mlp.down": {
+          "activation_amax": 288982.96875
+        },
+        "denoiser.transformer.layers.38.mlp.gate_up.projections.gate": {
+          "activation_amax": 6525.51025390625
+        },
+        "denoiser.transformer.layers.38.mlp.gate_up.projections.up": {
+          "activation_amax": 6525.51025390625
+        },
+        "denoiser.transformer.layers.39.mlp.down": {
+          "activation_amax": 358875.78125
+        },
+        "denoiser.transformer.layers.39.mlp.gate_up.projections.gate": {
+          "activation_amax": 7271.94189453125
+        },
+        "denoiser.transformer.layers.39.mlp.gate_up.projections.up": {
+          "activation_amax": 7271.94189453125
+        },
+        "denoiser.transformer.layers.4.mlp.down": {
+          "activation_amax": 4715.27099609375
+        },
+        "denoiser.transformer.layers.4.mlp.gate_up.projections.gate": {
+          "activation_amax": 1285.5098876953125
+        },
+        "denoiser.transformer.layers.4.mlp.gate_up.projections.up": {
+          "activation_amax": 1285.5098876953125
+        },
+        "denoiser.transformer.layers.40.mlp.down": {
+          "activation_amax": 445672.6875
+        },
+        "denoiser.transformer.layers.40.mlp.gate_up.projections.gate": {
+          "activation_amax": 7271.94189453125
+        },
+        "denoiser.transformer.layers.40.mlp.gate_up.projections.up": {
+          "activation_amax": 7271.94189453125
+        },
+        "denoiser.transformer.layers.41.mlp.down": {
+          "activation_amax": 496651.71875
+        },
+        "denoiser.transformer.layers.41.mlp.gate_up.projections.gate": {
+          "activation_amax": 8103.755859375
+        },
+        "denoiser.transformer.layers.41.mlp.gate_up.projections.up": {
+          "activation_amax": 8103.755859375
+        },
+        "denoiser.transformer.layers.42.mlp.down": {
+          "activation_amax": 616770.8125
+        },
+        "denoiser.transformer.layers.42.mlp.gate_up.projections.gate": {
+          "activation_amax": 9030.7177734375
+        },
+        "denoiser.transformer.layers.42.mlp.gate_up.projections.up": {
+          "activation_amax": 9030.7177734375
+        },
+        "denoiser.transformer.layers.43.mlp.down": {
+          "activation_amax": 616770.8125
+        },
+        "denoiser.transformer.layers.43.mlp.gate_up.projections.gate": {
+          "activation_amax": 9030.7177734375
+        },
+        "denoiser.transformer.layers.43.mlp.gate_up.projections.up": {
+          "activation_amax": 9030.7177734375
+        },
+        "denoiser.transformer.layers.44.mlp.down": {
+          "activation_amax": 687321.25
+        },
+        "denoiser.transformer.layers.44.mlp.gate_up.projections.gate": {
+          "activation_amax": 10063.712890625
+        },
+        "denoiser.transformer.layers.44.mlp.gate_up.projections.up": {
+          "activation_amax": 10063.712890625
+        },
+        "denoiser.transformer.layers.45.mlp.down": {
+          "activation_amax": 853555.25
+        },
+        "denoiser.transformer.layers.45.mlp.gate_up.projections.gate": {
+          "activation_amax": 11214.8681640625
+        },
+        "denoiser.transformer.layers.45.mlp.gate_up.projections.up": {
+          "activation_amax": 11214.8681640625
+        },
+        "denoiser.transformer.layers.46.mlp.down": {
+          "activation_amax": 1059994.25
+        },
+        "denoiser.transformer.layers.46.mlp.gate_up.projections.gate": {
+          "activation_amax": 12497.7001953125
+        },
+        "denoiser.transformer.layers.46.mlp.gate_up.projections.up": {
+          "activation_amax": 12497.7001953125
+        },
+        "denoiser.transformer.layers.47.mlp.down": {
+          "activation_amax": 1316362.125
+        },
+        "denoiser.transformer.layers.47.mlp.gate_up.projections.gate": {
+          "activation_amax": 13927.271484375
+        },
+        "denoiser.transformer.layers.47.mlp.gate_up.projections.up": {
+          "activation_amax": 13927.271484375
+        },
+        "denoiser.transformer.layers.48.mlp.down": {
+          "activation_amax": 2030107.875
+        },
+        "denoiser.transformer.layers.48.mlp.gate_up.projections.gate": {
+          "activation_amax": 17295.69140625
+        },
+        "denoiser.transformer.layers.48.mlp.gate_up.projections.up": {
+          "activation_amax": 17295.69140625
+        },
+        "denoiser.transformer.layers.49.mlp.down": {
+          "activation_amax": 2809486.5
+        },
+        "denoiser.transformer.layers.49.mlp.gate_up.projections.gate": {
+          "activation_amax": 19274.087890625
+        },
+        "denoiser.transformer.layers.49.mlp.gate_up.projections.up": {
+          "activation_amax": 19274.087890625
+        },
+        "denoiser.transformer.layers.5.mlp.down": {
+          "activation_amax": 5254.6357421875
+        },
+        "denoiser.transformer.layers.5.mlp.gate_up.projections.gate": {
+          "activation_amax": 2209.302001953125
+        },
+        "denoiser.transformer.layers.5.mlp.gate_up.projections.up": {
+          "activation_amax": 2209.302001953125
+        },
+        "denoiser.transformer.layers.6.mlp.down": {
+          "activation_amax": 5254.6357421875
+        },
+        "denoiser.transformer.layers.6.mlp.gate_up.projections.gate": {
+          "activation_amax": 2209.302001953125
+        },
+        "denoiser.transformer.layers.6.mlp.gate_up.projections.up": {
+          "activation_amax": 2209.302001953125
+        },
+        "denoiser.transformer.layers.7.mlp.down": {
+          "activation_amax": 4715.27099609375
+        },
+        "denoiser.transformer.layers.7.mlp.gate_up.projections.gate": {
+          "activation_amax": 2462.01708984375
+        },
+        "denoiser.transformer.layers.7.mlp.gate_up.projections.up": {
+          "activation_amax": 2462.01708984375
+        },
+        "denoiser.transformer.layers.8.mlp.down": {
+          "activation_amax": 5855.6962890625
+        },
+        "denoiser.transformer.layers.8.mlp.gate_up.projections.gate": {
+          "activation_amax": 2462.01708984375
+        },
+        "denoiser.transformer.layers.8.mlp.gate_up.projections.up": {
+          "activation_amax": 2462.01708984375
+        },
+        "denoiser.transformer.layers.9.mlp.down": {
+          "activation_amax": 5855.6962890625
+        },
+        "denoiser.transformer.layers.9.mlp.gate_up.projections.gate": {
+          "activation_amax": 2743.63916015625
+        },
+        "denoiser.transformer.layers.9.mlp.gate_up.projections.up": {
+          "activation_amax": 2743.63916015625
+        }
+      },
+      "quantized_patterns": [
+        "transformer_blocks.*.ff.net.0.proj",
+        "transformer_blocks.*.ff.net.2"
+      ]
+    },
+    "text_encoder": {
+      "enabled": false,
+      "excluded_patterns": [
+        "attention",
+        "embedding",
+        "norm",
+        "rope",
+        "softmax",
+        "checkpoint_layers.50:64",
+        "conditioning_output"
+      ],
+      "modules": {},
+      "quantized_patterns": [
+        "retained_layers.0:50.mlp.{gate,up,down}"
+      ]
+    },
+    "video_vae": {
+      "enabled": false,
+      "excluded_patterns": [
+        "post_quant_conv",
+        "decoder_boundaries",
+        "conv",
+        "norm",
+        "rope",
+        "softmax",
+        "residual",
+        "affine",
+        "pixel_postprocess"
+      ],
+      "modules": {},
+      "quantized_patterns": [
+        "decoder.transformer_blocks.*.{q,k,v,out,gate,up,down}"
+      ]
+    }
+  },
+  "modelopt_commit": "6a4b3f147e14a6fec690fedbced8df402344085d",
+  "numerical_format": {
+    "activation": "a4",
+    "block_scale": "fp8_e4m3",
+    "block_size": 16,
+    "output": "bf16",
+    "tensor_scale": "fp32",
+    "values": "e2m1",
+    "weight": "w4"
+  },
+  "schema_version": 1
+}

modular_model_index.json

@@ -0,0 +1,131 @@
+{
+  "_blocks_class_name": "MiniMaxH3Blocks",
+  "_class_name": "MiniMaxH3ModularPipeline",
+  "_diffusers_version": "0.36.0.dev0",
+  "audio_scheduler": [
+    "diffusers",
+    "MiniMaxH3Scheduler",
+    {
+      "pretrained_model_name_or_path": "FastVideo/FastVideo-FastH3-8-Step-V2",
+      "revision": null,
+      "subfolder": "audio_scheduler",
+      "type_hint": [
+        "diffusers",
+        "MiniMaxH3Scheduler"
+      ],
+      "variant": null
+    }
+  ],
+  "audio_vae": [
+    "diffusers",
+    "AutoencoderKLMiniMaxH3Audio",
+    {
+      "pretrained_model_name_or_path": "FastVideo/FastVideo-FastH3-8-Step-V2",
+      "revision": null,
+      "subfolder": "audio_vae",
+      "type_hint": [
+        "diffusers",
+        "AutoencoderKLMiniMaxH3Audio"
+      ],
+      "variant": null
+    }
+  ],
+  "processor": [
+    "transformers",
+    "Qwen3VLProcessor",
+    {
+      "pretrained_model_name_or_path": "FastVideo/FastVideo-FastH3-8-Step-V2",
+      "revision": null,
+      "subfolder": "processor",
+      "type_hint": [
+        "transformers",
+        "Qwen3VLProcessor"
+      ],
+      "variant": null
+    }
+  ],
+  "scheduler": [
+    "diffusers",
+    "MiniMaxH3Scheduler",
+    {
+      "pretrained_model_name_or_path": "FastVideo/FastVideo-FastH3-8-Step-V2",
+      "revision": null,
+      "subfolder": "scheduler",
+      "type_hint": [
+        "diffusers",
+        "MiniMaxH3Scheduler"
+      ],
+      "variant": null
+    }
+  ],
+  "text_encoder": [
+    "transformers",
+    "Qwen3VLForConditionalGeneration",
+    {
+      "pretrained_model_name_or_path": "FastVideo/FastVideo-FastH3-8-Step-V2",
+      "revision": null,
+      "subfolder": "text_encoder",
+      "type_hint": [
+        "transformers",
+        "Qwen3VLForConditionalGeneration"
+      ],
+      "variant": null
+    }
+  ],
+  "tokenizer": [
+    "transformers",
+    "Qwen2TokenizerFast",
+    {
+      "pretrained_model_name_or_path": "FastVideo/FastVideo-FastH3-8-Step-V2",
+      "revision": null,
+      "subfolder": "tokenizer",
+      "type_hint": [
+        "transformers",
+        "Qwen2TokenizerFast"
+      ],
+      "variant": null
+    }
+  ],
+  "transformer": [
+    "diffusers",
+    "MiniMaxH3Transformer3DModel",
+    {
+      "pretrained_model_name_or_path": "FastVideo/FastVideo-FastH3-8-Step-V2",
+      "revision": null,
+      "subfolder": "transformer",
+      "type_hint": [
+        "diffusers",
+        "MiniMaxH3Transformer3DModel"
+      ],
+      "variant": null
+    }
+  ],
+  "transformer_ref": [
+    "diffusers",
+    "MiniMaxH3Transformer3DModel",
+    {
+      "pretrained_model_name_or_path": "MiniMaxAI/MiniMax-H3",
+      "revision": null,
+      "subfolder": "transformer_ref",
+      "type_hint": [
+        "diffusers",
+        "MiniMaxH3Transformer3DModel"
+      ],
+      "variant": null
+    }
+  ],
+  "vae": [
+    "diffusers",
+    "AutoencoderKLMiniMaxH3",
+    {
+      "pretrained_model_name_or_path": "FastVideo/FastVideo-FastH3-8-Step-V2",
+      "revision": null,
+      "subfolder": "vae",
+      "type_hint": [
+        "diffusers",
+        "AutoencoderKLMiniMaxH3"
+      ],
+      "variant": null
+    }
+  ]
+}

processor/chat_template.json

@@ -0,0 +1,3 @@
+{
+    "chat_template": "{%- if tools %}\n    {{- '<|im_start|>system\\n' }}\n    {%- if messages[0].role == 'system' %}\n        {%- if messages[0].content is string %}\n            {{- messages[0].content }}\n        {%- else %}\n            {%- for content in messages[0].content %}\n                {%- if 'text' in content %}\n                    {{- content.text }}\n                {%- endif %}\n            {%- endfor %}\n        {%- endif %}\n        {{- '\\n\\n' }}\n    {%- endif %}\n    {{- \"# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n    {%- for tool in tools %}\n        {{- \"\\n\" }}\n        {{- tool | tojson }}\n    {%- endfor %}\n    {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n    {%- if messages[0].role == 'system' %}\n        {{- '<|im_start|>system\\n' }}\n        {%- if messages[0].content is string %}\n            {{- messages[0].content }}\n        {%- else %}\n            {%- for content in messages[0].content %}\n                {%- if 'text' in content %}\n                    {{- content.text }}\n                {%- endif %}\n            {%- endfor %}\n        {%- endif %}\n        {{- '<|im_end|>\\n' }}\n    {%- endif %}\n{%- endif %}\n{%- set image_count = namespace(value=0) %}\n{%- set video_count = namespace(value=0) %}\n{%- for message in messages %}\n    {%- if message.role == \"user\" %}\n        {{- '<|im_start|>' + message.role + '\\n' }}\n        {%- if message.content is string %}\n            {{- message.content }}\n        {%- else %}\n            {%- for content in message.content %}\n                {%- if content.type == 'image' or 'image' in content or 'image_url' in content %}\n                    {%- set image_count.value = image_count.value + 1 %}\n                    {%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%}\n                    <|vision_start|><|image_pad|><|vision_end|>\n                {%- elif content.type == 'video' or 'video' in content %}\n                    {%- set video_count.value = video_count.value + 1 %}\n                    {%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%}\n                    <|vision_start|><|video_pad|><|vision_end|>\n                {%- elif 'text' in content %}\n                    {{- content.text }}\n                {%- endif %}\n            {%- endfor %}\n        {%- endif %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {{- '<|im_start|>' + message.role + '\\n' }}\n        {%- if message.content is string %}\n            {{- message.content }}\n        {%- else %}\n            {%- for content_item in message.content %}\n                {%- if 'text' in content_item %}\n                    {{- content_item.text }}\n                {%- endif %}\n            {%- endfor %}\n        {%- endif %}\n        {%- if message.tool_calls %}\n            {%- for tool_call in message.tool_calls %}\n                {%- if (loop.first and message.content) or (not loop.first) %}\n                    {{- '\\n' }}\n                {%- endif %}\n                {%- if tool_call.function %}\n                    {%- set tool_call = tool_call.function %}\n                {%- endif %}\n                {{- '<tool_call>\\n{\"name\": \"' }}\n                {{- tool_call.name }}\n                {{- '\", \"arguments\": ' }}\n                {%- if tool_call.arguments is string %}\n                    {{- tool_call.arguments }}\n                {%- else %}\n                    {{- tool_call.arguments | tojson }}\n                {%- endif %}\n                {{- '}\\n</tool_call>' }}\n            {%- endfor %}\n        {%- endif %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"tool\" %}\n        {%- if loop.first or (messages[loop.index0 - 1].role != \"tool\") %}\n            {{- '<|im_start|>user' }}\n        {%- endif %}\n        {{- '\\n<tool_response>\\n' }}\n        {%- if message.content is string %}\n            {{- message.content }}\n        {%- else %}\n            {%- for content in message.content %}\n                {%- if content.type == 'image' or 'image' in content or 'image_url' in content %}\n                    {%- set image_count.value = image_count.value + 1 %}\n                    {%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%}\n                    <|vision_start|><|image_pad|><|vision_end|>\n                {%- elif content.type == 'video' or 'video' in content %}\n                    {%- set video_count.value = video_count.value + 1 %}\n                    {%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%}\n                    <|vision_start|><|video_pad|><|vision_end|>\n                {%- elif 'text' in content %}\n                    {{- content.text }}\n                {%- endif %}\n            {%- endfor %}\n        {%- endif %}\n        {{- '\\n</tool_response>' }}\n        {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n            {{- '<|im_end|>\\n' }}\n        {%- endif %}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n"
+}

processor/preprocessor_config.json

@@ -0,0 +1,21 @@
+{
+    "size": {
+        "longest_edge": 16777216,
+        "shortest_edge": 65536
+    },
+    "patch_size": 16,
+    "temporal_patch_size": 2,
+    "merge_size": 2,
+    "image_mean": [
+        0.5,
+        0.5,
+        0.5
+    ],
+    "image_std": [
+        0.5,
+        0.5,
+        0.5
+    ],
+    "processor_class": "Qwen3VLProcessor",
+    "image_processor_type": "Qwen2VLImageProcessorFast"
+}

processor/tokenizer_config.json

@@ -0,0 +1,246 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151665": {
+      "content": "<tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151666": {
+      "content": "</tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151667": {
+      "content": "<think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151668": {
+      "content": "</think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>",
+    "<d>",
+    "</d>",
+    "<|cutoff|>",
+    "<|lyrics_start|>",
+    "<|lyrics_end|>",
+    "<|caption_start|>",
+    "<|caption_end|>"
+  ],
+  "bos_token": null,
+  "chat_template": "{%- if tools %}\n    {{- '<|im_start|>system\\n' }}\n    {%- if messages[0].role == 'system' %}\n        {%- if messages[0].content is string %}\n            {{- messages[0].content }}\n        {%- else %}\n            {%- for content in messages[0].content %}\n                {%- if 'text' in content %}\n                    {{- content.text }}\n                {%- endif %}\n            {%- endfor %}\n        {%- endif %}\n        {{- '\\n\\n' }}\n    {%- endif %}\n    {{- \"# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n    {%- for tool in tools %}\n        {{- \"\\n\" }}\n        {{- tool | tojson }}\n    {%- endfor %}\n    {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n    {%- if messages[0].role == 'system' %}\n        {{- '<|im_start|>system\\n' }}\n        {%- if messages[0].content is string %}\n            {{- messages[0].content }}\n        {%- else %}\n            {%- for content in messages[0].content %}\n                {%- if 'text' in content %}\n                    {{- content.text }}\n                {%- endif %}\n            {%- endfor %}\n        {%- endif %}\n        {{- '<|im_end|>\\n' }}\n    {%- endif %}\n{%- endif %}\n{%- set image_count = namespace(value=0) %}\n{%- set video_count = namespace(value=0) %}\n{%- for message in messages %}\n    {%- if message.role == \"user\" %}\n        {{- '<|im_start|>' + message.role + '\\n' }}\n        {%- if message.content is string %}\n            {{- message.content }}\n        {%- else %}\n            {%- for content in message.content %}\n                {%- if content.type == 'image' or 'image' in content or 'image_url' in content %}\n                    {%- set image_count.value = image_count.value + 1 %}\n                    {%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%}\n                    <|vision_start|><|image_pad|><|vision_end|>\n                {%- elif content.type == 'video' or 'video' in content %}\n                    {%- set video_count.value = video_count.value + 1 %}\n                    {%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%}\n                    <|vision_start|><|video_pad|><|vision_end|>\n                {%- elif 'text' in content %}\n                    {{- content.text }}\n                {%- endif %}\n            {%- endfor %}\n        {%- endif %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {{- '<|im_start|>' + message.role + '\\n' }}\n        {%- if message.content is string %}\n            {{- message.content }}\n        {%- else %}\n            {%- for content_item in message.content %}\n                {%- if 'text' in content_item %}\n                    {{- content_item.text }}\n                {%- endif %}\n            {%- endfor %}\n        {%- endif %}\n        {%- if message.tool_calls %}\n            {%- for tool_call in message.tool_calls %}\n                {%- if (loop.first and message.content) or (not loop.first) %}\n                    {{- '\\n' }}\n                {%- endif %}\n                {%- if tool_call.function %}\n                    {%- set tool_call = tool_call.function %}\n                {%- endif %}\n                {{- '<tool_call>\\n{\"name\": \"' }}\n                {{- tool_call.name }}\n                {{- '\", \"arguments\": ' }}\n                {%- if tool_call.arguments is string %}\n                    {{- tool_call.arguments }}\n                {%- else %}\n                    {{- tool_call.arguments | tojson }}\n                {%- endif %}\n                {{- '}\\n</tool_call>' }}\n            {%- endfor %}\n        {%- endif %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"tool\" %}\n        {%- if loop.first or (messages[loop.index0 - 1].role != \"tool\") %}\n            {{- '<|im_start|>user' }}\n        {%- endif %}\n        {{- '\\n<tool_response>\\n' }}\n        {%- if message.content is string %}\n            {{- message.content }}\n        {%- else %}\n            {%- for content in message.content %}\n                {%- if content.type == 'image' or 'image' in content or 'image_url' in content %}\n                    {%- set image_count.value = image_count.value + 1 %}\n                    {%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%}\n                    <|vision_start|><|image_pad|><|vision_end|>\n                {%- elif content.type == 'video' or 'video' in content %}\n                    {%- set video_count.value = video_count.value + 1 %}\n                    {%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%}\n                    <|vision_start|><|video_pad|><|vision_end|>\n                {%- elif 'text' in content %}\n                    {{- content.text }}\n                {%- endif %}\n            {%- endfor %}\n        {%- endif %}\n        {{- '\\n</tool_response>' }}\n        {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n            {{- '<|im_end|>\\n' }}\n        {%- endif %}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "model_max_length": 262144,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

processor/video_preprocessor_config.json

@@ -0,0 +1,21 @@
+{
+    "size": {
+        "longest_edge": 25165824,
+        "shortest_edge": 4096
+    },
+    "patch_size": 16,
+    "temporal_patch_size": 2,
+    "merge_size": 2,
+    "image_mean": [
+        0.5,
+        0.5,
+        0.5
+    ],
+    "image_std": [
+        0.5,
+        0.5,
+        0.5
+    ],
+    "processor_class": "Qwen3VLProcessor",
+    "video_processor_type": "Qwen3VLVideoProcessor"
+}

scheduler/scheduler_config.json

@@ -0,0 +1,5 @@
+{
+  "_class_name": "MiniMaxH3Scheduler",
+  "_diffusers_version": "0.36.0.dev0",
+  "shift": 10.0
+}

text_encoder/chat_template.json

@@ -0,0 +1,3 @@
+{
+    "chat_template": "{%- if tools %}\n    {{- '<|im_start|>system\\n' }}\n    {%- if messages[0].role == 'system' %}\n        {%- if messages[0].content is string %}\n            {{- messages[0].content }}\n        {%- else %}\n            {%- for content in messages[0].content %}\n                {%- if 'text' in content %}\n                    {{- content.text }}\n                {%- endif %}\n            {%- endfor %}\n        {%- endif %}\n        {{- '\\n\\n' }}\n    {%- endif %}\n    {{- \"# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n    {%- for tool in tools %}\n        {{- \"\\n\" }}\n        {{- tool | tojson }}\n    {%- endfor %}\n    {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n    {%- if messages[0].role == 'system' %}\n        {{- '<|im_start|>system\\n' }}\n        {%- if messages[0].content is string %}\n            {{- messages[0].content }}\n        {%- else %}\n            {%- for content in messages[0].content %}\n                {%- if 'text' in content %}\n                    {{- content.text }}\n                {%- endif %}\n            {%- endfor %}\n        {%- endif %}\n        {{- '<|im_end|>\\n' }}\n    {%- endif %}\n{%- endif %}\n{%- set image_count = namespace(value=0) %}\n{%- set video_count = namespace(value=0) %}\n{%- for message in messages %}\n    {%- if message.role == \"user\" %}\n        {{- '<|im_start|>' + message.role + '\\n' }}\n        {%- if message.content is string %}\n            {{- message.content }}\n        {%- else %}\n            {%- for content in message.content %}\n                {%- if content.type == 'image' or 'image' in content or 'image_url' in content %}\n                    {%- set image_count.value = image_count.value + 1 %}\n                    {%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%}\n                    <|vision_start|><|image_pad|><|vision_end|>\n                {%- elif content.type == 'video' or 'video' in content %}\n                    {%- set video_count.value = video_count.value + 1 %}\n                    {%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%}\n                    <|vision_start|><|video_pad|><|vision_end|>\n                {%- elif 'text' in content %}\n                    {{- content.text }}\n                {%- endif %}\n            {%- endfor %}\n        {%- endif %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {{- '<|im_start|>' + message.role + '\\n' }}\n        {%- if message.content is string %}\n            {{- message.content }}\n        {%- else %}\n            {%- for content_item in message.content %}\n                {%- if 'text' in content_item %}\n                    {{- content_item.text }}\n                {%- endif %}\n            {%- endfor %}\n        {%- endif %}\n        {%- if message.tool_calls %}\n            {%- for tool_call in message.tool_calls %}\n                {%- if (loop.first and message.content) or (not loop.first) %}\n                    {{- '\\n' }}\n                {%- endif %}\n                {%- if tool_call.function %}\n                    {%- set tool_call = tool_call.function %}\n                {%- endif %}\n                {{- '<tool_call>\\n{\"name\": \"' }}\n                {{- tool_call.name }}\n                {{- '\", \"arguments\": ' }}\n                {%- if tool_call.arguments is string %}\n                    {{- tool_call.arguments }}\n                {%- else %}\n                    {{- tool_call.arguments | tojson }}\n                {%- endif %}\n                {{- '}\\n</tool_call>' }}\n            {%- endfor %}\n        {%- endif %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"tool\" %}\n        {%- if loop.first or (messages[loop.index0 - 1].role != \"tool\") %}\n            {{- '<|im_start|>user' }}\n        {%- endif %}\n        {{- '\\n<tool_response>\\n' }}\n        {%- if message.content is string %}\n            {{- message.content }}\n        {%- else %}\n            {%- for content in message.content %}\n                {%- if content.type == 'image' or 'image' in content or 'image_url' in content %}\n                    {%- set image_count.value = image_count.value + 1 %}\n                    {%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%}\n                    <|vision_start|><|image_pad|><|vision_end|>\n                {%- elif content.type == 'video' or 'video' in content %}\n                    {%- set video_count.value = video_count.value + 1 %}\n                    {%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%}\n                    <|vision_start|><|video_pad|><|vision_end|>\n                {%- elif 'text' in content %}\n                    {{- content.text }}\n                {%- endif %}\n            {%- endfor %}\n        {%- endif %}\n        {{- '\\n</tool_response>' }}\n        {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n            {{- '<|im_end|>\\n' }}\n        {%- endif %}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n"
+}

text_encoder/config.json

@@ -0,0 +1,62 @@
+{
+  "architectures": [
+    "Qwen3VLForConditionalGeneration"
+  ],
+  "image_token_id": 151655,
+  "model_type": "qwen3_vl",
+  "text_config": {
+    "attention_bias": false,
+    "attention_dropout": 0.0,
+    "bos_token_id": 151643,
+    "dtype": "bfloat16",
+    "eos_token_id": 151645,
+    "head_dim": 128,
+    "hidden_act": "silu",
+    "hidden_size": 5120,
+    "initializer_range": 0.02,
+    "intermediate_size": 25600,
+    "max_position_embeddings": 262144,
+    "model_type": "qwen3_vl_text",
+    "num_attention_heads": 64,
+    "num_hidden_layers": 64,
+    "num_key_value_heads": 8,
+    "rms_norm_eps": 1e-06,
+    "rope_scaling": {
+      "mrope_interleaved": true,
+      "mrope_section": [
+        24,
+        20,
+        20
+      ],
+      "rope_type": "default"
+    },
+    "rope_theta": 5000000,
+    "use_cache": true,
+    "vocab_size": 151936
+  },
+  "tie_word_embeddings": false,
+  "transformers_version": "4.57.0.dev0",
+  "video_token_id": 151656,
+  "vision_config": {
+    "deepstack_visual_indexes": [
+      8,
+      16,
+      24
+    ],
+    "depth": 27,
+    "hidden_act": "gelu_pytorch_tanh",
+    "hidden_size": 1152,
+    "in_channels": 3,
+    "initializer_range": 0.02,
+    "intermediate_size": 4304,
+    "model_type": "qwen3_vl",
+    "num_heads": 16,
+    "num_position_embeddings": 2304,
+    "out_hidden_size": 5120,
+    "patch_size": 16,
+    "spatial_merge_size": 2,
+    "temporal_patch_size": 2
+  },
+  "vision_end_token_id": 151653,
+  "vision_start_token_id": 151652
+}

text_encoder/model-00001-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6b9dfbc930e505402ae9d7e5091a9d7d656cda5f34614f01cfe70bfb0cca27cb
+size 4932328944

text_encoder/model-00002-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d8bb44b4ff303fe76fe9e894022fb3dc71b15a2e716592790fe0e3c3e60478fa
+size 4875990528

text_encoder/model-00003-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:54f22e8b3168f8dc962fac0d313607ebf52a12b433d4cf3098a0d82d9f042940
+size 4875990552

text_encoder/model-00006-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:82f05620d1f718a90c362b221d6a184ff1a0f53301d706882d3df49695fa1974
+size 4875990584

text_encoder/model-00007-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fb91da8cb01ff4de3eef0eab1c3e769a734b3a1aafc61734068638a0d6c86934
+size 4875990584

text_encoder/model-00011-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3820ffe8d8d6477f6fe8d614ef3c87abb264ee39accebf43a1507b970d80946f
+size 4875990584

text_encoder/model-00014-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e45b6c9998c77ee5a6577f9f47bc76416c1d4d387169e50c4c9d3134ea51b13b
+size 3270697008

text_encoder/model.safetensors.index.json

@@ -0,0 +1,1065 @@
+{
+  "metadata": {
+    "total_size": 66714780128
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00014-of-00014.safetensors",
+    "model.language_model.embed_tokens.weight": "model-00001-of-00014.safetensors",
+    "model.language_model.layers.0.input_layernorm.weight": "model-00001-of-00014.safetensors",
+    "model.language_model.layers.0.mlp.down_proj.weight": "model-00001-of-00014.safetensors",
+    "model.language_model.layers.0.mlp.gate_proj.weight": "model-00001-of-00014.safetensors",
+    "model.language_model.layers.0.mlp.up_proj.weight": "model-00001-of-00014.safetensors",
+    "model.language_model.layers.0.post_attention_layernorm.weight": "model-00001-of-00014.safetensors",
+    "model.language_model.layers.0.self_attn.k_norm.weight": "model-00001-of-00014.safetensors",
+    "model.language_model.layers.0.self_attn.k_proj.weight": "model-00001-of-00014.safetensors",
+    "model.language_model.layers.0.self_attn.o_proj.weight": "model-00001-of-00014.safetensors",
+    "model.language_model.layers.0.self_attn.q_norm.weight": "model-00001-of-00014.safetensors",
+    "model.language_model.layers.0.self_attn.q_proj.weight": "model-00001-of-00014.safetensors",
+    "model.language_model.layers.0.self_attn.v_proj.weight": "model-00001-of-00014.safetensors",
+    "model.language_model.layers.1.input_layernorm.weight": "model-00001-of-00014.safetensors",
+    "model.language_model.layers.1.mlp.down_proj.weight": "model-00001-of-00014.safetensors",
+    "model.language_model.layers.1.mlp.gate_proj.weight": "model-00001-of-00014.safetensors",
+    "model.language_model.layers.1.mlp.up_proj.weight": "model-00001-of-00014.safetensors",
+    "model.language_model.layers.1.post_attention_layernorm.weight": "model-00001-of-00014.safetensors",
+    "model.language_model.layers.1.self_attn.k_norm.weight": "model-00001-of-00014.safetensors",
+    "model.language_model.layers.1.self_attn.k_proj.weight": "model-00001-of-00014.safetensors",
+    "model.language_model.layers.1.self_attn.o_proj.weight": "model-00001-of-00014.safetensors",
+    "model.language_model.layers.1.self_attn.q_norm.weight": "model-00001-of-00014.safetensors",
+    "model.language_model.layers.1.self_attn.q_proj.weight": "model-00001-of-00014.safetensors",
+    "model.language_model.layers.1.self_attn.v_proj.weight": "model-00001-of-00014.safetensors",
+    "model.language_model.layers.10.input_layernorm.weight": "model-00003-of-00014.safetensors",
+    "model.language_model.layers.10.mlp.down_proj.weight": "model-00003-of-00014.safetensors",
+    "model.language_model.layers.10.mlp.gate_proj.weight": "model-00003-of-00014.safetensors",
+    "model.language_model.layers.10.mlp.up_proj.weight": "model-00003-of-00014.safetensors",
+    "model.language_model.layers.10.post_attention_layernorm.weight": "model-00003-of-00014.safetensors",
+    "model.language_model.layers.10.self_attn.k_norm.weight": "model-00003-of-00014.safetensors",
+    "model.language_model.layers.10.self_attn.k_proj.weight": "model-00003-of-00014.safetensors",
+    "model.language_model.layers.10.self_attn.o_proj.weight": "model-00003-of-00014.safetensors",
+    "model.language_model.layers.10.self_attn.q_norm.weight": "model-00003-of-00014.safetensors",
+    "model.language_model.layers.10.self_attn.q_proj.weight": "model-00003-of-00014.safetensors",
+    "model.language_model.layers.10.self_attn.v_proj.weight": "model-00003-of-00014.safetensors",
+    "model.language_model.layers.11.input_layernorm.weight": "model-00003-of-00014.safetensors",
+    "model.language_model.layers.11.mlp.down_proj.weight": "model-00003-of-00014.safetensors",
+    "model.language_model.layers.11.mlp.gate_proj.weight": "model-00003-of-00014.safetensors",
+    "model.language_model.layers.11.mlp.up_proj.weight": "model-00003-of-00014.safetensors",
+    "model.language_model.layers.11.post_attention_layernorm.weight": "model-00003-of-00014.safetensors",
+    "model.language_model.layers.11.self_attn.k_norm.weight": "model-00003-of-00014.safetensors",
+    "model.language_model.layers.11.self_attn.k_proj.weight": "model-00003-of-00014.safetensors",
+    "model.language_model.layers.11.self_attn.o_proj.weight": "model-00003-of-00014.safetensors",
+    "model.language_model.layers.11.self_attn.q_norm.weight": "model-00003-of-00014.safetensors",
+    "model.language_model.layers.11.self_attn.q_proj.weight": "model-00003-of-00014.safetensors",
+    "model.language_model.layers.11.self_attn.v_proj.weight": "model-00003-of-00014.safetensors",
+    "model.language_model.layers.12.input_layernorm.weight": "model-00003-of-00014.safetensors",
+    "model.language_model.layers.12.mlp.down_proj.weight": "model-00003-of-00014.safetensors",
+    "model.language_model.layers.12.mlp.gate_proj.weight": "model-00003-of-00014.safetensors",
+    "model.language_model.layers.12.mlp.up_proj.weight": "model-00003-of-00014.safetensors",
+    "model.language_model.layers.12.post_attention_layernorm.weight": "model-00003-of-00014.safetensors",
+    "model.language_model.layers.12.self_attn.k_norm.weight": "model-00003-of-00014.safetensors",
+    "model.language_model.layers.12.self_attn.k_proj.weight": "model-00003-of-00014.safetensors",
+    "model.language_model.layers.12.self_attn.o_proj.weight": "model-00003-of-00014.safetensors",
+    "model.language_model.layers.12.self_attn.q_norm.weight": "model-00003-of-00014.safetensors",
+    "model.language_model.layers.12.self_attn.q_proj.weight": "model-00003-of-00014.safetensors",
+    "model.language_model.layers.12.self_attn.v_proj.weight": "model-00003-of-00014.safetensors",
+    "model.language_model.layers.13.input_layernorm.weight": "model-00003-of-00014.safetensors",
+    "model.language_model.layers.13.mlp.down_proj.weight": "model-00004-of-00014.safetensors",
+    "model.language_model.layers.13.mlp.gate_proj.weight": "model-00003-of-00014.safetensors",
+    "model.language_model.layers.13.mlp.up_proj.weight": "model-00004-of-00014.safetensors",
+    "model.language_model.layers.13.post_attention_layernorm.weight": "model-00003-of-00014.safetensors",
+    "model.language_model.layers.13.self_attn.k_norm.weight": "model-00003-of-00014.safetensors",
+    "model.language_model.layers.13.self_attn.k_proj.weight": "model-00003-of-00014.safetensors",
+    "model.language_model.layers.13.self_attn.o_proj.weight": "model-00003-of-00014.safetensors",
+    "model.language_model.layers.13.self_attn.q_norm.weight": "model-00003-of-00014.safetensors",
+    "model.language_model.layers.13.self_attn.q_proj.weight": "model-00003-of-00014.safetensors",
+    "model.language_model.layers.13.self_attn.v_proj.weight": "model-00003-of-00014.safetensors",
+    "model.language_model.layers.14.input_layernorm.weight": "model-00004-of-00014.safetensors",
+    "model.language_model.layers.14.mlp.down_proj.weight": "model-00004-of-00014.safetensors",
+    "model.language_model.layers.14.mlp.gate_proj.weight": "model-00004-of-00014.safetensors",
+    "model.language_model.layers.14.mlp.up_proj.weight": "model-00004-of-00014.safetensors",
+    "model.language_model.layers.14.post_attention_layernorm.weight": "model-00004-of-00014.safetensors",
+    "model.language_model.layers.14.self_attn.k_norm.weight": "model-00004-of-00014.safetensors",
+    "model.language_model.layers.14.self_attn.k_proj.weight": "model-00004-of-00014.safetensors",
+    "model.language_model.layers.14.self_attn.o_proj.weight": "model-00004-of-00014.safetensors",
+    "model.language_model.layers.14.self_attn.q_norm.weight": "model-00004-of-00014.safetensors",
+    "model.language_model.layers.14.self_attn.q_proj.weight": "model-00004-of-00014.safetensors",
+    "model.language_model.layers.14.self_attn.v_proj.weight": "model-00004-of-00014.safetensors",
+    "model.language_model.layers.15.input_layernorm.weight": "model-00004-of-00014.safetensors",
+    "model.language_model.layers.15.mlp.down_proj.weight": "model-00004-of-00014.safetensors",
+    "model.language_model.layers.15.mlp.gate_proj.weight": "model-00004-of-00014.safetensors",
+    "model.language_model.layers.15.mlp.up_proj.weight": "model-00004-of-00014.safetensors",
+    "model.language_model.layers.15.post_attention_layernorm.weight": "model-00004-of-00014.safetensors",
+    "model.language_model.layers.15.self_attn.k_norm.weight": "model-00004-of-00014.safetensors",
+    "model.language_model.layers.15.self_attn.k_proj.weight": "model-00004-of-00014.safetensors",
+    "model.language_model.layers.15.self_attn.o_proj.weight": "model-00004-of-00014.safetensors",
+    "model.language_model.layers.15.self_attn.q_norm.weight": "model-00004-of-00014.safetensors",
+    "model.language_model.layers.15.self_attn.q_proj.weight": "model-00004-of-00014.safetensors",
+    "model.language_model.layers.15.self_attn.v_proj.weight": "model-00004-of-00014.safetensors",
+    "model.language_model.layers.16.input_layernorm.weight": "model-00004-of-00014.safetensors",
+    "model.language_model.layers.16.mlp.down_proj.weight": "model-00004-of-00014.safetensors",
+    "model.language_model.layers.16.mlp.gate_proj.weight": "model-00004-of-00014.safetensors",
+    "model.language_model.layers.16.mlp.up_proj.weight": "model-00004-of-00014.safetensors",
+    "model.language_model.layers.16.post_attention_layernorm.weight": "model-00004-of-00014.safetensors",
+    "model.language_model.layers.16.self_attn.k_norm.weight": "model-00004-of-00014.safetensors",
+    "model.language_model.layers.16.self_attn.k_proj.weight": "model-00004-of-00014.safetensors",
+    "model.language_model.layers.16.self_attn.o_proj.weight": "model-00004-of-00014.safetensors",
+    "model.language_model.layers.16.self_attn.q_norm.weight": "model-00004-of-00014.safetensors",
+    "model.language_model.layers.16.self_attn.q_proj.weight": "model-00004-of-00014.safetensors",
+    "model.language_model.layers.16.self_attn.v_proj.weight": "model-00004-of-00014.safetensors",
+    "model.language_model.layers.17.input_layernorm.weight": "model-00004-of-00014.safetensors",
+    "model.language_model.layers.17.mlp.down_proj.weight": "model-00004-of-00014.safetensors",
+    "model.language_model.layers.17.mlp.gate_proj.weight": "model-00004-of-00014.safetensors",
+    "model.language_model.layers.17.mlp.up_proj.weight": "model-00004-of-00014.safetensors",
+    "model.language_model.layers.17.post_attention_layernorm.weight": "model-00004-of-00014.safetensors",
+    "model.language_model.layers.17.self_attn.k_norm.weight": "model-00004-of-00014.safetensors",
+    "model.language_model.layers.17.self_attn.k_proj.weight": "model-00004-of-00014.safetensors",
+    "model.language_model.layers.17.self_attn.o_proj.weight": "model-00004-of-00014.safetensors",
+    "model.language_model.layers.17.self_attn.q_norm.weight": "model-00004-of-00014.safetensors",
+    "model.language_model.layers.17.self_attn.q_proj.weight": "model-00004-of-00014.safetensors",
+    "model.language_model.layers.17.self_attn.v_proj.weight": "model-00004-of-00014.safetensors",
+    "model.language_model.layers.18.input_layernorm.weight": "model-00004-of-00014.safetensors",
+    "model.language_model.layers.18.mlp.down_proj.weight": "model-00005-of-00014.safetensors",
+    "model.language_model.layers.18.mlp.gate_proj.weight": "model-00004-of-00014.safetensors",
+    "model.language_model.layers.18.mlp.up_proj.weight": "model-00005-of-00014.safetensors",
+    "model.language_model.layers.18.post_attention_layernorm.weight": "model-00004-of-00014.safetensors",
+    "model.language_model.layers.18.self_attn.k_norm.weight": "model-00004-of-00014.safetensors",
+    "model.language_model.layers.18.self_attn.k_proj.weight": "model-00004-of-00014.safetensors",
+    "model.language_model.layers.18.self_attn.o_proj.weight": "model-00004-of-00014.safetensors",
+    "model.language_model.layers.18.self_attn.q_norm.weight": "model-00004-of-00014.safetensors",
+    "model.language_model.layers.18.self_attn.q_proj.weight": "model-00004-of-00014.safetensors",
+    "model.language_model.layers.18.self_attn.v_proj.weight": "model-00004-of-00014.safetensors",
+    "model.language_model.layers.19.input_layernorm.weight": "model-00005-of-00014.safetensors",
+    "model.language_model.layers.19.mlp.down_proj.weight": "model-00005-of-00014.safetensors",
+    "model.language_model.layers.19.mlp.gate_proj.weight": "model-00005-of-00014.safetensors",
+    "model.language_model.layers.19.mlp.up_proj.weight": "model-00005-of-00014.safetensors",
+    "model.language_model.layers.19.post_attention_layernorm.weight": "model-00005-of-00014.safetensors",
+    "model.language_model.layers.19.self_attn.k_norm.weight": "model-00005-of-00014.safetensors",
+    "model.language_model.layers.19.self_attn.k_proj.weight": "model-00005-of-00014.safetensors",
+    "model.language_model.layers.19.self_attn.o_proj.weight": "model-00005-of-00014.safetensors",
+    "model.language_model.layers.19.self_attn.q_norm.weight": "model-00005-of-00014.safetensors",
+    "model.language_model.layers.19.self_attn.q_proj.weight": "model-00005-of-00014.safetensors",
+    "model.language_model.layers.19.self_attn.v_proj.weight": "model-00005-of-00014.safetensors",
+    "model.language_model.layers.2.input_layernorm.weight": "model-00001-of-00014.safetensors",
+    "model.language_model.layers.2.mlp.down_proj.weight": "model-00001-of-00014.safetensors",
+    "model.language_model.layers.2.mlp.gate_proj.weight": "model-00001-of-00014.safetensors",
+    "model.language_model.layers.2.mlp.up_proj.weight": "model-00001-of-00014.safetensors",
+    "model.language_model.layers.2.post_attention_layernorm.weight": "model-00001-of-00014.safetensors",
+    "model.language_model.layers.2.self_attn.k_norm.weight": "model-00001-of-00014.safetensors",
+    "model.language_model.layers.2.self_attn.k_proj.weight": "model-00001-of-00014.safetensors",
+    "model.language_model.layers.2.self_attn.o_proj.weight": "model-00001-of-00014.safetensors",
+    "model.language_model.layers.2.self_attn.q_norm.weight": "model-00001-of-00014.safetensors",
+    "model.language_model.layers.2.self_attn.q_proj.weight": "model-00001-of-00014.safetensors",
+    "model.language_model.layers.2.self_attn.v_proj.weight": "model-00001-of-00014.safetensors",
+    "model.language_model.layers.20.input_layernorm.weight": "model-00005-of-00014.safetensors",
+    "model.language_model.layers.20.mlp.down_proj.weight": "model-00005-of-00014.safetensors",
+    "model.language_model.layers.20.mlp.gate_proj.weight": "model-00005-of-00014.safetensors",
+    "model.language_model.layers.20.mlp.up_proj.weight": "model-00005-of-00014.safetensors",
+    "model.language_model.layers.20.post_attention_layernorm.weight": "model-00005-of-00014.safetensors",
+    "model.language_model.layers.20.self_attn.k_norm.weight": "model-00005-of-00014.safetensors",
+    "model.language_model.layers.20.self_attn.k_proj.weight": "model-00005-of-00014.safetensors",
+    "model.language_model.layers.20.self_attn.o_proj.weight": "model-00005-of-00014.safetensors",
+    "model.language_model.layers.20.self_attn.q_norm.weight": "model-00005-of-00014.safetensors",
+    "model.language_model.layers.20.self_attn.q_proj.weight": "model-00005-of-00014.safetensors",
+    "model.language_model.layers.20.self_attn.v_proj.weight": "model-00005-of-00014.safetensors",
+    "model.language_model.layers.21.input_layernorm.weight": "model-00005-of-00014.safetensors",
+    "model.language_model.layers.21.mlp.down_proj.weight": "model-00005-of-00014.safetensors",
+    "model.language_model.layers.21.mlp.gate_proj.weight": "model-00005-of-00014.safetensors",
+    "model.language_model.layers.21.mlp.up_proj.weight": "model-00005-of-00014.safetensors",
+    "model.language_model.layers.21.post_attention_layernorm.weight": "model-00005-of-00014.safetensors",
+    "model.language_model.layers.21.self_attn.k_norm.weight": "model-00005-of-00014.safetensors",
+    "model.language_model.layers.21.self_attn.k_proj.weight": "model-00005-of-00014.safetensors",
+    "model.language_model.layers.21.self_attn.o_proj.weight": "model-00005-of-00014.safetensors",
+    "model.language_model.layers.21.self_attn.q_norm.weight": "model-00005-of-00014.safetensors",
+    "model.language_model.layers.21.self_attn.q_proj.weight": "model-00005-of-00014.safetensors",
+    "model.language_model.layers.21.self_attn.v_proj.weight": "model-00005-of-00014.safetensors",
+    "model.language_model.layers.22.input_layernorm.weight": "model-00005-of-00014.safetensors",
+    "model.language_model.layers.22.mlp.down_proj.weight": "model-00005-of-00014.safetensors",
+    "model.language_model.layers.22.mlp.gate_proj.weight": "model-00005-of-00014.safetensors",
+    "model.language_model.layers.22.mlp.up_proj.weight": "model-00005-of-00014.safetensors",
+    "model.language_model.layers.22.post_attention_layernorm.weight": "model-00005-of-00014.safetensors",
+    "model.language_model.layers.22.self_attn.k_norm.weight": "model-00005-of-00014.safetensors",
+    "model.language_model.layers.22.self_attn.k_proj.weight": "model-00005-of-00014.safetensors",
+    "model.language_model.layers.22.self_attn.o_proj.weight": "model-00005-of-00014.safetensors",
+    "model.language_model.layers.22.self_attn.q_norm.weight": "model-00005-of-00014.safetensors",
+    "model.language_model.layers.22.self_attn.q_proj.weight": "model-00005-of-00014.safetensors",
+    "model.language_model.layers.22.self_attn.v_proj.weight": "model-00005-of-00014.safetensors",
+    "model.language_model.layers.23.input_layernorm.weight": "model-00005-of-00014.safetensors",
+    "model.language_model.layers.23.mlp.down_proj.weight": "model-00006-of-00014.safetensors",
+    "model.language_model.layers.23.mlp.gate_proj.weight": "model-00005-of-00014.safetensors",
+    "model.language_model.layers.23.mlp.up_proj.weight": "model-00006-of-00014.safetensors",
+    "model.language_model.layers.23.post_attention_layernorm.weight": "model-00005-of-00014.safetensors",
+    "model.language_model.layers.23.self_attn.k_norm.weight": "model-00005-of-00014.safetensors",
+    "model.language_model.layers.23.self_attn.k_proj.weight": "model-00005-of-00014.safetensors",
+    "model.language_model.layers.23.self_attn.o_proj.weight": "model-00005-of-00014.safetensors",
+    "model.language_model.layers.23.self_attn.q_norm.weight": "model-00005-of-00014.safetensors",
+    "model.language_model.layers.23.self_attn.q_proj.weight": "model-00005-of-00014.safetensors",
+    "model.language_model.layers.23.self_attn.v_proj.weight": "model-00005-of-00014.safetensors",
+    "model.language_model.layers.24.input_layernorm.weight": "model-00006-of-00014.safetensors",
+    "model.language_model.layers.24.mlp.down_proj.weight": "model-00006-of-00014.safetensors",
+    "model.language_model.layers.24.mlp.gate_proj.weight": "model-00006-of-00014.safetensors",
+    "model.language_model.layers.24.mlp.up_proj.weight": "model-00006-of-00014.safetensors",
+    "model.language_model.layers.24.post_attention_layernorm.weight": "model-00006-of-00014.safetensors",
+    "model.language_model.layers.24.self_attn.k_norm.weight": "model-00006-of-00014.safetensors",
+    "model.language_model.layers.24.self_attn.k_proj.weight": "model-00006-of-00014.safetensors",
+    "model.language_model.layers.24.self_attn.o_proj.weight": "model-00006-of-00014.safetensors",
+    "model.language_model.layers.24.self_attn.q_norm.weight": "model-00006-of-00014.safetensors",
+    "model.language_model.layers.24.self_attn.q_proj.weight": "model-00006-of-00014.safetensors",
+    "model.language_model.layers.24.self_attn.v_proj.weight": "model-00006-of-00014.safetensors",
+    "model.language_model.layers.25.input_layernorm.weight": "model-00006-of-00014.safetensors",
+    "model.language_model.layers.25.mlp.down_proj.weight": "model-00006-of-00014.safetensors",
+    "model.language_model.layers.25.mlp.gate_proj.weight": "model-00006-of-00014.safetensors",
+    "model.language_model.layers.25.mlp.up_proj.weight": "model-00006-of-00014.safetensors",
+    "model.language_model.layers.25.post_attention_layernorm.weight": "model-00006-of-00014.safetensors",
+    "model.language_model.layers.25.self_attn.k_norm.weight": "model-00006-of-00014.safetensors",
+    "model.language_model.layers.25.self_attn.k_proj.weight": "model-00006-of-00014.safetensors",
+    "model.language_model.layers.25.self_attn.o_proj.weight": "model-00006-of-00014.safetensors",
+    "model.language_model.layers.25.self_attn.q_norm.weight": "model-00006-of-00014.safetensors",
+    "model.language_model.layers.25.self_attn.q_proj.weight": "model-00006-of-00014.safetensors",
+    "model.language_model.layers.25.self_attn.v_proj.weight": "model-00006-of-00014.safetensors",
+    "model.language_model.layers.26.input_layernorm.weight": "model-00006-of-00014.safetensors",
+    "model.language_model.layers.26.mlp.down_proj.weight": "model-00006-of-00014.safetensors",
+    "model.language_model.layers.26.mlp.gate_proj.weight": "model-00006-of-00014.safetensors",
+    "model.language_model.layers.26.mlp.up_proj.weight": "model-00006-of-00014.safetensors",
+    "model.language_model.layers.26.post_attention_layernorm.weight": "model-00006-of-00014.safetensors",
+    "model.language_model.layers.26.self_attn.k_norm.weight": "model-00006-of-00014.safetensors",
+    "model.language_model.layers.26.self_attn.k_proj.weight": "model-00006-of-00014.safetensors",
+    "model.language_model.layers.26.self_attn.o_proj.weight": "model-00006-of-00014.safetensors",
+    "model.language_model.layers.26.self_attn.q_norm.weight": "model-00006-of-00014.safetensors",
+    "model.language_model.layers.26.self_attn.q_proj.weight": "model-00006-of-00014.safetensors",
+    "model.language_model.layers.26.self_attn.v_proj.weight": "model-00006-of-00014.safetensors",
+    "model.language_model.layers.27.input_layernorm.weight": "model-00006-of-00014.safetensors",
+    "model.language_model.layers.27.mlp.down_proj.weight": "model-00006-of-00014.safetensors",
+    "model.language_model.layers.27.mlp.gate_proj.weight": "model-00006-of-00014.safetensors",
+    "model.language_model.layers.27.mlp.up_proj.weight": "model-00006-of-00014.safetensors",
+    "model.language_model.layers.27.post_attention_layernorm.weight": "model-00006-of-00014.safetensors",
+    "model.language_model.layers.27.self_attn.k_norm.weight": "model-00006-of-00014.safetensors",
+    "model.language_model.layers.27.self_attn.k_proj.weight": "model-00006-of-00014.safetensors",
+    "model.language_model.layers.27.self_attn.o_proj.weight": "model-00006-of-00014.safetensors",
+    "model.language_model.layers.27.self_attn.q_norm.weight": "model-00006-of-00014.safetensors",
+    "model.language_model.layers.27.self_attn.q_proj.weight": "model-00006-of-00014.safetensors",
+    "model.language_model.layers.27.self_attn.v_proj.weight": "model-00006-of-00014.safetensors",
+    "model.language_model.layers.28.input_layernorm.weight": "model-00006-of-00014.safetensors",
+    "model.language_model.layers.28.mlp.down_proj.weight": "model-00007-of-00014.safetensors",
+    "model.language_model.layers.28.mlp.gate_proj.weight": "model-00006-of-00014.safetensors",
+    "model.language_model.layers.28.mlp.up_proj.weight": "model-00007-of-00014.safetensors",
+    "model.language_model.layers.28.post_attention_layernorm.weight": "model-00006-of-00014.safetensors",
+    "model.language_model.layers.28.self_attn.k_norm.weight": "model-00006-of-00014.safetensors",
+    "model.language_model.layers.28.self_attn.k_proj.weight": "model-00006-of-00014.safetensors",
+    "model.language_model.layers.28.self_attn.o_proj.weight": "model-00006-of-00014.safetensors",
+    "model.language_model.layers.28.self_attn.q_norm.weight": "model-00006-of-00014.safetensors",
+    "model.language_model.layers.28.self_attn.q_proj.weight": "model-00006-of-00014.safetensors",
+    "model.language_model.layers.28.self_attn.v_proj.weight": "model-00006-of-00014.safetensors",
+    "model.language_model.layers.29.input_layernorm.weight": "model-00007-of-00014.safetensors",
+    "model.language_model.layers.29.mlp.down_proj.weight": "model-00007-of-00014.safetensors",
+    "model.language_model.layers.29.mlp.gate_proj.weight": "model-00007-of-00014.safetensors",
+    "model.language_model.layers.29.mlp.up_proj.weight": "model-00007-of-00014.safetensors",
+    "model.language_model.layers.29.post_attention_layernorm.weight": "model-00007-of-00014.safetensors",
+    "model.language_model.layers.29.self_attn.k_norm.weight": "model-00007-of-00014.safetensors",
+    "model.language_model.layers.29.self_attn.k_proj.weight": "model-00007-of-00014.safetensors",
+    "model.language_model.layers.29.self_attn.o_proj.weight": "model-00007-of-00014.safetensors",
+    "model.language_model.layers.29.self_attn.q_norm.weight": "model-00007-of-00014.safetensors",
+    "model.language_model.layers.29.self_attn.q_proj.weight": "model-00007-of-00014.safetensors",
+    "model.language_model.layers.29.self_attn.v_proj.weight": "model-00007-of-00014.safetensors",
+    "model.language_model.layers.3.input_layernorm.weight": "model-00001-of-00014.safetensors",
+    "model.language_model.layers.3.mlp.down_proj.weight": "model-00002-of-00014.safetensors",
+    "model.language_model.layers.3.mlp.gate_proj.weight": "model-00001-of-00014.safetensors",
+    "model.language_model.layers.3.mlp.up_proj.weight": "model-00002-of-00014.safetensors",
+    "model.language_model.layers.3.post_attention_layernorm.weight": "model-00001-of-00014.safetensors",
+    "model.language_model.layers.3.self_attn.k_norm.weight": "model-00001-of-00014.safetensors",
+    "model.language_model.layers.3.self_attn.k_proj.weight": "model-00001-of-00014.safetensors",
+    "model.language_model.layers.3.self_attn.o_proj.weight": "model-00001-of-00014.safetensors",
+    "model.language_model.layers.3.self_attn.q_norm.weight": "model-00001-of-00014.safetensors",
+    "model.language_model.layers.3.self_attn.q_proj.weight": "model-00001-of-00014.safetensors",
+    "model.language_model.layers.3.self_attn.v_proj.weight": "model-00001-of-00014.safetensors",
+    "model.language_model.layers.30.input_layernorm.weight": "model-00007-of-00014.safetensors",
+    "model.language_model.layers.30.mlp.down_proj.weight": "model-00007-of-00014.safetensors",
+    "model.language_model.layers.30.mlp.gate_proj.weight": "model-00007-of-00014.safetensors",
+    "model.language_model.layers.30.mlp.up_proj.weight": "model-00007-of-00014.safetensors",
+    "model.language_model.layers.30.post_attention_layernorm.weight": "model-00007-of-00014.safetensors",
+    "model.language_model.layers.30.self_attn.k_norm.weight": "model-00007-of-00014.safetensors",
+    "model.language_model.layers.30.self_attn.k_proj.weight": "model-00007-of-00014.safetensors",
+    "model.language_model.layers.30.self_attn.o_proj.weight": "model-00007-of-00014.safetensors",
+    "model.language_model.layers.30.self_attn.q_norm.weight": "model-00007-of-00014.safetensors",
+    "model.language_model.layers.30.self_attn.q_proj.weight": "model-00007-of-00014.safetensors",
+    "model.language_model.layers.30.self_attn.v_proj.weight": "model-00007-of-00014.safetensors",
+    "model.language_model.layers.31.input_layernorm.weight": "model-00007-of-00014.safetensors",
+    "model.language_model.layers.31.mlp.down_proj.weight": "model-00007-of-00014.safetensors",
+    "model.language_model.layers.31.mlp.gate_proj.weight": "model-00007-of-00014.safetensors",
+    "model.language_model.layers.31.mlp.up_proj.weight": "model-00007-of-00014.safetensors",
+    "model.language_model.layers.31.post_attention_layernorm.weight": "model-00007-of-00014.safetensors",
+    "model.language_model.layers.31.self_attn.k_norm.weight": "model-00007-of-00014.safetensors",
+    "model.language_model.layers.31.self_attn.k_proj.weight": "model-00007-of-00014.safetensors",
+    "model.language_model.layers.31.self_attn.o_proj.weight": "model-00007-of-00014.safetensors",
+    "model.language_model.layers.31.self_attn.q_norm.weight": "model-00007-of-00014.safetensors",
+    "model.language_model.layers.31.self_attn.q_proj.weight": "model-00007-of-00014.safetensors",
+    "model.language_model.layers.31.self_attn.v_proj.weight": "model-00007-of-00014.safetensors",
+    "model.language_model.layers.32.input_layernorm.weight": "model-00007-of-00014.safetensors",
+    "model.language_model.layers.32.mlp.down_proj.weight": "model-00007-of-00014.safetensors",
+    "model.language_model.layers.32.mlp.gate_proj.weight": "model-00007-of-00014.safetensors",
+    "model.language_model.layers.32.mlp.up_proj.weight": "model-00007-of-00014.safetensors",
+    "model.language_model.layers.32.post_attention_layernorm.weight": "model-00007-of-00014.safetensors",
+    "model.language_model.layers.32.self_attn.k_norm.weight": "model-00007-of-00014.safetensors",
+    "model.language_model.layers.32.self_attn.k_proj.weight": "model-00007-of-00014.safetensors",
+    "model.language_model.layers.32.self_attn.o_proj.weight": "model-00007-of-00014.safetensors",
+    "model.language_model.layers.32.self_attn.q_norm.weight": "model-00007-of-00014.safetensors",
+    "model.language_model.layers.32.self_attn.q_proj.weight": "model-00007-of-00014.safetensors",
+    "model.language_model.layers.32.self_attn.v_proj.weight": "model-00007-of-00014.safetensors",
+    "model.language_model.layers.33.input_layernorm.weight": "model-00007-of-00014.safetensors",
+    "model.language_model.layers.33.mlp.down_proj.weight": "model-00008-of-00014.safetensors",
+    "model.language_model.layers.33.mlp.gate_proj.weight": "model-00007-of-00014.safetensors",
+    "model.language_model.layers.33.mlp.up_proj.weight": "model-00008-of-00014.safetensors",
+    "model.language_model.layers.33.post_attention_layernorm.weight": "model-00007-of-00014.safetensors",
+    "model.language_model.layers.33.self_attn.k_norm.weight": "model-00007-of-00014.safetensors",
+    "model.language_model.layers.33.self_attn.k_proj.weight": "model-00007-of-00014.safetensors",
+    "model.language_model.layers.33.self_attn.o_proj.weight": "model-00007-of-00014.safetensors",
+    "model.language_model.layers.33.self_attn.q_norm.weight": "model-00007-of-00014.safetensors",
+    "model.language_model.layers.33.self_attn.q_proj.weight": "model-00007-of-00014.safetensors",
+    "model.language_model.layers.33.self_attn.v_proj.weight": "model-00007-of-00014.safetensors",
+    "model.language_model.layers.34.input_layernorm.weight": "model-00008-of-00014.safetensors",
+    "model.language_model.layers.34.mlp.down_proj.weight": "model-00008-of-00014.safetensors",
+    "model.language_model.layers.34.mlp.gate_proj.weight": "model-00008-of-00014.safetensors",
+    "model.language_model.layers.34.mlp.up_proj.weight": "model-00008-of-00014.safetensors",
+    "model.language_model.layers.34.post_attention_layernorm.weight": "model-00008-of-00014.safetensors",
+    "model.language_model.layers.34.self_attn.k_norm.weight": "model-00008-of-00014.safetensors",
+    "model.language_model.layers.34.self_attn.k_proj.weight": "model-00008-of-00014.safetensors",
+    "model.language_model.layers.34.self_attn.o_proj.weight": "model-00008-of-00014.safetensors",
+    "model.language_model.layers.34.self_attn.q_norm.weight": "model-00008-of-00014.safetensors",
+    "model.language_model.layers.34.self_attn.q_proj.weight": "model-00008-of-00014.safetensors",
+    "model.language_model.layers.34.self_attn.v_proj.weight": "model-00008-of-00014.safetensors",
+    "model.language_model.layers.35.input_layernorm.weight": "model-00008-of-00014.safetensors",
+    "model.language_model.layers.35.mlp.down_proj.weight": "model-00008-of-00014.safetensors",
+    "model.language_model.layers.35.mlp.gate_proj.weight": "model-00008-of-00014.safetensors",
+    "model.language_model.layers.35.mlp.up_proj.weight": "model-00008-of-00014.safetensors",
+    "model.language_model.layers.35.post_attention_layernorm.weight": "model-00008-of-00014.safetensors",
+    "model.language_model.layers.35.self_attn.k_norm.weight": "model-00008-of-00014.safetensors",
+    "model.language_model.layers.35.self_attn.k_proj.weight": "model-00008-of-00014.safetensors",
+    "model.language_model.layers.35.self_attn.o_proj.weight": "model-00008-of-00014.safetensors",
+    "model.language_model.layers.35.self_attn.q_norm.weight": "model-00008-of-00014.safetensors",
+    "model.language_model.layers.35.self_attn.q_proj.weight": "model-00008-of-00014.safetensors",
+    "model.language_model.layers.35.self_attn.v_proj.weight": "model-00008-of-00014.safetensors",
+    "model.language_model.layers.36.input_layernorm.weight": "model-00008-of-00014.safetensors",
+    "model.language_model.layers.36.mlp.down_proj.weight": "model-00008-of-00014.safetensors",
+    "model.language_model.layers.36.mlp.gate_proj.weight": "model-00008-of-00014.safetensors",
+    "model.language_model.layers.36.mlp.up_proj.weight": "model-00008-of-00014.safetensors",
+    "model.language_model.layers.36.post_attention_layernorm.weight": "model-00008-of-00014.safetensors",
+    "model.language_model.layers.36.self_attn.k_norm.weight": "model-00008-of-00014.safetensors",
+    "model.language_model.layers.36.self_attn.k_proj.weight": "model-00008-of-00014.safetensors",
+    "model.language_model.layers.36.self_attn.o_proj.weight": "model-00008-of-00014.safetensors",
+    "model.language_model.layers.36.self_attn.q_norm.weight": "model-00008-of-00014.safetensors",
+    "model.language_model.layers.36.self_attn.q_proj.weight": "model-00008-of-00014.safetensors",
+    "model.language_model.layers.36.self_attn.v_proj.weight": "model-00008-of-00014.safetensors",
+    "model.language_model.layers.37.input_layernorm.weight": "model-00008-of-00014.safetensors",
+    "model.language_model.layers.37.mlp.down_proj.weight": "model-00008-of-00014.safetensors",
+    "model.language_model.layers.37.mlp.gate_proj.weight": "model-00008-of-00014.safetensors",
+    "model.language_model.layers.37.mlp.up_proj.weight": "model-00008-of-00014.safetensors",
+    "model.language_model.layers.37.post_attention_layernorm.weight": "model-00008-of-00014.safetensors",
+    "model.language_model.layers.37.self_attn.k_norm.weight": "model-00008-of-00014.safetensors",
+    "model.language_model.layers.37.self_attn.k_proj.weight": "model-00008-of-00014.safetensors",
+    "model.language_model.layers.37.self_attn.o_proj.weight": "model-00008-of-00014.safetensors",
+    "model.language_model.layers.37.self_attn.q_norm.weight": "model-00008-of-00014.safetensors",
+    "model.language_model.layers.37.self_attn.q_proj.weight": "model-00008-of-00014.safetensors",
+    "model.language_model.layers.37.self_attn.v_proj.weight": "model-00008-of-00014.safetensors",
+    "model.language_model.layers.38.input_layernorm.weight": "model-00008-of-00014.safetensors",
+    "model.language_model.layers.38.mlp.down_proj.weight": "model-00009-of-00014.safetensors",
+    "model.language_model.layers.38.mlp.gate_proj.weight": "model-00008-of-00014.safetensors",
+    "model.language_model.layers.38.mlp.up_proj.weight": "model-00009-of-00014.safetensors",
+    "model.language_model.layers.38.post_attention_layernorm.weight": "model-00008-of-00014.safetensors",
+    "model.language_model.layers.38.self_attn.k_norm.weight": "model-00008-of-00014.safetensors",
+    "model.language_model.layers.38.self_attn.k_proj.weight": "model-00008-of-00014.safetensors",
+    "model.language_model.layers.38.self_attn.o_proj.weight": "model-00008-of-00014.safetensors",
+    "model.language_model.layers.38.self_attn.q_norm.weight": "model-00008-of-00014.safetensors",
+    "model.language_model.layers.38.self_attn.q_proj.weight": "model-00008-of-00014.safetensors",
+    "model.language_model.layers.38.self_attn.v_proj.weight": "model-00008-of-00014.safetensors",
+    "model.language_model.layers.39.input_layernorm.weight": "model-00009-of-00014.safetensors",
+    "model.language_model.layers.39.mlp.down_proj.weight": "model-00009-of-00014.safetensors",
+    "model.language_model.layers.39.mlp.gate_proj.weight": "model-00009-of-00014.safetensors",
+    "model.language_model.layers.39.mlp.up_proj.weight": "model-00009-of-00014.safetensors",
+    "model.language_model.layers.39.post_attention_layernorm.weight": "model-00009-of-00014.safetensors",
+    "model.language_model.layers.39.self_attn.k_norm.weight": "model-00009-of-00014.safetensors",
+    "model.language_model.layers.39.self_attn.k_proj.weight": "model-00009-of-00014.safetensors",
+    "model.language_model.layers.39.self_attn.o_proj.weight": "model-00009-of-00014.safetensors",
+    "model.language_model.layers.39.self_attn.q_norm.weight": "model-00009-of-00014.safetensors",
+    "model.language_model.layers.39.self_attn.q_proj.weight": "model-00009-of-00014.safetensors",
+    "model.language_model.layers.39.self_attn.v_proj.weight": "model-00009-of-00014.safetensors",
+    "model.language_model.layers.4.input_layernorm.weight": "model-00002-of-00014.safetensors",
+    "model.language_model.layers.4.mlp.down_proj.weight": "model-00002-of-00014.safetensors",
+    "model.language_model.layers.4.mlp.gate_proj.weight": "model-00002-of-00014.safetensors",
+    "model.language_model.layers.4.mlp.up_proj.weight": "model-00002-of-00014.safetensors",
+    "model.language_model.layers.4.post_attention_layernorm.weight": "model-00002-of-00014.safetensors",
+    "model.language_model.layers.4.self_attn.k_norm.weight": "model-00002-of-00014.safetensors",
+    "model.language_model.layers.4.self_attn.k_proj.weight": "model-00002-of-00014.safetensors",
+    "model.language_model.layers.4.self_attn.o_proj.weight": "model-00002-of-00014.safetensors",
+    "model.language_model.layers.4.self_attn.q_norm.weight": "model-00002-of-00014.safetensors",
+    "model.language_model.layers.4.self_attn.q_proj.weight": "model-00002-of-00014.safetensors",
+    "model.language_model.layers.4.self_attn.v_proj.weight": "model-00002-of-00014.safetensors",
+    "model.language_model.layers.40.input_layernorm.weight": "model-00009-of-00014.safetensors",
+    "model.language_model.layers.40.mlp.down_proj.weight": "model-00009-of-00014.safetensors",
+    "model.language_model.layers.40.mlp.gate_proj.weight": "model-00009-of-00014.safetensors",
+    "model.language_model.layers.40.mlp.up_proj.weight": "model-00009-of-00014.safetensors",
+    "model.language_model.layers.40.post_attention_layernorm.weight": "model-00009-of-00014.safetensors",
+    "model.language_model.layers.40.self_attn.k_norm.weight": "model-00009-of-00014.safetensors",
+    "model.language_model.layers.40.self_attn.k_proj.weight": "model-00009-of-00014.safetensors",
+    "model.language_model.layers.40.self_attn.o_proj.weight": "model-00009-of-00014.safetensors",
+    "model.language_model.layers.40.self_attn.q_norm.weight": "model-00009-of-00014.safetensors",
+    "model.language_model.layers.40.self_attn.q_proj.weight": "model-00009-of-00014.safetensors",
+    "model.language_model.layers.40.self_attn.v_proj.weight": "model-00009-of-00014.safetensors",
+    "model.language_model.layers.41.input_layernorm.weight": "model-00009-of-00014.safetensors",
+    "model.language_model.layers.41.mlp.down_proj.weight": "model-00009-of-00014.safetensors",
+    "model.language_model.layers.41.mlp.gate_proj.weight": "model-00009-of-00014.safetensors",
+    "model.language_model.layers.41.mlp.up_proj.weight": "model-00009-of-00014.safetensors",
+    "model.language_model.layers.41.post_attention_layernorm.weight": "model-00009-of-00014.safetensors",
+    "model.language_model.layers.41.self_attn.k_norm.weight": "model-00009-of-00014.safetensors",
+    "model.language_model.layers.41.self_attn.k_proj.weight": "model-00009-of-00014.safetensors",
+    "model.language_model.layers.41.self_attn.o_proj.weight": "model-00009-of-00014.safetensors",
+    "model.language_model.layers.41.self_attn.q_norm.weight": "model-00009-of-00014.safetensors",
+    "model.language_model.layers.41.self_attn.q_proj.weight": "model-00009-of-00014.safetensors",
+    "model.language_model.layers.41.self_attn.v_proj.weight": "model-00009-of-00014.safetensors",
+    "model.language_model.layers.42.input_layernorm.weight": "model-00009-of-00014.safetensors",
+    "model.language_model.layers.42.mlp.down_proj.weight": "model-00009-of-00014.safetensors",
+    "model.language_model.layers.42.mlp.gate_proj.weight": "model-00009-of-00014.safetensors",
+    "model.language_model.layers.42.mlp.up_proj.weight": "model-00009-of-00014.safetensors",
+    "model.language_model.layers.42.post_attention_layernorm.weight": "model-00009-of-00014.safetensors",
+    "model.language_model.layers.42.self_attn.k_norm.weight": "model-00009-of-00014.safetensors",
+    "model.language_model.layers.42.self_attn.k_proj.weight": "model-00009-of-00014.safetensors",
+    "model.language_model.layers.42.self_attn.o_proj.weight": "model-00009-of-00014.safetensors",
+    "model.language_model.layers.42.self_attn.q_norm.weight": "model-00009-of-00014.safetensors",
+    "model.language_model.layers.42.self_attn.q_proj.weight": "model-00009-of-00014.safetensors",
+    "model.language_model.layers.42.self_attn.v_proj.weight": "model-00009-of-00014.safetensors",
+    "model.language_model.layers.43.input_layernorm.weight": "model-00009-of-00014.safetensors",
+    "model.language_model.layers.43.mlp.down_proj.weight": "model-00010-of-00014.safetensors",
+    "model.language_model.layers.43.mlp.gate_proj.weight": "model-00009-of-00014.safetensors",
+    "model.language_model.layers.43.mlp.up_proj.weight": "model-00010-of-00014.safetensors",
+    "model.language_model.layers.43.post_attention_layernorm.weight": "model-00009-of-00014.safetensors",
+    "model.language_model.layers.43.self_attn.k_norm.weight": "model-00009-of-00014.safetensors",
+    "model.language_model.layers.43.self_attn.k_proj.weight": "model-00009-of-00014.safetensors",
+    "model.language_model.layers.43.self_attn.o_proj.weight": "model-00009-of-00014.safetensors",
+    "model.language_model.layers.43.self_attn.q_norm.weight": "model-00009-of-00014.safetensors",
+    "model.language_model.layers.43.self_attn.q_proj.weight": "model-00009-of-00014.safetensors",
+    "model.language_model.layers.43.self_attn.v_proj.weight": "model-00009-of-00014.safetensors",
+    "model.language_model.layers.44.input_layernorm.weight": "model-00010-of-00014.safetensors",
+    "model.language_model.layers.44.mlp.down_proj.weight": "model-00010-of-00014.safetensors",
+    "model.language_model.layers.44.mlp.gate_proj.weight": "model-00010-of-00014.safetensors",
+    "model.language_model.layers.44.mlp.up_proj.weight": "model-00010-of-00014.safetensors",
+    "model.language_model.layers.44.post_attention_layernorm.weight": "model-00010-of-00014.safetensors",
+    "model.language_model.layers.44.self_attn.k_norm.weight": "model-00010-of-00014.safetensors",
+    "model.language_model.layers.44.self_attn.k_proj.weight": "model-00010-of-00014.safetensors",
+    "model.language_model.layers.44.self_attn.o_proj.weight": "model-00010-of-00014.safetensors",
+    "model.language_model.layers.44.self_attn.q_norm.weight": "model-00010-of-00014.safetensors",
+    "model.language_model.layers.44.self_attn.q_proj.weight": "model-00010-of-00014.safetensors",
+    "model.language_model.layers.44.self_attn.v_proj.weight": "model-00010-of-00014.safetensors",
+    "model.language_model.layers.45.input_layernorm.weight": "model-00010-of-00014.safetensors",
+    "model.language_model.layers.45.mlp.down_proj.weight": "model-00010-of-00014.safetensors",
+    "model.language_model.layers.45.mlp.gate_proj.weight": "model-00010-of-00014.safetensors",
+    "model.language_model.layers.45.mlp.up_proj.weight": "model-00010-of-00014.safetensors",
+    "model.language_model.layers.45.post_attention_layernorm.weight": "model-00010-of-00014.safetensors",
+    "model.language_model.layers.45.self_attn.k_norm.weight": "model-00010-of-00014.safetensors",
+    "model.language_model.layers.45.self_attn.k_proj.weight": "model-00010-of-00014.safetensors",
+    "model.language_model.layers.45.self_attn.o_proj.weight": "model-00010-of-00014.safetensors",
+    "model.language_model.layers.45.self_attn.q_norm.weight": "model-00010-of-00014.safetensors",
+    "model.language_model.layers.45.self_attn.q_proj.weight": "model-00010-of-00014.safetensors",
+    "model.language_model.layers.45.self_attn.v_proj.weight": "model-00010-of-00014.safetensors",
+    "model.language_model.layers.46.input_layernorm.weight": "model-00010-of-00014.safetensors",
+    "model.language_model.layers.46.mlp.down_proj.weight": "model-00010-of-00014.safetensors",
+    "model.language_model.layers.46.mlp.gate_proj.weight": "model-00010-of-00014.safetensors",
+    "model.language_model.layers.46.mlp.up_proj.weight": "model-00010-of-00014.safetensors",
+    "model.language_model.layers.46.post_attention_layernorm.weight": "model-00010-of-00014.safetensors",
+    "model.language_model.layers.46.self_attn.k_norm.weight": "model-00010-of-00014.safetensors",
+    "model.language_model.layers.46.self_attn.k_proj.weight": "model-00010-of-00014.safetensors",
+    "model.language_model.layers.46.self_attn.o_proj.weight": "model-00010-of-00014.safetensors",
+    "model.language_model.layers.46.self_attn.q_norm.weight": "model-00010-of-00014.safetensors",
+    "model.language_model.layers.46.self_attn.q_proj.weight": "model-00010-of-00014.safetensors",
+    "model.language_model.layers.46.self_attn.v_proj.weight": "model-00010-of-00014.safetensors",
+    "model.language_model.layers.47.input_layernorm.weight": "model-00010-of-00014.safetensors",
+    "model.language_model.layers.47.mlp.down_proj.weight": "model-00010-of-00014.safetensors",
+    "model.language_model.layers.47.mlp.gate_proj.weight": "model-00010-of-00014.safetensors",
+    "model.language_model.layers.47.mlp.up_proj.weight": "model-00010-of-00014.safetensors",
+    "model.language_model.layers.47.post_attention_layernorm.weight": "model-00010-of-00014.safetensors",
+    "model.language_model.layers.47.self_attn.k_norm.weight": "model-00010-of-00014.safetensors",
+    "model.language_model.layers.47.self_attn.k_proj.weight": "model-00010-of-00014.safetensors",
+    "model.language_model.layers.47.self_attn.o_proj.weight": "model-00010-of-00014.safetensors",
+    "model.language_model.layers.47.self_attn.q_norm.weight": "model-00010-of-00014.safetensors",
+    "model.language_model.layers.47.self_attn.q_proj.weight": "model-00010-of-00014.safetensors",
+    "model.language_model.layers.47.self_attn.v_proj.weight": "model-00010-of-00014.safetensors",
+    "model.language_model.layers.48.input_layernorm.weight": "model-00010-of-00014.safetensors",
+    "model.language_model.layers.48.mlp.down_proj.weight": "model-00011-of-00014.safetensors",
+    "model.language_model.layers.48.mlp.gate_proj.weight": "model-00010-of-00014.safetensors",
+    "model.language_model.layers.48.mlp.up_proj.weight": "model-00011-of-00014.safetensors",
+    "model.language_model.layers.48.post_attention_layernorm.weight": "model-00010-of-00014.safetensors",
+    "model.language_model.layers.48.self_attn.k_norm.weight": "model-00010-of-00014.safetensors",
+    "model.language_model.layers.48.self_attn.k_proj.weight": "model-00010-of-00014.safetensors",
+    "model.language_model.layers.48.self_attn.o_proj.weight": "model-00010-of-00014.safetensors",
+    "model.language_model.layers.48.self_attn.q_norm.weight": "model-00010-of-00014.safetensors",
+    "model.language_model.layers.48.self_attn.q_proj.weight": "model-00010-of-00014.safetensors",
+    "model.language_model.layers.48.self_attn.v_proj.weight": "model-00010-of-00014.safetensors",
+    "model.language_model.layers.49.input_layernorm.weight": "model-00011-of-00014.safetensors",
+    "model.language_model.layers.49.mlp.down_proj.weight": "model-00011-of-00014.safetensors",
+    "model.language_model.layers.49.mlp.gate_proj.weight": "model-00011-of-00014.safetensors",
+    "model.language_model.layers.49.mlp.up_proj.weight": "model-00011-of-00014.safetensors",
+    "model.language_model.layers.49.post_attention_layernorm.weight": "model-00011-of-00014.safetensors",
+    "model.language_model.layers.49.self_attn.k_norm.weight": "model-00011-of-00014.safetensors",
+    "model.language_model.layers.49.self_attn.k_proj.weight": "model-00011-of-00014.safetensors",
+    "model.language_model.layers.49.self_attn.o_proj.weight": "model-00011-of-00014.safetensors",
+    "model.language_model.layers.49.self_attn.q_norm.weight": "model-00011-of-00014.safetensors",
+    "model.language_model.layers.49.self_attn.q_proj.weight": "model-00011-of-00014.safetensors",
+    "model.language_model.layers.49.self_attn.v_proj.weight": "model-00011-of-00014.safetensors",
+    "model.language_model.layers.5.input_layernorm.weight": "model-00002-of-00014.safetensors",
+    "model.language_model.layers.5.mlp.down_proj.weight": "model-00002-of-00014.safetensors",
+    "model.language_model.layers.5.mlp.gate_proj.weight": "model-00002-of-00014.safetensors",
+    "model.language_model.layers.5.mlp.up_proj.weight": "model-00002-of-00014.safetensors",
+    "model.language_model.layers.5.post_attention_layernorm.weight": "model-00002-of-00014.safetensors",
+    "model.language_model.layers.5.self_attn.k_norm.weight": "model-00002-of-00014.safetensors",
+    "model.language_model.layers.5.self_attn.k_proj.weight": "model-00002-of-00014.safetensors",
+    "model.language_model.layers.5.self_attn.o_proj.weight": "model-00002-of-00014.safetensors",
+    "model.language_model.layers.5.self_attn.q_norm.weight": "model-00002-of-00014.safetensors",
+    "model.language_model.layers.5.self_attn.q_proj.weight": "model-00002-of-00014.safetensors",
+    "model.language_model.layers.5.self_attn.v_proj.weight": "model-00002-of-00014.safetensors",
+    "model.language_model.layers.50.input_layernorm.weight": "model-00011-of-00014.safetensors",
+    "model.language_model.layers.50.mlp.down_proj.weight": "model-00011-of-00014.safetensors",
+    "model.language_model.layers.50.mlp.gate_proj.weight": "model-00011-of-00014.safetensors",
+    "model.language_model.layers.50.mlp.up_proj.weight": "model-00011-of-00014.safetensors",
+    "model.language_model.layers.50.post_attention_layernorm.weight": "model-00011-of-00014.safetensors",
+    "model.language_model.layers.50.self_attn.k_norm.weight": "model-00011-of-00014.safetensors",
+    "model.language_model.layers.50.self_attn.k_proj.weight": "model-00011-of-00014.safetensors",
+    "model.language_model.layers.50.self_attn.o_proj.weight": "model-00011-of-00014.safetensors",
+    "model.language_model.layers.50.self_attn.q_norm.weight": "model-00011-of-00014.safetensors",
+    "model.language_model.layers.50.self_attn.q_proj.weight": "model-00011-of-00014.safetensors",
+    "model.language_model.layers.50.self_attn.v_proj.weight": "model-00011-of-00014.safetensors",
+    "model.language_model.layers.51.input_layernorm.weight": "model-00011-of-00014.safetensors",
+    "model.language_model.layers.51.mlp.down_proj.weight": "model-00011-of-00014.safetensors",
+    "model.language_model.layers.51.mlp.gate_proj.weight": "model-00011-of-00014.safetensors",
+    "model.language_model.layers.51.mlp.up_proj.weight": "model-00011-of-00014.safetensors",
+    "model.language_model.layers.51.post_attention_layernorm.weight": "model-00011-of-00014.safetensors",
+    "model.language_model.layers.51.self_attn.k_norm.weight": "model-00011-of-00014.safetensors",
+    "model.language_model.layers.51.self_attn.k_proj.weight": "model-00011-of-00014.safetensors",
+    "model.language_model.layers.51.self_attn.o_proj.weight": "model-00011-of-00014.safetensors",
+    "model.language_model.layers.51.self_attn.q_norm.weight": "model-00011-of-00014.safetensors",
+    "model.language_model.layers.51.self_attn.q_proj.weight": "model-00011-of-00014.safetensors",
+    "model.language_model.layers.51.self_attn.v_proj.weight": "model-00011-of-00014.safetensors",
+    "model.language_model.layers.52.input_layernorm.weight": "model-00011-of-00014.safetensors",
+    "model.language_model.layers.52.mlp.down_proj.weight": "model-00011-of-00014.safetensors",
+    "model.language_model.layers.52.mlp.gate_proj.weight": "model-00011-of-00014.safetensors",
+    "model.language_model.layers.52.mlp.up_proj.weight": "model-00011-of-00014.safetensors",
+    "model.language_model.layers.52.post_attention_layernorm.weight": "model-00011-of-00014.safetensors",
+    "model.language_model.layers.52.self_attn.k_norm.weight": "model-00011-of-00014.safetensors",
+    "model.language_model.layers.52.self_attn.k_proj.weight": "model-00011-of-00014.safetensors",
+    "model.language_model.layers.52.self_attn.o_proj.weight": "model-00011-of-00014.safetensors",
+    "model.language_model.layers.52.self_attn.q_norm.weight": "model-00011-of-00014.safetensors",
+    "model.language_model.layers.52.self_attn.q_proj.weight": "model-00011-of-00014.safetensors",
+    "model.language_model.layers.52.self_attn.v_proj.weight": "model-00011-of-00014.safetensors",
+    "model.language_model.layers.53.input_layernorm.weight": "model-00011-of-00014.safetensors",
+    "model.language_model.layers.53.mlp.down_proj.weight": "model-00012-of-00014.safetensors",
+    "model.language_model.layers.53.mlp.gate_proj.weight": "model-00011-of-00014.safetensors",
+    "model.language_model.layers.53.mlp.up_proj.weight": "model-00012-of-00014.safetensors",
+    "model.language_model.layers.53.post_attention_layernorm.weight": "model-00011-of-00014.safetensors",
+    "model.language_model.layers.53.self_attn.k_norm.weight": "model-00011-of-00014.safetensors",
+    "model.language_model.layers.53.self_attn.k_proj.weight": "model-00011-of-00014.safetensors",
+    "model.language_model.layers.53.self_attn.o_proj.weight": "model-00011-of-00014.safetensors",
+    "model.language_model.layers.53.self_attn.q_norm.weight": "model-00011-of-00014.safetensors",
+    "model.language_model.layers.53.self_attn.q_proj.weight": "model-00011-of-00014.safetensors",
+    "model.language_model.layers.53.self_attn.v_proj.weight": "model-00011-of-00014.safetensors",
+    "model.language_model.layers.54.input_layernorm.weight": "model-00012-of-00014.safetensors",
+    "model.language_model.layers.54.mlp.down_proj.weight": "model-00012-of-00014.safetensors",
+    "model.language_model.layers.54.mlp.gate_proj.weight": "model-00012-of-00014.safetensors",
+    "model.language_model.layers.54.mlp.up_proj.weight": "model-00012-of-00014.safetensors",
+    "model.language_model.layers.54.post_attention_layernorm.weight": "model-00012-of-00014.safetensors",
+    "model.language_model.layers.54.self_attn.k_norm.weight": "model-00012-of-00014.safetensors",
+    "model.language_model.layers.54.self_attn.k_proj.weight": "model-00012-of-00014.safetensors",
+    "model.language_model.layers.54.self_attn.o_proj.weight": "model-00012-of-00014.safetensors",
+    "model.language_model.layers.54.self_attn.q_norm.weight": "model-00012-of-00014.safetensors",
+    "model.language_model.layers.54.self_attn.q_proj.weight": "model-00012-of-00014.safetensors",
+    "model.language_model.layers.54.self_attn.v_proj.weight": "model-00012-of-00014.safetensors",
+    "model.language_model.layers.55.input_layernorm.weight": "model-00012-of-00014.safetensors",
+    "model.language_model.layers.55.mlp.down_proj.weight": "model-00012-of-00014.safetensors",
+    "model.language_model.layers.55.mlp.gate_proj.weight": "model-00012-of-00014.safetensors",
+    "model.language_model.layers.55.mlp.up_proj.weight": "model-00012-of-00014.safetensors",
+    "model.language_model.layers.55.post_attention_layernorm.weight": "model-00012-of-00014.safetensors",
+    "model.language_model.layers.55.self_attn.k_norm.weight": "model-00012-of-00014.safetensors",
+    "model.language_model.layers.55.self_attn.k_proj.weight": "model-00012-of-00014.safetensors",
+    "model.language_model.layers.55.self_attn.o_proj.weight": "model-00012-of-00014.safetensors",
+    "model.language_model.layers.55.self_attn.q_norm.weight": "model-00012-of-00014.safetensors",
+    "model.language_model.layers.55.self_attn.q_proj.weight": "model-00012-of-00014.safetensors",
+    "model.language_model.layers.55.self_attn.v_proj.weight": "model-00012-of-00014.safetensors",
+    "model.language_model.layers.56.input_layernorm.weight": "model-00012-of-00014.safetensors",
+    "model.language_model.layers.56.mlp.down_proj.weight": "model-00012-of-00014.safetensors",
+    "model.language_model.layers.56.mlp.gate_proj.weight": "model-00012-of-00014.safetensors",
+    "model.language_model.layers.56.mlp.up_proj.weight": "model-00012-of-00014.safetensors",
+    "model.language_model.layers.56.post_attention_layernorm.weight": "model-00012-of-00014.safetensors",
+    "model.language_model.layers.56.self_attn.k_norm.weight": "model-00012-of-00014.safetensors",
+    "model.language_model.layers.56.self_attn.k_proj.weight": "model-00012-of-00014.safetensors",
+    "model.language_model.layers.56.self_attn.o_proj.weight": "model-00012-of-00014.safetensors",
+    "model.language_model.layers.56.self_attn.q_norm.weight": "model-00012-of-00014.safetensors",
+    "model.language_model.layers.56.self_attn.q_proj.weight": "model-00012-of-00014.safetensors",
+    "model.language_model.layers.56.self_attn.v_proj.weight": "model-00012-of-00014.safetensors",
+    "model.language_model.layers.57.input_layernorm.weight": "model-00012-of-00014.safetensors",
+    "model.language_model.layers.57.mlp.down_proj.weight": "model-00012-of-00014.safetensors",
+    "model.language_model.layers.57.mlp.gate_proj.weight": "model-00012-of-00014.safetensors",
+    "model.language_model.layers.57.mlp.up_proj.weight": "model-00012-of-00014.safetensors",
+    "model.language_model.layers.57.post_attention_layernorm.weight": "model-00012-of-00014.safetensors",
+    "model.language_model.layers.57.self_attn.k_norm.weight": "model-00012-of-00014.safetensors",
+    "model.language_model.layers.57.self_attn.k_proj.weight": "model-00012-of-00014.safetensors",
+    "model.language_model.layers.57.self_attn.o_proj.weight": "model-00012-of-00014.safetensors",
+    "model.language_model.layers.57.self_attn.q_norm.weight": "model-00012-of-00014.safetensors",
+    "model.language_model.layers.57.self_attn.q_proj.weight": "model-00012-of-00014.safetensors",
+    "model.language_model.layers.57.self_attn.v_proj.weight": "model-00012-of-00014.safetensors",
+    "model.language_model.layers.58.input_layernorm.weight": "model-00012-of-00014.safetensors",
+    "model.language_model.layers.58.mlp.down_proj.weight": "model-00013-of-00014.safetensors",
+    "model.language_model.layers.58.mlp.gate_proj.weight": "model-00012-of-00014.safetensors",
+    "model.language_model.layers.58.mlp.up_proj.weight": "model-00013-of-00014.safetensors",
+    "model.language_model.layers.58.post_attention_layernorm.weight": "model-00012-of-00014.safetensors",
+    "model.language_model.layers.58.self_attn.k_norm.weight": "model-00012-of-00014.safetensors",
+    "model.language_model.layers.58.self_attn.k_proj.weight": "model-00012-of-00014.safetensors",
+    "model.language_model.layers.58.self_attn.o_proj.weight": "model-00012-of-00014.safetensors",
+    "model.language_model.layers.58.self_attn.q_norm.weight": "model-00012-of-00014.safetensors",
+    "model.language_model.layers.58.self_attn.q_proj.weight": "model-00012-of-00014.safetensors",
+    "model.language_model.layers.58.self_attn.v_proj.weight": "model-00012-of-00014.safetensors",
+    "model.language_model.layers.59.input_layernorm.weight": "model-00013-of-00014.safetensors",
+    "model.language_model.layers.59.mlp.down_proj.weight": "model-00013-of-00014.safetensors",
+    "model.language_model.layers.59.mlp.gate_proj.weight": "model-00013-of-00014.safetensors",
+    "model.language_model.layers.59.mlp.up_proj.weight": "model-00013-of-00014.safetensors",
+    "model.language_model.layers.59.post_attention_layernorm.weight": "model-00013-of-00014.safetensors",
+    "model.language_model.layers.59.self_attn.k_norm.weight": "model-00013-of-00014.safetensors",
+    "model.language_model.layers.59.self_attn.k_proj.weight": "model-00013-of-00014.safetensors",
+    "model.language_model.layers.59.self_attn.o_proj.weight": "model-00013-of-00014.safetensors",
+    "model.language_model.layers.59.self_attn.q_norm.weight": "model-00013-of-00014.safetensors",
+    "model.language_model.layers.59.self_attn.q_proj.weight": "model-00013-of-00014.safetensors",
+    "model.language_model.layers.59.self_attn.v_proj.weight": "model-00013-of-00014.safetensors",
+    "model.language_model.layers.6.input_layernorm.weight": "model-00002-of-00014.safetensors",
+    "model.language_model.layers.6.mlp.down_proj.weight": "model-00002-of-00014.safetensors",
+    "model.language_model.layers.6.mlp.gate_proj.weight": "model-00002-of-00014.safetensors",
+    "model.language_model.layers.6.mlp.up_proj.weight": "model-00002-of-00014.safetensors",
+    "model.language_model.layers.6.post_attention_layernorm.weight": "model-00002-of-00014.safetensors",
+    "model.language_model.layers.6.self_attn.k_norm.weight": "model-00002-of-00014.safetensors",
+    "model.language_model.layers.6.self_attn.k_proj.weight": "model-00002-of-00014.safetensors",
+    "model.language_model.layers.6.self_attn.o_proj.weight": "model-00002-of-00014.safetensors",
+    "model.language_model.layers.6.self_attn.q_norm.weight": "model-00002-of-00014.safetensors",
+    "model.language_model.layers.6.self_attn.q_proj.weight": "model-00002-of-00014.safetensors",
+    "model.language_model.layers.6.self_attn.v_proj.weight": "model-00002-of-00014.safetensors",
+    "model.language_model.layers.60.input_layernorm.weight": "model-00013-of-00014.safetensors",
+    "model.language_model.layers.60.mlp.down_proj.weight": "model-00013-of-00014.safetensors",
+    "model.language_model.layers.60.mlp.gate_proj.weight": "model-00013-of-00014.safetensors",
+    "model.language_model.layers.60.mlp.up_proj.weight": "model-00013-of-00014.safetensors",
+    "model.language_model.layers.60.post_attention_layernorm.weight": "model-00013-of-00014.safetensors",
+    "model.language_model.layers.60.self_attn.k_norm.weight": "model-00013-of-00014.safetensors",
+    "model.language_model.layers.60.self_attn.k_proj.weight": "model-00013-of-00014.safetensors",
+    "model.language_model.layers.60.self_attn.o_proj.weight": "model-00013-of-00014.safetensors",
+    "model.language_model.layers.60.self_attn.q_norm.weight": "model-00013-of-00014.safetensors",
+    "model.language_model.layers.60.self_attn.q_proj.weight": "model-00013-of-00014.safetensors",
+    "model.language_model.layers.60.self_attn.v_proj.weight": "model-00013-of-00014.safetensors",
+    "model.language_model.layers.61.input_layernorm.weight": "model-00013-of-00014.safetensors",
+    "model.language_model.layers.61.mlp.down_proj.weight": "model-00013-of-00014.safetensors",
+    "model.language_model.layers.61.mlp.gate_proj.weight": "model-00013-of-00014.safetensors",
+    "model.language_model.layers.61.mlp.up_proj.weight": "model-00013-of-00014.safetensors",
+    "model.language_model.layers.61.post_attention_layernorm.weight": "model-00013-of-00014.safetensors",
+    "model.language_model.layers.61.self_attn.k_norm.weight": "model-00013-of-00014.safetensors",
+    "model.language_model.layers.61.self_attn.k_proj.weight": "model-00013-of-00014.safetensors",
+    "model.language_model.layers.61.self_attn.o_proj.weight": "model-00013-of-00014.safetensors",
+    "model.language_model.layers.61.self_attn.q_norm.weight": "model-00013-of-00014.safetensors",
+    "model.language_model.layers.61.self_attn.q_proj.weight": "model-00013-of-00014.safetensors",
+    "model.language_model.layers.61.self_attn.v_proj.weight": "model-00013-of-00014.safetensors",
+    "model.language_model.layers.62.input_layernorm.weight": "model-00013-of-00014.safetensors",
+    "model.language_model.layers.62.mlp.down_proj.weight": "model-00013-of-00014.safetensors",
+    "model.language_model.layers.62.mlp.gate_proj.weight": "model-00013-of-00014.safetensors",
+    "model.language_model.layers.62.mlp.up_proj.weight": "model-00013-of-00014.safetensors",
+    "model.language_model.layers.62.post_attention_layernorm.weight": "model-00013-of-00014.safetensors",
+    "model.language_model.layers.62.self_attn.k_norm.weight": "model-00013-of-00014.safetensors",
+    "model.language_model.layers.62.self_attn.k_proj.weight": "model-00013-of-00014.safetensors",
+    "model.language_model.layers.62.self_attn.o_proj.weight": "model-00013-of-00014.safetensors",
+    "model.language_model.layers.62.self_attn.q_norm.weight": "model-00013-of-00014.safetensors",
+    "model.language_model.layers.62.self_attn.q_proj.weight": "model-00013-of-00014.safetensors",
+    "model.language_model.layers.62.self_attn.v_proj.weight": "model-00013-of-00014.safetensors",
+    "model.language_model.layers.63.input_layernorm.weight": "model-00013-of-00014.safetensors",
+    "model.language_model.layers.63.mlp.down_proj.weight": "model-00014-of-00014.safetensors",
+    "model.language_model.layers.63.mlp.gate_proj.weight": "model-00013-of-00014.safetensors",
+    "model.language_model.layers.63.mlp.up_proj.weight": "model-00014-of-00014.safetensors",
+    "model.language_model.layers.63.post_attention_layernorm.weight": "model-00013-of-00014.safetensors",
+    "model.language_model.layers.63.self_attn.k_norm.weight": "model-00013-of-00014.safetensors",
+    "model.language_model.layers.63.self_attn.k_proj.weight": "model-00013-of-00014.safetensors",
+    "model.language_model.layers.63.self_attn.o_proj.weight": "model-00013-of-00014.safetensors",
+    "model.language_model.layers.63.self_attn.q_norm.weight": "model-00013-of-00014.safetensors",
+    "model.language_model.layers.63.self_attn.q_proj.weight": "model-00013-of-00014.safetensors",
+    "model.language_model.layers.63.self_attn.v_proj.weight": "model-00013-of-00014.safetensors",
+    "model.language_model.layers.7.input_layernorm.weight": "model-00002-of-00014.safetensors",
+    "model.language_model.layers.7.mlp.down_proj.weight": "model-00002-of-00014.safetensors",
+    "model.language_model.layers.7.mlp.gate_proj.weight": "model-00002-of-00014.safetensors",
+    "model.language_model.layers.7.mlp.up_proj.weight": "model-00002-of-00014.safetensors",
+    "model.language_model.layers.7.post_attention_layernorm.weight": "model-00002-of-00014.safetensors",
+    "model.language_model.layers.7.self_attn.k_norm.weight": "model-00002-of-00014.safetensors",
+    "model.language_model.layers.7.self_attn.k_proj.weight": "model-00002-of-00014.safetensors",
+    "model.language_model.layers.7.self_attn.o_proj.weight": "model-00002-of-00014.safetensors",
+    "model.language_model.layers.7.self_attn.q_norm.weight": "model-00002-of-00014.safetensors",
+    "model.language_model.layers.7.self_attn.q_proj.weight": "model-00002-of-00014.safetensors",
+    "model.language_model.layers.7.self_attn.v_proj.weight": "model-00002-of-00014.safetensors",
+    "model.language_model.layers.8.input_layernorm.weight": "model-00002-of-00014.safetensors",
+    "model.language_model.layers.8.mlp.down_proj.weight": "model-00003-of-00014.safetensors",
+    "model.language_model.layers.8.mlp.gate_proj.weight": "model-00002-of-00014.safetensors",
+    "model.language_model.layers.8.mlp.up_proj.weight": "model-00003-of-00014.safetensors",
+    "model.language_model.layers.8.post_attention_layernorm.weight": "model-00002-of-00014.safetensors",
+    "model.language_model.layers.8.self_attn.k_norm.weight": "model-00002-of-00014.safetensors",
+    "model.language_model.layers.8.self_attn.k_proj.weight": "model-00002-of-00014.safetensors",
+    "model.language_model.layers.8.self_attn.o_proj.weight": "model-00002-of-00014.safetensors",
+    "model.language_model.layers.8.self_attn.q_norm.weight": "model-00002-of-00014.safetensors",
+    "model.language_model.layers.8.self_attn.q_proj.weight": "model-00002-of-00014.safetensors",
+    "model.language_model.layers.8.self_attn.v_proj.weight": "model-00002-of-00014.safetensors",
+    "model.language_model.layers.9.input_layernorm.weight": "model-00003-of-00014.safetensors",
+    "model.language_model.layers.9.mlp.down_proj.weight": "model-00003-of-00014.safetensors",
+    "model.language_model.layers.9.mlp.gate_proj.weight": "model-00003-of-00014.safetensors",
+    "model.language_model.layers.9.mlp.up_proj.weight": "model-00003-of-00014.safetensors",
+    "model.language_model.layers.9.post_attention_layernorm.weight": "model-00003-of-00014.safetensors",
+    "model.language_model.layers.9.self_attn.k_norm.weight": "model-00003-of-00014.safetensors",
+    "model.language_model.layers.9.self_attn.k_proj.weight": "model-00003-of-00014.safetensors",
+    "model.language_model.layers.9.self_attn.o_proj.weight": "model-00003-of-00014.safetensors",
+    "model.language_model.layers.9.self_attn.q_norm.weight": "model-00003-of-00014.safetensors",
+    "model.language_model.layers.9.self_attn.q_proj.weight": "model-00003-of-00014.safetensors",
+    "model.language_model.layers.9.self_attn.v_proj.weight": "model-00003-of-00014.safetensors",
+    "model.language_model.norm.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.0.attn.proj.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.0.attn.proj.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.0.attn.qkv.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.0.attn.qkv.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.0.mlp.linear_fc1.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.0.mlp.linear_fc1.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.0.mlp.linear_fc2.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.0.mlp.linear_fc2.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.0.norm1.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.0.norm1.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.0.norm2.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.0.norm2.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.1.attn.proj.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.1.attn.proj.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.1.attn.qkv.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.1.attn.qkv.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.1.mlp.linear_fc1.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.1.mlp.linear_fc1.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.1.mlp.linear_fc2.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.1.mlp.linear_fc2.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.1.norm1.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.1.norm1.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.1.norm2.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.1.norm2.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.10.attn.proj.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.10.attn.proj.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.10.attn.qkv.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.10.attn.qkv.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.10.mlp.linear_fc1.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.10.mlp.linear_fc1.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.10.mlp.linear_fc2.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.10.mlp.linear_fc2.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.10.norm1.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.10.norm1.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.10.norm2.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.10.norm2.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.11.attn.proj.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.11.attn.proj.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.11.attn.qkv.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.11.attn.qkv.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.11.mlp.linear_fc1.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.11.mlp.linear_fc1.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.11.mlp.linear_fc2.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.11.mlp.linear_fc2.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.11.norm1.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.11.norm1.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.11.norm2.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.11.norm2.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.12.attn.proj.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.12.attn.proj.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.12.attn.qkv.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.12.attn.qkv.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.12.mlp.linear_fc1.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.12.mlp.linear_fc1.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.12.mlp.linear_fc2.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.12.mlp.linear_fc2.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.12.norm1.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.12.norm1.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.12.norm2.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.12.norm2.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.13.attn.proj.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.13.attn.proj.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.13.attn.qkv.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.13.attn.qkv.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.13.mlp.linear_fc1.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.13.mlp.linear_fc1.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.13.mlp.linear_fc2.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.13.mlp.linear_fc2.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.13.norm1.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.13.norm1.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.13.norm2.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.13.norm2.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.14.attn.proj.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.14.attn.proj.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.14.attn.qkv.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.14.attn.qkv.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.14.mlp.linear_fc1.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.14.mlp.linear_fc1.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.14.mlp.linear_fc2.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.14.mlp.linear_fc2.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.14.norm1.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.14.norm1.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.14.norm2.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.14.norm2.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.15.attn.proj.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.15.attn.proj.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.15.attn.qkv.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.15.attn.qkv.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.15.mlp.linear_fc1.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.15.mlp.linear_fc1.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.15.mlp.linear_fc2.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.15.mlp.linear_fc2.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.15.norm1.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.15.norm1.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.15.norm2.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.15.norm2.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.16.attn.proj.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.16.attn.proj.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.16.attn.qkv.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.16.attn.qkv.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.16.mlp.linear_fc1.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.16.mlp.linear_fc1.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.16.mlp.linear_fc2.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.16.mlp.linear_fc2.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.16.norm1.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.16.norm1.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.16.norm2.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.16.norm2.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.17.attn.proj.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.17.attn.proj.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.17.attn.qkv.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.17.attn.qkv.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.17.mlp.linear_fc1.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.17.mlp.linear_fc1.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.17.mlp.linear_fc2.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.17.mlp.linear_fc2.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.17.norm1.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.17.norm1.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.17.norm2.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.17.norm2.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.18.attn.proj.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.18.attn.proj.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.18.attn.qkv.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.18.attn.qkv.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.18.mlp.linear_fc1.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.18.mlp.linear_fc1.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.18.mlp.linear_fc2.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.18.mlp.linear_fc2.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.18.norm1.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.18.norm1.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.18.norm2.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.18.norm2.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.19.attn.proj.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.19.attn.proj.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.19.attn.qkv.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.19.attn.qkv.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.19.mlp.linear_fc1.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.19.mlp.linear_fc1.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.19.mlp.linear_fc2.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.19.mlp.linear_fc2.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.19.norm1.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.19.norm1.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.19.norm2.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.19.norm2.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.2.attn.proj.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.2.attn.proj.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.2.attn.qkv.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.2.attn.qkv.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.2.mlp.linear_fc1.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.2.mlp.linear_fc1.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.2.mlp.linear_fc2.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.2.mlp.linear_fc2.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.2.norm1.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.2.norm1.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.2.norm2.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.2.norm2.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.20.attn.proj.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.20.attn.proj.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.20.attn.qkv.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.20.attn.qkv.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.20.mlp.linear_fc1.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.20.mlp.linear_fc1.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.20.mlp.linear_fc2.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.20.mlp.linear_fc2.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.20.norm1.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.20.norm1.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.20.norm2.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.20.norm2.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.21.attn.proj.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.21.attn.proj.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.21.attn.qkv.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.21.attn.qkv.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.21.mlp.linear_fc1.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.21.mlp.linear_fc1.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.21.mlp.linear_fc2.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.21.mlp.linear_fc2.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.21.norm1.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.21.norm1.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.21.norm2.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.21.norm2.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.22.attn.proj.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.22.attn.proj.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.22.attn.qkv.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.22.attn.qkv.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.22.mlp.linear_fc1.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.22.mlp.linear_fc1.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.22.mlp.linear_fc2.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.22.mlp.linear_fc2.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.22.norm1.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.22.norm1.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.22.norm2.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.22.norm2.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.23.attn.proj.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.23.attn.proj.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.23.attn.qkv.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.23.attn.qkv.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.23.mlp.linear_fc1.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.23.mlp.linear_fc1.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.23.mlp.linear_fc2.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.23.mlp.linear_fc2.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.23.norm1.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.23.norm1.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.23.norm2.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.23.norm2.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.24.attn.proj.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.24.attn.proj.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.24.attn.qkv.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.24.attn.qkv.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.24.mlp.linear_fc1.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.24.mlp.linear_fc1.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.24.mlp.linear_fc2.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.24.mlp.linear_fc2.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.24.norm1.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.24.norm1.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.24.norm2.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.24.norm2.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.25.attn.proj.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.25.attn.proj.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.25.attn.qkv.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.25.attn.qkv.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.25.mlp.linear_fc1.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.25.mlp.linear_fc1.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.25.mlp.linear_fc2.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.25.mlp.linear_fc2.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.25.norm1.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.25.norm1.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.25.norm2.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.25.norm2.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.26.attn.proj.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.26.attn.proj.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.26.attn.qkv.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.26.attn.qkv.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.26.mlp.linear_fc1.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.26.mlp.linear_fc1.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.26.mlp.linear_fc2.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.26.mlp.linear_fc2.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.26.norm1.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.26.norm1.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.26.norm2.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.26.norm2.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.3.attn.proj.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.3.attn.proj.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.3.attn.qkv.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.3.attn.qkv.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.3.mlp.linear_fc1.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.3.mlp.linear_fc1.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.3.mlp.linear_fc2.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.3.mlp.linear_fc2.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.3.norm1.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.3.norm1.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.3.norm2.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.3.norm2.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.4.attn.proj.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.4.attn.proj.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.4.attn.qkv.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.4.attn.qkv.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.4.mlp.linear_fc1.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.4.mlp.linear_fc1.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.4.mlp.linear_fc2.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.4.mlp.linear_fc2.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.4.norm1.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.4.norm1.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.4.norm2.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.4.norm2.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.5.attn.proj.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.5.attn.proj.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.5.attn.qkv.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.5.attn.qkv.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.5.mlp.linear_fc1.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.5.mlp.linear_fc1.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.5.mlp.linear_fc2.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.5.mlp.linear_fc2.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.5.norm1.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.5.norm1.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.5.norm2.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.5.norm2.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.6.attn.proj.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.6.attn.proj.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.6.attn.qkv.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.6.attn.qkv.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.6.mlp.linear_fc1.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.6.mlp.linear_fc1.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.6.mlp.linear_fc2.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.6.mlp.linear_fc2.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.6.norm1.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.6.norm1.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.6.norm2.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.6.norm2.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.7.attn.proj.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.7.attn.proj.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.7.attn.qkv.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.7.attn.qkv.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.7.mlp.linear_fc1.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.7.mlp.linear_fc1.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.7.mlp.linear_fc2.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.7.mlp.linear_fc2.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.7.norm1.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.7.norm1.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.7.norm2.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.7.norm2.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.8.attn.proj.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.8.attn.proj.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.8.attn.qkv.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.8.attn.qkv.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.8.mlp.linear_fc1.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.8.mlp.linear_fc1.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.8.mlp.linear_fc2.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.8.mlp.linear_fc2.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.8.norm1.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.8.norm1.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.8.norm2.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.8.norm2.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.9.attn.proj.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.9.attn.proj.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.9.attn.qkv.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.9.attn.qkv.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.9.mlp.linear_fc1.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.9.mlp.linear_fc1.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.9.mlp.linear_fc2.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.9.mlp.linear_fc2.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.9.norm1.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.9.norm1.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.9.norm2.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.9.norm2.weight": "model-00014-of-00014.safetensors",
+    "model.visual.deepstack_merger_list.0.linear_fc1.bias": "model-00014-of-00014.safetensors",
+    "model.visual.deepstack_merger_list.0.linear_fc1.weight": "model-00014-of-00014.safetensors",
+    "model.visual.deepstack_merger_list.0.linear_fc2.bias": "model-00014-of-00014.safetensors",
+    "model.visual.deepstack_merger_list.0.linear_fc2.weight": "model-00014-of-00014.safetensors",
+    "model.visual.deepstack_merger_list.0.norm.bias": "model-00014-of-00014.safetensors",
+    "model.visual.deepstack_merger_list.0.norm.weight": "model-00014-of-00014.safetensors",
+    "model.visual.deepstack_merger_list.1.linear_fc1.bias": "model-00014-of-00014.safetensors",
+    "model.visual.deepstack_merger_list.1.linear_fc1.weight": "model-00014-of-00014.safetensors",
+    "model.visual.deepstack_merger_list.1.linear_fc2.bias": "model-00014-of-00014.safetensors",
+    "model.visual.deepstack_merger_list.1.linear_fc2.weight": "model-00014-of-00014.safetensors",
+    "model.visual.deepstack_merger_list.1.norm.bias": "model-00014-of-00014.safetensors",
+    "model.visual.deepstack_merger_list.1.norm.weight": "model-00014-of-00014.safetensors",
+    "model.visual.deepstack_merger_list.2.linear_fc1.bias": "model-00014-of-00014.safetensors",
+    "model.visual.deepstack_merger_list.2.linear_fc1.weight": "model-00014-of-00014.safetensors",
+    "model.visual.deepstack_merger_list.2.linear_fc2.bias": "model-00014-of-00014.safetensors",
+    "model.visual.deepstack_merger_list.2.linear_fc2.weight": "model-00014-of-00014.safetensors",
+    "model.visual.deepstack_merger_list.2.norm.bias": "model-00014-of-00014.safetensors",
+    "model.visual.deepstack_merger_list.2.norm.weight": "model-00014-of-00014.safetensors",
+    "model.visual.merger.linear_fc1.bias": "model-00014-of-00014.safetensors",
+    "model.visual.merger.linear_fc1.weight": "model-00014-of-00014.safetensors",
+    "model.visual.merger.linear_fc2.bias": "model-00014-of-00014.safetensors",
+    "model.visual.merger.linear_fc2.weight": "model-00014-of-00014.safetensors",
+    "model.visual.merger.norm.bias": "model-00014-of-00014.safetensors",
+    "model.visual.merger.norm.weight": "model-00014-of-00014.safetensors",
+    "model.visual.patch_embed.proj.bias": "model-00014-of-00014.safetensors",
+    "model.visual.patch_embed.proj.weight": "model-00014-of-00014.safetensors",
+    "model.visual.pos_embed.weight": "model-00014-of-00014.safetensors"
+  }
+}

text_encoder/preprocessor_config.json

@@ -0,0 +1,21 @@
+{
+    "size": {
+        "longest_edge": 16777216,
+        "shortest_edge": 65536
+    },
+    "patch_size": 16,
+    "temporal_patch_size": 2,
+    "merge_size": 2,
+    "image_mean": [
+        0.5,
+        0.5,
+        0.5
+    ],
+    "image_std": [
+        0.5,
+        0.5,
+        0.5
+    ],
+    "processor_class": "Qwen3VLProcessor",
+    "image_processor_type": "Qwen2VLImageProcessorFast"
+}

text_encoder/tokenizer_config.json

@@ -0,0 +1,246 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151665": {
+      "content": "<tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151666": {
+      "content": "</tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151667": {
+      "content": "<think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151668": {
+      "content": "</think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>",
+    "<d>",
+    "</d>",
+    "<|cutoff|>",
+    "<|lyrics_start|>",
+    "<|lyrics_end|>",
+    "<|caption_start|>",
+    "<|caption_end|>"
+  ],
+  "bos_token": null,
+  "chat_template": "{%- if tools %}\n    {{- '<|im_start|>system\\n' }}\n    {%- if messages[0].role == 'system' %}\n        {%- if messages[0].content is string %}\n            {{- messages[0].content }}\n        {%- else %}\n            {%- for content in messages[0].content %}\n                {%- if 'text' in content %}\n                    {{- content.text }}\n                {%- endif %}\n            {%- endfor %}\n        {%- endif %}\n        {{- '\\n\\n' }}\n    {%- endif %}\n    {{- \"# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n    {%- for tool in tools %}\n        {{- \"\\n\" }}\n        {{- tool | tojson }}\n    {%- endfor %}\n    {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n    {%- if messages[0].role == 'system' %}\n        {{- '<|im_start|>system\\n' }}\n        {%- if messages[0].content is string %}\n            {{- messages[0].content }}\n        {%- else %}\n            {%- for content in messages[0].content %}\n                {%- if 'text' in content %}\n                    {{- content.text }}\n                {%- endif %}\n            {%- endfor %}\n        {%- endif %}\n        {{- '<|im_end|>\\n' }}\n    {%- endif %}\n{%- endif %}\n{%- set image_count = namespace(value=0) %}\n{%- set video_count = namespace(value=0) %}\n{%- for message in messages %}\n    {%- if message.role == \"user\" %}\n        {{- '<|im_start|>' + message.role + '\\n' }}\n        {%- if message.content is string %}\n            {{- message.content }}\n        {%- else %}\n            {%- for content in message.content %}\n                {%- if content.type == 'image' or 'image' in content or 'image_url' in content %}\n                    {%- set image_count.value = image_count.value + 1 %}\n                    {%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%}\n                    <|vision_start|><|image_pad|><|vision_end|>\n                {%- elif content.type == 'video' or 'video' in content %}\n                    {%- set video_count.value = video_count.value + 1 %}\n                    {%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%}\n                    <|vision_start|><|video_pad|><|vision_end|>\n                {%- elif 'text' in content %}\n                    {{- content.text }}\n                {%- endif %}\n            {%- endfor %}\n        {%- endif %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {{- '<|im_start|>' + message.role + '\\n' }}\n        {%- if message.content is string %}\n            {{- message.content }}\n        {%- else %}\n            {%- for content_item in message.content %}\n                {%- if 'text' in content_item %}\n                    {{- content_item.text }}\n                {%- endif %}\n            {%- endfor %}\n        {%- endif %}\n        {%- if message.tool_calls %}\n            {%- for tool_call in message.tool_calls %}\n                {%- if (loop.first and message.content) or (not loop.first) %}\n                    {{- '\\n' }}\n                {%- endif %}\n                {%- if tool_call.function %}\n                    {%- set tool_call = tool_call.function %}\n                {%- endif %}\n                {{- '<tool_call>\\n{\"name\": \"' }}\n                {{- tool_call.name }}\n                {{- '\", \"arguments\": ' }}\n                {%- if tool_call.arguments is string %}\n                    {{- tool_call.arguments }}\n                {%- else %}\n                    {{- tool_call.arguments | tojson }}\n                {%- endif %}\n                {{- '}\\n</tool_call>' }}\n            {%- endfor %}\n        {%- endif %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"tool\" %}\n        {%- if loop.first or (messages[loop.index0 - 1].role != \"tool\") %}\n            {{- '<|im_start|>user' }}\n        {%- endif %}\n        {{- '\\n<tool_response>\\n' }}\n        {%- if message.content is string %}\n            {{- message.content }}\n        {%- else %}\n            {%- for content in message.content %}\n                {%- if content.type == 'image' or 'image' in content or 'image_url' in content %}\n                    {%- set image_count.value = image_count.value + 1 %}\n                    {%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%}\n                    <|vision_start|><|image_pad|><|vision_end|>\n                {%- elif content.type == 'video' or 'video' in content %}\n                    {%- set video_count.value = video_count.value + 1 %}\n                    {%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%}\n                    <|vision_start|><|video_pad|><|vision_end|>\n                {%- elif 'text' in content %}\n                    {{- content.text }}\n                {%- endif %}\n            {%- endfor %}\n        {%- endif %}\n        {{- '\\n</tool_response>' }}\n        {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n            {{- '<|im_end|>\\n' }}\n        {%- endif %}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "model_max_length": 262144,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

text_encoder/video_preprocessor_config.json

@@ -0,0 +1,21 @@
+{
+    "size": {
+        "longest_edge": 25165824,
+        "shortest_edge": 4096
+    },
+    "patch_size": 16,
+    "temporal_patch_size": 2,
+    "merge_size": 2,
+    "image_mean": [
+        0.5,
+        0.5,
+        0.5
+    ],
+    "image_std": [
+        0.5,
+        0.5,
+        0.5
+    ],
+    "processor_class": "Qwen3VLProcessor",
+    "video_processor_type": "Qwen3VLVideoProcessor"
+}

tokenizer/tokenizer_config.json

@@ -0,0 +1,246 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151665": {
+      "content": "<tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151666": {
+      "content": "</tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151667": {
+      "content": "<think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151668": {
+      "content": "</think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>",
+    "<d>",
+    "</d>",
+    "<|cutoff|>",
+    "<|lyrics_start|>",
+    "<|lyrics_end|>",
+    "<|caption_start|>",
+    "<|caption_end|>"
+  ],
+  "bos_token": null,
+  "chat_template": "{%- if tools %}\n    {{- '<|im_start|>system\\n' }}\n    {%- if messages[0].role == 'system' %}\n        {%- if messages[0].content is string %}\n            {{- messages[0].content }}\n        {%- else %}\n            {%- for content in messages[0].content %}\n                {%- if 'text' in content %}\n                    {{- content.text }}\n                {%- endif %}\n            {%- endfor %}\n        {%- endif %}\n        {{- '\\n\\n' }}\n    {%- endif %}\n    {{- \"# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n    {%- for tool in tools %}\n        {{- \"\\n\" }}\n        {{- tool | tojson }}\n    {%- endfor %}\n    {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n    {%- if messages[0].role == 'system' %}\n        {{- '<|im_start|>system\\n' }}\n        {%- if messages[0].content is string %}\n            {{- messages[0].content }}\n        {%- else %}\n            {%- for content in messages[0].content %}\n                {%- if 'text' in content %}\n                    {{- content.text }}\n                {%- endif %}\n            {%- endfor %}\n        {%- endif %}\n        {{- '<|im_end|>\\n' }}\n    {%- endif %}\n{%- endif %}\n{%- set image_count = namespace(value=0) %}\n{%- set video_count = namespace(value=0) %}\n{%- for message in messages %}\n    {%- if message.role == \"user\" %}\n        {{- '<|im_start|>' + message.role + '\\n' }}\n        {%- if message.content is string %}\n            {{- message.content }}\n        {%- else %}\n            {%- for content in message.content %}\n                {%- if content.type == 'image' or 'image' in content or 'image_url' in content %}\n                    {%- set image_count.value = image_count.value + 1 %}\n                    {%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%}\n                    <|vision_start|><|image_pad|><|vision_end|>\n                {%- elif content.type == 'video' or 'video' in content %}\n                    {%- set video_count.value = video_count.value + 1 %}\n                    {%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%}\n                    <|vision_start|><|video_pad|><|vision_end|>\n                {%- elif 'text' in content %}\n                    {{- content.text }}\n                {%- endif %}\n            {%- endfor %}\n        {%- endif %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {{- '<|im_start|>' + message.role + '\\n' }}\n        {%- if message.content is string %}\n            {{- message.content }}\n        {%- else %}\n            {%- for content_item in message.content %}\n                {%- if 'text' in content_item %}\n                    {{- content_item.text }}\n                {%- endif %}\n            {%- endfor %}\n        {%- endif %}\n        {%- if message.tool_calls %}\n            {%- for tool_call in message.tool_calls %}\n                {%- if (loop.first and message.content) or (not loop.first) %}\n                    {{- '\\n' }}\n                {%- endif %}\n                {%- if tool_call.function %}\n                    {%- set tool_call = tool_call.function %}\n                {%- endif %}\n                {{- '<tool_call>\\n{\"name\": \"' }}\n                {{- tool_call.name }}\n                {{- '\", \"arguments\": ' }}\n                {%- if tool_call.arguments is string %}\n                    {{- tool_call.arguments }}\n                {%- else %}\n                    {{- tool_call.arguments | tojson }}\n                {%- endif %}\n                {{- '}\\n</tool_call>' }}\n            {%- endfor %}\n        {%- endif %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"tool\" %}\n        {%- if loop.first or (messages[loop.index0 - 1].role != \"tool\") %}\n            {{- '<|im_start|>user' }}\n        {%- endif %}\n        {{- '\\n<tool_response>\\n' }}\n        {%- if message.content is string %}\n            {{- message.content }}\n        {%- else %}\n            {%- for content in message.content %}\n                {%- if content.type == 'image' or 'image' in content or 'image_url' in content %}\n                    {%- set image_count.value = image_count.value + 1 %}\n                    {%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%}\n                    <|vision_start|><|image_pad|><|vision_end|>\n                {%- elif content.type == 'video' or 'video' in content %}\n                    {%- set video_count.value = video_count.value + 1 %}\n                    {%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%}\n                    <|vision_start|><|video_pad|><|vision_end|>\n                {%- elif 'text' in content %}\n                    {{- content.text }}\n                {%- endif %}\n            {%- endfor %}\n        {%- endif %}\n        {{- '\\n</tool_response>' }}\n        {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n            {{- '<|im_end|>\\n' }}\n        {%- endif %}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "model_max_length": 262144,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

transformer/config.json

@@ -0,0 +1,26 @@
+{
+  "_class_name": "MiniMaxH3Transformer3DModel",
+  "_diffusers_version": "0.36.0.dev0",
+  "num_attention_heads": 56,
+  "attention_head_dim": 128,
+  "hidden_size": 5376,
+  "num_layers": 50,
+  "num_refiner_layers": 2,
+  "ffn_dim": 14336,
+  "in_channels": 24,
+  "audio_in_channels": 32,
+  "patch_size": [
+    1,
+    2,
+    2
+  ],
+  "text_dim": 5120,
+  "freq_dim": 256,
+  "time_embed_hidden_dim": 5376,
+  "time_embed_dim": 2688,
+  "rope_freq_dim": 16,
+  "rope_theta": 10000.0,
+  "norm_eps": 1e-05,
+  "qk_norm_eps": 1e-05,
+  "final_norm_eps": 1e-05
+}

transformer/diffusion_pytorch_model-00002-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fdb4db67af50e554d63f6107eb25dffe05436b93d010fe7c73365a0daef7a495
+size 3989259848

transformer/diffusion_pytorch_model-00003-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:56589eb613578fc3b7630eccfe7f2c2096b063369aa7d4ed0328f0d378567a06
+size 3989259864

transformer/diffusion_pytorch_model-00007-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:14d416a288d5254035e76e42d5eb3b8cf56602bbcc595beb0c157124bb8e7044
+size 3989259832

transformer/diffusion_pytorch_model-00008-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4f8e479a96a692f1a04bdb4bd26c3ad2369c0bd076052067b8d613e0adcf7877
+size 3989259864

transformer/diffusion_pytorch_model-00009-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7daad24c9223ddfc42877366db947c8169f7f85d8f05dc415452a31e80c38c03
+size 3546104680

transformer/diffusion_pytorch_model.safetensors.index.json

@@ -0,0 +1,895 @@
+{
+  "metadata": {
+    "total_size": 70099502592
+  },
+  "weight_map": {
+    "audio_proj_in.bias": "diffusion_pytorch_model-00001-of-00014.safetensors",
+    "audio_proj_in.weight": "diffusion_pytorch_model-00001-of-00014.safetensors",
+    "audio_proj_out.bias": "diffusion_pytorch_model-00001-of-00014.safetensors",
+    "audio_proj_out.weight": "diffusion_pytorch_model-00001-of-00014.safetensors",
+    "context_embedder.bias": "diffusion_pytorch_model-00001-of-00014.safetensors",
+    "context_embedder.weight": "diffusion_pytorch_model-00001-of-00014.safetensors",
+    "norm_out.linear.bias": "diffusion_pytorch_model-00001-of-00014.safetensors",
+    "norm_out.linear.weight": "diffusion_pytorch_model-00001-of-00014.safetensors",
+    "norm_out.norm.weight": "diffusion_pytorch_model-00001-of-00014.safetensors",
+    "proj_in.bias": "diffusion_pytorch_model-00001-of-00014.safetensors",
+    "proj_in.weight": "diffusion_pytorch_model-00001-of-00014.safetensors",
+    "proj_out.bias": "diffusion_pytorch_model-00001-of-00014.safetensors",
+    "proj_out.weight": "diffusion_pytorch_model-00001-of-00014.safetensors",
+    "time_embedder.linear_1.bias": "diffusion_pytorch_model-00001-of-00014.safetensors",
+    "time_embedder.linear_1.weight": "diffusion_pytorch_model-00001-of-00014.safetensors",
+    "time_embedder.linear_2.bias": "diffusion_pytorch_model-00001-of-00014.safetensors",
+    "time_embedder.linear_2.weight": "diffusion_pytorch_model-00001-of-00014.safetensors",
+    "token_refiner.final_norm.weight": "diffusion_pytorch_model-00001-of-00014.safetensors",
+    "token_refiner.refiner_blocks.0.attn.norm_k.weight": "diffusion_pytorch_model-00001-of-00014.safetensors",
+    "token_refiner.refiner_blocks.0.attn.norm_q.weight": "diffusion_pytorch_model-00001-of-00014.safetensors",
+    "token_refiner.refiner_blocks.0.attn.to_k.weight": "diffusion_pytorch_model-00001-of-00014.safetensors",
+    "token_refiner.refiner_blocks.0.attn.to_out.0.weight": "diffusion_pytorch_model-00001-of-00014.safetensors",
+    "token_refiner.refiner_blocks.0.attn.to_q.weight": "diffusion_pytorch_model-00001-of-00014.safetensors",
+    "token_refiner.refiner_blocks.0.attn.to_v.weight": "diffusion_pytorch_model-00001-of-00014.safetensors",
+    "token_refiner.refiner_blocks.0.ff.net.0.proj.weight": "diffusion_pytorch_model-00001-of-00014.safetensors",
+    "token_refiner.refiner_blocks.0.ff.net.2.weight": "diffusion_pytorch_model-00001-of-00014.safetensors",
+    "token_refiner.refiner_blocks.0.norm1.weight": "diffusion_pytorch_model-00001-of-00014.safetensors",
+    "token_refiner.refiner_blocks.0.norm2.weight": "diffusion_pytorch_model-00001-of-00014.safetensors",
+    "token_refiner.refiner_blocks.1.attn.norm_k.weight": "diffusion_pytorch_model-00001-of-00014.safetensors",
+    "token_refiner.refiner_blocks.1.attn.norm_q.weight": "diffusion_pytorch_model-00001-of-00014.safetensors",
+    "token_refiner.refiner_blocks.1.attn.to_k.weight": "diffusion_pytorch_model-00001-of-00014.safetensors",
+    "token_refiner.refiner_blocks.1.attn.to_out.0.weight": "diffusion_pytorch_model-00001-of-00014.safetensors",
+    "token_refiner.refiner_blocks.1.attn.to_q.weight": "diffusion_pytorch_model-00001-of-00014.safetensors",
+    "token_refiner.refiner_blocks.1.attn.to_v.weight": "diffusion_pytorch_model-00001-of-00014.safetensors",
+    "token_refiner.refiner_blocks.1.ff.net.0.proj.weight": "diffusion_pytorch_model-00001-of-00014.safetensors",
+    "token_refiner.refiner_blocks.1.ff.net.2.weight": "diffusion_pytorch_model-00001-of-00014.safetensors",
+    "token_refiner.refiner_blocks.1.norm1.weight": "diffusion_pytorch_model-00001-of-00014.safetensors",
+    "token_refiner.refiner_blocks.1.norm2.weight": "diffusion_pytorch_model-00001-of-00014.safetensors",
+    "transformer_blocks.0.adaln_proj.linear.bias": "diffusion_pytorch_model-00001-of-00014.safetensors",
+    "transformer_blocks.0.adaln_proj.linear.weight": "diffusion_pytorch_model-00001-of-00014.safetensors",
+    "transformer_blocks.0.attn.norm_k.weight": "diffusion_pytorch_model-00001-of-00014.safetensors",
+    "transformer_blocks.0.attn.norm_q.weight": "diffusion_pytorch_model-00001-of-00014.safetensors",
+    "transformer_blocks.0.attn.to_gate_compress.weight": "diffusion_pytorch_model-00001-of-00014.safetensors",
+    "transformer_blocks.0.attn.to_k.weight": "diffusion_pytorch_model-00001-of-00014.safetensors",
+    "transformer_blocks.0.attn.to_out.0.weight": "diffusion_pytorch_model-00001-of-00014.safetensors",
+    "transformer_blocks.0.attn.to_q.weight": "diffusion_pytorch_model-00001-of-00014.safetensors",
+    "transformer_blocks.0.attn.to_v.weight": "diffusion_pytorch_model-00001-of-00014.safetensors",
+    "transformer_blocks.0.ff.net.0.proj.weight_packed": "diffusion_pytorch_model-00001-of-00014.safetensors",
+    "transformer_blocks.0.ff.net.0.proj.weight_scale": "diffusion_pytorch_model-00001-of-00014.safetensors",
+    "transformer_blocks.0.ff.net.0.proj.weight_tensor_scale": "diffusion_pytorch_model-00001-of-00014.safetensors",
+    "transformer_blocks.0.ff.net.2.weight_packed": "diffusion_pytorch_model-00001-of-00014.safetensors",
+    "transformer_blocks.0.ff.net.2.weight_scale": "diffusion_pytorch_model-00001-of-00014.safetensors",
+    "transformer_blocks.0.ff.net.2.weight_tensor_scale": "diffusion_pytorch_model-00001-of-00014.safetensors",
+    "transformer_blocks.0.norm1.weight": "diffusion_pytorch_model-00001-of-00014.safetensors",
+    "transformer_blocks.0.norm2.weight": "diffusion_pytorch_model-00001-of-00014.safetensors",
+    "transformer_blocks.1.adaln_proj.linear.bias": "diffusion_pytorch_model-00001-of-00014.safetensors",
+    "transformer_blocks.1.adaln_proj.linear.weight": "diffusion_pytorch_model-00001-of-00014.safetensors",
+    "transformer_blocks.1.attn.norm_k.weight": "diffusion_pytorch_model-00001-of-00014.safetensors",
+    "transformer_blocks.1.attn.norm_q.weight": "diffusion_pytorch_model-00001-of-00014.safetensors",
+    "transformer_blocks.1.attn.to_gate_compress.weight": "diffusion_pytorch_model-00001-of-00014.safetensors",
+    "transformer_blocks.1.attn.to_k.weight": "diffusion_pytorch_model-00001-of-00014.safetensors",
+    "transformer_blocks.1.attn.to_out.0.weight": "diffusion_pytorch_model-00001-of-00014.safetensors",
+    "transformer_blocks.1.attn.to_q.weight": "diffusion_pytorch_model-00001-of-00014.safetensors",
+    "transformer_blocks.1.attn.to_v.weight": "diffusion_pytorch_model-00001-of-00014.safetensors",
+    "transformer_blocks.1.ff.net.0.proj.weight_packed": "diffusion_pytorch_model-00001-of-00014.safetensors",
+    "transformer_blocks.1.ff.net.0.proj.weight_scale": "diffusion_pytorch_model-00001-of-00014.safetensors",
+    "transformer_blocks.1.ff.net.0.proj.weight_tensor_scale": "diffusion_pytorch_model-00001-of-00014.safetensors",
+    "transformer_blocks.1.ff.net.2.weight_packed": "diffusion_pytorch_model-00001-of-00014.safetensors",
+    "transformer_blocks.1.ff.net.2.weight_scale": "diffusion_pytorch_model-00001-of-00014.safetensors",
+    "transformer_blocks.1.ff.net.2.weight_tensor_scale": "diffusion_pytorch_model-00001-of-00014.safetensors",
+    "transformer_blocks.1.norm1.weight": "diffusion_pytorch_model-00001-of-00014.safetensors",
+    "transformer_blocks.1.norm2.weight": "diffusion_pytorch_model-00001-of-00014.safetensors",
+    "transformer_blocks.10.adaln_proj.linear.bias": "diffusion_pytorch_model-00001-of-00014.safetensors",
+    "transformer_blocks.10.adaln_proj.linear.weight": "diffusion_pytorch_model-00001-of-00014.safetensors",
+    "transformer_blocks.10.attn.norm_k.weight": "diffusion_pytorch_model-00001-of-00014.safetensors",
+    "transformer_blocks.10.attn.norm_q.weight": "diffusion_pytorch_model-00001-of-00014.safetensors",
+    "transformer_blocks.10.attn.to_gate_compress.weight": "diffusion_pytorch_model-00001-of-00014.safetensors",
+    "transformer_blocks.10.attn.to_k.weight": "diffusion_pytorch_model-00001-of-00014.safetensors",
+    "transformer_blocks.10.attn.to_out.0.weight": "diffusion_pytorch_model-00001-of-00014.safetensors",
+    "transformer_blocks.10.attn.to_q.weight": "diffusion_pytorch_model-00001-of-00014.safetensors",
+    "transformer_blocks.10.attn.to_v.weight": "diffusion_pytorch_model-00001-of-00014.safetensors",
+    "transformer_blocks.10.ff.net.0.proj.weight_packed": "diffusion_pytorch_model-00002-of-00014.safetensors",
+    "transformer_blocks.10.ff.net.0.proj.weight_scale": "diffusion_pytorch_model-00002-of-00014.safetensors",
+    "transformer_blocks.10.ff.net.0.proj.weight_tensor_scale": "diffusion_pytorch_model-00002-of-00014.safetensors",
+    "transformer_blocks.10.ff.net.2.weight_packed": "diffusion_pytorch_model-00002-of-00014.safetensors",
+    "transformer_blocks.10.ff.net.2.weight_scale": "diffusion_pytorch_model-00002-of-00014.safetensors",
+    "transformer_blocks.10.ff.net.2.weight_tensor_scale": "diffusion_pytorch_model-00002-of-00014.safetensors",
+    "transformer_blocks.10.norm1.weight": "diffusion_pytorch_model-00002-of-00014.safetensors",
+    "transformer_blocks.10.norm2.weight": "diffusion_pytorch_model-00002-of-00014.safetensors",
+    "transformer_blocks.11.adaln_proj.linear.bias": "diffusion_pytorch_model-00002-of-00014.safetensors",
+    "transformer_blocks.11.adaln_proj.linear.weight": "diffusion_pytorch_model-00002-of-00014.safetensors",
+    "transformer_blocks.11.attn.norm_k.weight": "diffusion_pytorch_model-00002-of-00014.safetensors",
+    "transformer_blocks.11.attn.norm_q.weight": "diffusion_pytorch_model-00002-of-00014.safetensors",
+    "transformer_blocks.11.attn.to_gate_compress.weight": "diffusion_pytorch_model-00002-of-00014.safetensors",
+    "transformer_blocks.11.attn.to_k.weight": "diffusion_pytorch_model-00002-of-00014.safetensors",
+    "transformer_blocks.11.attn.to_out.0.weight": "diffusion_pytorch_model-00002-of-00014.safetensors",
+    "transformer_blocks.11.attn.to_q.weight": "diffusion_pytorch_model-00002-of-00014.safetensors",
+    "transformer_blocks.11.attn.to_v.weight": "diffusion_pytorch_model-00002-of-00014.safetensors",
+    "transformer_blocks.11.ff.net.0.proj.weight_packed": "diffusion_pytorch_model-00002-of-00014.safetensors",
+    "transformer_blocks.11.ff.net.0.proj.weight_scale": "diffusion_pytorch_model-00002-of-00014.safetensors",
+    "transformer_blocks.11.ff.net.0.proj.weight_tensor_scale": "diffusion_pytorch_model-00002-of-00014.safetensors",
+    "transformer_blocks.11.ff.net.2.weight_packed": "diffusion_pytorch_model-00002-of-00014.safetensors",
+    "transformer_blocks.11.ff.net.2.weight_scale": "diffusion_pytorch_model-00002-of-00014.safetensors",
+    "transformer_blocks.11.ff.net.2.weight_tensor_scale": "diffusion_pytorch_model-00002-of-00014.safetensors",
+    "transformer_blocks.11.norm1.weight": "diffusion_pytorch_model-00002-of-00014.safetensors",
+    "transformer_blocks.11.norm2.weight": "diffusion_pytorch_model-00002-of-00014.safetensors",
+    "transformer_blocks.12.adaln_proj.linear.bias": "diffusion_pytorch_model-00002-of-00014.safetensors",
+    "transformer_blocks.12.adaln_proj.linear.weight": "diffusion_pytorch_model-00002-of-00014.safetensors",
+    "transformer_blocks.12.attn.norm_k.weight": "diffusion_pytorch_model-00002-of-00014.safetensors",
+    "transformer_blocks.12.attn.norm_q.weight": "diffusion_pytorch_model-00002-of-00014.safetensors",
+    "transformer_blocks.12.attn.to_gate_compress.weight": "diffusion_pytorch_model-00002-of-00014.safetensors",
+    "transformer_blocks.12.attn.to_k.weight": "diffusion_pytorch_model-00002-of-00014.safetensors",
+    "transformer_blocks.12.attn.to_out.0.weight": "diffusion_pytorch_model-00002-of-00014.safetensors",
+    "transformer_blocks.12.attn.to_q.weight": "diffusion_pytorch_model-00002-of-00014.safetensors",
+    "transformer_blocks.12.attn.to_v.weight": "diffusion_pytorch_model-00002-of-00014.safetensors",
+    "transformer_blocks.12.ff.net.0.proj.weight_packed": "diffusion_pytorch_model-00002-of-00014.safetensors",
+    "transformer_blocks.12.ff.net.0.proj.weight_scale": "diffusion_pytorch_model-00002-of-00014.safetensors",
+    "transformer_blocks.12.ff.net.0.proj.weight_tensor_scale": "diffusion_pytorch_model-00002-of-00014.safetensors",
+    "transformer_blocks.12.ff.net.2.weight_packed": "diffusion_pytorch_model-00002-of-00014.safetensors",
+    "transformer_blocks.12.ff.net.2.weight_scale": "diffusion_pytorch_model-00002-of-00014.safetensors",
+    "transformer_blocks.12.ff.net.2.weight_tensor_scale": "diffusion_pytorch_model-00002-of-00014.safetensors",
+    "transformer_blocks.12.norm1.weight": "diffusion_pytorch_model-00002-of-00014.safetensors",
+    "transformer_blocks.12.norm2.weight": "diffusion_pytorch_model-00002-of-00014.safetensors",
+    "transformer_blocks.13.adaln_proj.linear.bias": "diffusion_pytorch_model-00002-of-00014.safetensors",
+    "transformer_blocks.13.adaln_proj.linear.weight": "diffusion_pytorch_model-00002-of-00014.safetensors",
+    "transformer_blocks.13.attn.norm_k.weight": "diffusion_pytorch_model-00002-of-00014.safetensors",
+    "transformer_blocks.13.attn.norm_q.weight": "diffusion_pytorch_model-00002-of-00014.safetensors",
+    "transformer_blocks.13.attn.to_gate_compress.weight": "diffusion_pytorch_model-00002-of-00014.safetensors",
+    "transformer_blocks.13.attn.to_k.weight": "diffusion_pytorch_model-00002-of-00014.safetensors",
+    "transformer_blocks.13.attn.to_out.0.weight": "diffusion_pytorch_model-00002-of-00014.safetensors",
+    "transformer_blocks.13.attn.to_q.weight": "diffusion_pytorch_model-00002-of-00014.safetensors",
+    "transformer_blocks.13.attn.to_v.weight": "diffusion_pytorch_model-00002-of-00014.safetensors",
+    "transformer_blocks.13.ff.net.0.proj.weight_packed": "diffusion_pytorch_model-00002-of-00014.safetensors",
+    "transformer_blocks.13.ff.net.0.proj.weight_scale": "diffusion_pytorch_model-00002-of-00014.safetensors",
+    "transformer_blocks.13.ff.net.0.proj.weight_tensor_scale": "diffusion_pytorch_model-00002-of-00014.safetensors",
+    "transformer_blocks.13.ff.net.2.weight_packed": "diffusion_pytorch_model-00002-of-00014.safetensors",
+    "transformer_blocks.13.ff.net.2.weight_scale": "diffusion_pytorch_model-00002-of-00014.safetensors",
+    "transformer_blocks.13.ff.net.2.weight_tensor_scale": "diffusion_pytorch_model-00002-of-00014.safetensors",
+    "transformer_blocks.13.norm1.weight": "diffusion_pytorch_model-00002-of-00014.safetensors",
+    "transformer_blocks.13.norm2.weight": "diffusion_pytorch_model-00002-of-00014.safetensors",
+    "transformer_blocks.14.adaln_proj.linear.bias": "diffusion_pytorch_model-00002-of-00014.safetensors",
+    "transformer_blocks.14.adaln_proj.linear.weight": "diffusion_pytorch_model-00002-of-00014.safetensors",
+    "transformer_blocks.14.attn.norm_k.weight": "diffusion_pytorch_model-00002-of-00014.safetensors",
+    "transformer_blocks.14.attn.norm_q.weight": "diffusion_pytorch_model-00002-of-00014.safetensors",
+    "transformer_blocks.14.attn.to_gate_compress.weight": "diffusion_pytorch_model-00002-of-00014.safetensors",
+    "transformer_blocks.14.attn.to_k.weight": "diffusion_pytorch_model-00002-of-00014.safetensors",
+    "transformer_blocks.14.attn.to_out.0.weight": "diffusion_pytorch_model-00002-of-00014.safetensors",
+    "transformer_blocks.14.attn.to_q.weight": "diffusion_pytorch_model-00003-of-00014.safetensors",
+    "transformer_blocks.14.attn.to_v.weight": "diffusion_pytorch_model-00003-of-00014.safetensors",
+    "transformer_blocks.14.ff.net.0.proj.weight_packed": "diffusion_pytorch_model-00003-of-00014.safetensors",
+    "transformer_blocks.14.ff.net.0.proj.weight_scale": "diffusion_pytorch_model-00003-of-00014.safetensors",
+    "transformer_blocks.14.ff.net.0.proj.weight_tensor_scale": "diffusion_pytorch_model-00003-of-00014.safetensors",
+    "transformer_blocks.14.ff.net.2.weight_packed": "diffusion_pytorch_model-00003-of-00014.safetensors",
+    "transformer_blocks.14.ff.net.2.weight_scale": "diffusion_pytorch_model-00003-of-00014.safetensors",
+    "transformer_blocks.14.ff.net.2.weight_tensor_scale": "diffusion_pytorch_model-00003-of-00014.safetensors",
+    "transformer_blocks.14.norm1.weight": "diffusion_pytorch_model-00003-of-00014.safetensors",
+    "transformer_blocks.14.norm2.weight": "diffusion_pytorch_model-00003-of-00014.safetensors",
+    "transformer_blocks.15.adaln_proj.linear.bias": "diffusion_pytorch_model-00003-of-00014.safetensors",
+    "transformer_blocks.15.adaln_proj.linear.weight": "diffusion_pytorch_model-00003-of-00014.safetensors",
+    "transformer_blocks.15.attn.norm_k.weight": "diffusion_pytorch_model-00003-of-00014.safetensors",
+    "transformer_blocks.15.attn.norm_q.weight": "diffusion_pytorch_model-00003-of-00014.safetensors",
+    "transformer_blocks.15.attn.to_gate_compress.weight": "diffusion_pytorch_model-00003-of-00014.safetensors",
+    "transformer_blocks.15.attn.to_k.weight": "diffusion_pytorch_model-00003-of-00014.safetensors",
+    "transformer_blocks.15.attn.to_out.0.weight": "diffusion_pytorch_model-00003-of-00014.safetensors",
+    "transformer_blocks.15.attn.to_q.weight": "diffusion_pytorch_model-00003-of-00014.safetensors",
+    "transformer_blocks.15.attn.to_v.weight": "diffusion_pytorch_model-00003-of-00014.safetensors",
+    "transformer_blocks.15.ff.net.0.proj.weight_packed": "diffusion_pytorch_model-00003-of-00014.safetensors",
+    "transformer_blocks.15.ff.net.0.proj.weight_scale": "diffusion_pytorch_model-00003-of-00014.safetensors",
+    "transformer_blocks.15.ff.net.0.proj.weight_tensor_scale": "diffusion_pytorch_model-00003-of-00014.safetensors",
+    "transformer_blocks.15.ff.net.2.weight_packed": "diffusion_pytorch_model-00003-of-00014.safetensors",
+    "transformer_blocks.15.ff.net.2.weight_scale": "diffusion_pytorch_model-00003-of-00014.safetensors",
+    "transformer_blocks.15.ff.net.2.weight_tensor_scale": "diffusion_pytorch_model-00003-of-00014.safetensors",
+    "transformer_blocks.15.norm1.weight": "diffusion_pytorch_model-00003-of-00014.safetensors",
+    "transformer_blocks.15.norm2.weight": "diffusion_pytorch_model-00003-of-00014.safetensors",
+    "transformer_blocks.16.adaln_proj.linear.bias": "diffusion_pytorch_model-00003-of-00014.safetensors",
+    "transformer_blocks.16.adaln_proj.linear.weight": "diffusion_pytorch_model-00003-of-00014.safetensors",
+    "transformer_blocks.16.attn.norm_k.weight": "diffusion_pytorch_model-00003-of-00014.safetensors",
+    "transformer_blocks.16.attn.norm_q.weight": "diffusion_pytorch_model-00003-of-00014.safetensors",
+    "transformer_blocks.16.attn.to_gate_compress.weight": "diffusion_pytorch_model-00003-of-00014.safetensors",
+    "transformer_blocks.16.attn.to_k.weight": "diffusion_pytorch_model-00003-of-00014.safetensors",
+    "transformer_blocks.16.attn.to_out.0.weight": "diffusion_pytorch_model-00003-of-00014.safetensors",
+    "transformer_blocks.16.attn.to_q.weight": "diffusion_pytorch_model-00003-of-00014.safetensors",
+    "transformer_blocks.16.attn.to_v.weight": "diffusion_pytorch_model-00003-of-00014.safetensors",
+    "transformer_blocks.16.ff.net.0.proj.weight_packed": "diffusion_pytorch_model-00003-of-00014.safetensors",
+    "transformer_blocks.16.ff.net.0.proj.weight_scale": "diffusion_pytorch_model-00003-of-00014.safetensors",
+    "transformer_blocks.16.ff.net.0.proj.weight_tensor_scale": "diffusion_pytorch_model-00003-of-00014.safetensors",
+    "transformer_blocks.16.ff.net.2.weight_packed": "diffusion_pytorch_model-00003-of-00014.safetensors",
+    "transformer_blocks.16.ff.net.2.weight_scale": "diffusion_pytorch_model-00003-of-00014.safetensors",
+    "transformer_blocks.16.ff.net.2.weight_tensor_scale": "diffusion_pytorch_model-00003-of-00014.safetensors",
+    "transformer_blocks.16.norm1.weight": "diffusion_pytorch_model-00003-of-00014.safetensors",
+    "transformer_blocks.16.norm2.weight": "diffusion_pytorch_model-00003-of-00014.safetensors",
+    "transformer_blocks.17.adaln_proj.linear.bias": "diffusion_pytorch_model-00003-of-00014.safetensors",
+    "transformer_blocks.17.adaln_proj.linear.weight": "diffusion_pytorch_model-00003-of-00014.safetensors",
+    "transformer_blocks.17.attn.norm_k.weight": "diffusion_pytorch_model-00003-of-00014.safetensors",
+    "transformer_blocks.17.attn.norm_q.weight": "diffusion_pytorch_model-00003-of-00014.safetensors",
+    "transformer_blocks.17.attn.to_gate_compress.weight": "diffusion_pytorch_model-00003-of-00014.safetensors",
+    "transformer_blocks.17.attn.to_k.weight": "diffusion_pytorch_model-00003-of-00014.safetensors",
+    "transformer_blocks.17.attn.to_out.0.weight": "diffusion_pytorch_model-00003-of-00014.safetensors",
+    "transformer_blocks.17.attn.to_q.weight": "diffusion_pytorch_model-00003-of-00014.safetensors",
+    "transformer_blocks.17.attn.to_v.weight": "diffusion_pytorch_model-00003-of-00014.safetensors",
+    "transformer_blocks.17.ff.net.0.proj.weight_packed": "diffusion_pytorch_model-00003-of-00014.safetensors",
+    "transformer_blocks.17.ff.net.0.proj.weight_scale": "diffusion_pytorch_model-00003-of-00014.safetensors",
+    "transformer_blocks.17.ff.net.0.proj.weight_tensor_scale": "diffusion_pytorch_model-00003-of-00014.safetensors",
+    "transformer_blocks.17.ff.net.2.weight_packed": "diffusion_pytorch_model-00003-of-00014.safetensors",
+    "transformer_blocks.17.ff.net.2.weight_scale": "diffusion_pytorch_model-00003-of-00014.safetensors",
+    "transformer_blocks.17.ff.net.2.weight_tensor_scale": "diffusion_pytorch_model-00003-of-00014.safetensors",
+    "transformer_blocks.17.norm1.weight": "diffusion_pytorch_model-00003-of-00014.safetensors",
+    "transformer_blocks.17.norm2.weight": "diffusion_pytorch_model-00003-of-00014.safetensors",
+    "transformer_blocks.18.adaln_proj.linear.bias": "diffusion_pytorch_model-00003-of-00014.safetensors",
+    "transformer_blocks.18.adaln_proj.linear.weight": "diffusion_pytorch_model-00003-of-00014.safetensors",
+    "transformer_blocks.18.attn.norm_k.weight": "diffusion_pytorch_model-00003-of-00014.safetensors",
+    "transformer_blocks.18.attn.norm_q.weight": "diffusion_pytorch_model-00003-of-00014.safetensors",
+    "transformer_blocks.18.attn.to_gate_compress.weight": "diffusion_pytorch_model-00003-of-00014.safetensors",
+    "transformer_blocks.18.attn.to_k.weight": "diffusion_pytorch_model-00004-of-00014.safetensors",
+    "transformer_blocks.18.attn.to_out.0.weight": "diffusion_pytorch_model-00004-of-00014.safetensors",
+    "transformer_blocks.18.attn.to_q.weight": "diffusion_pytorch_model-00004-of-00014.safetensors",
+    "transformer_blocks.18.attn.to_v.weight": "diffusion_pytorch_model-00004-of-00014.safetensors",
+    "transformer_blocks.18.ff.net.0.proj.weight_packed": "diffusion_pytorch_model-00004-of-00014.safetensors",
+    "transformer_blocks.18.ff.net.0.proj.weight_scale": "diffusion_pytorch_model-00004-of-00014.safetensors",
+    "transformer_blocks.18.ff.net.0.proj.weight_tensor_scale": "diffusion_pytorch_model-00004-of-00014.safetensors",
+    "transformer_blocks.18.ff.net.2.weight_packed": "diffusion_pytorch_model-00004-of-00014.safetensors",
+    "transformer_blocks.18.ff.net.2.weight_scale": "diffusion_pytorch_model-00004-of-00014.safetensors",
+    "transformer_blocks.18.ff.net.2.weight_tensor_scale": "diffusion_pytorch_model-00004-of-00014.safetensors",
+    "transformer_blocks.18.norm1.weight": "diffusion_pytorch_model-00004-of-00014.safetensors",
+    "transformer_blocks.18.norm2.weight": "diffusion_pytorch_model-00004-of-00014.safetensors",
+    "transformer_blocks.19.adaln_proj.linear.bias": "diffusion_pytorch_model-00004-of-00014.safetensors",
+    "transformer_blocks.19.adaln_proj.linear.weight": "diffusion_pytorch_model-00004-of-00014.safetensors",
+    "transformer_blocks.19.attn.norm_k.weight": "diffusion_pytorch_model-00004-of-00014.safetensors",
+    "transformer_blocks.19.attn.norm_q.weight": "diffusion_pytorch_model-00004-of-00014.safetensors",
+    "transformer_blocks.19.attn.to_gate_compress.weight": "diffusion_pytorch_model-00004-of-00014.safetensors",
+    "transformer_blocks.19.attn.to_k.weight": "diffusion_pytorch_model-00004-of-00014.safetensors",
+    "transformer_blocks.19.attn.to_out.0.weight": "diffusion_pytorch_model-00004-of-00014.safetensors",
+    "transformer_blocks.19.attn.to_q.weight": "diffusion_pytorch_model-00004-of-00014.safetensors",
+    "transformer_blocks.19.attn.to_v.weight": "diffusion_pytorch_model-00004-of-00014.safetensors",
+    "transformer_blocks.19.ff.net.0.proj.weight_packed": "diffusion_pytorch_model-00004-of-00014.safetensors",
+    "transformer_blocks.19.ff.net.0.proj.weight_scale": "diffusion_pytorch_model-00004-of-00014.safetensors",
+    "transformer_blocks.19.ff.net.0.proj.weight_tensor_scale": "diffusion_pytorch_model-00004-of-00014.safetensors",
+    "transformer_blocks.19.ff.net.2.weight_packed": "diffusion_pytorch_model-00004-of-00014.safetensors",
+    "transformer_blocks.19.ff.net.2.weight_scale": "diffusion_pytorch_model-00004-of-00014.safetensors",
+    "transformer_blocks.19.ff.net.2.weight_tensor_scale": "diffusion_pytorch_model-00004-of-00014.safetensors",
+    "transformer_blocks.19.norm1.weight": "diffusion_pytorch_model-00004-of-00014.safetensors",
+    "transformer_blocks.19.norm2.weight": "diffusion_pytorch_model-00004-of-00014.safetensors",
+    "transformer_blocks.2.adaln_proj.linear.bias": "diffusion_pytorch_model-00004-of-00014.safetensors",
+    "transformer_blocks.2.adaln_proj.linear.weight": "diffusion_pytorch_model-00004-of-00014.safetensors",
+    "transformer_blocks.2.attn.norm_k.weight": "diffusion_pytorch_model-00004-of-00014.safetensors",
+    "transformer_blocks.2.attn.norm_q.weight": "diffusion_pytorch_model-00004-of-00014.safetensors",
+    "transformer_blocks.2.attn.to_gate_compress.weight": "diffusion_pytorch_model-00004-of-00014.safetensors",
+    "transformer_blocks.2.attn.to_k.weight": "diffusion_pytorch_model-00004-of-00014.safetensors",
+    "transformer_blocks.2.attn.to_out.0.weight": "diffusion_pytorch_model-00004-of-00014.safetensors",
+    "transformer_blocks.2.attn.to_q.weight": "diffusion_pytorch_model-00004-of-00014.safetensors",
+    "transformer_blocks.2.attn.to_v.weight": "diffusion_pytorch_model-00004-of-00014.safetensors",
+    "transformer_blocks.2.ff.net.0.proj.weight_packed": "diffusion_pytorch_model-00004-of-00014.safetensors",
+    "transformer_blocks.2.ff.net.0.proj.weight_scale": "diffusion_pytorch_model-00004-of-00014.safetensors",
+    "transformer_blocks.2.ff.net.0.proj.weight_tensor_scale": "diffusion_pytorch_model-00004-of-00014.safetensors",
+    "transformer_blocks.2.ff.net.2.weight_packed": "diffusion_pytorch_model-00004-of-00014.safetensors",
+    "transformer_blocks.2.ff.net.2.weight_scale": "diffusion_pytorch_model-00004-of-00014.safetensors",
+    "transformer_blocks.2.ff.net.2.weight_tensor_scale": "diffusion_pytorch_model-00004-of-00014.safetensors",
+    "transformer_blocks.2.norm1.weight": "diffusion_pytorch_model-00004-of-00014.safetensors",
+    "transformer_blocks.2.norm2.weight": "diffusion_pytorch_model-00004-of-00014.safetensors",
+    "transformer_blocks.20.adaln_proj.linear.bias": "diffusion_pytorch_model-00004-of-00014.safetensors",
+    "transformer_blocks.20.adaln_proj.linear.weight": "diffusion_pytorch_model-00004-of-00014.safetensors",
+    "transformer_blocks.20.attn.norm_k.weight": "diffusion_pytorch_model-00004-of-00014.safetensors",
+    "transformer_blocks.20.attn.norm_q.weight": "diffusion_pytorch_model-00004-of-00014.safetensors",
+    "transformer_blocks.20.attn.to_gate_compress.weight": "diffusion_pytorch_model-00004-of-00014.safetensors",
+    "transformer_blocks.20.attn.to_k.weight": "diffusion_pytorch_model-00004-of-00014.safetensors",
+    "transformer_blocks.20.attn.to_out.0.weight": "diffusion_pytorch_model-00004-of-00014.safetensors",
+    "transformer_blocks.20.attn.to_q.weight": "diffusion_pytorch_model-00004-of-00014.safetensors",
+    "transformer_blocks.20.attn.to_v.weight": "diffusion_pytorch_model-00004-of-00014.safetensors",
+    "transformer_blocks.20.ff.net.0.proj.weight_packed": "diffusion_pytorch_model-00004-of-00014.safetensors",
+    "transformer_blocks.20.ff.net.0.proj.weight_scale": "diffusion_pytorch_model-00004-of-00014.safetensors",
+    "transformer_blocks.20.ff.net.0.proj.weight_tensor_scale": "diffusion_pytorch_model-00004-of-00014.safetensors",
+    "transformer_blocks.20.ff.net.2.weight_packed": "diffusion_pytorch_model-00004-of-00014.safetensors",
+    "transformer_blocks.20.ff.net.2.weight_scale": "diffusion_pytorch_model-00004-of-00014.safetensors",
+    "transformer_blocks.20.ff.net.2.weight_tensor_scale": "diffusion_pytorch_model-00004-of-00014.safetensors",
+    "transformer_blocks.20.norm1.weight": "diffusion_pytorch_model-00004-of-00014.safetensors",
+    "transformer_blocks.20.norm2.weight": "diffusion_pytorch_model-00004-of-00014.safetensors",
+    "transformer_blocks.21.adaln_proj.linear.bias": "diffusion_pytorch_model-00004-of-00014.safetensors",
+    "transformer_blocks.21.adaln_proj.linear.weight": "diffusion_pytorch_model-00005-of-00014.safetensors",
+    "transformer_blocks.21.attn.norm_k.weight": "diffusion_pytorch_model-00005-of-00014.safetensors",
+    "transformer_blocks.21.attn.norm_q.weight": "diffusion_pytorch_model-00005-of-00014.safetensors",
+    "transformer_blocks.21.attn.to_gate_compress.weight": "diffusion_pytorch_model-00005-of-00014.safetensors",
+    "transformer_blocks.21.attn.to_k.weight": "diffusion_pytorch_model-00005-of-00014.safetensors",
+    "transformer_blocks.21.attn.to_out.0.weight": "diffusion_pytorch_model-00005-of-00014.safetensors",
+    "transformer_blocks.21.attn.to_q.weight": "diffusion_pytorch_model-00005-of-00014.safetensors",
+    "transformer_blocks.21.attn.to_v.weight": "diffusion_pytorch_model-00005-of-00014.safetensors",
+    "transformer_blocks.21.ff.net.0.proj.weight_packed": "diffusion_pytorch_model-00005-of-00014.safetensors",
+    "transformer_blocks.21.ff.net.0.proj.weight_scale": "diffusion_pytorch_model-00005-of-00014.safetensors",
+    "transformer_blocks.21.ff.net.0.proj.weight_tensor_scale": "diffusion_pytorch_model-00005-of-00014.safetensors",
+    "transformer_blocks.21.ff.net.2.weight_packed": "diffusion_pytorch_model-00005-of-00014.safetensors",
+    "transformer_blocks.21.ff.net.2.weight_scale": "diffusion_pytorch_model-00005-of-00014.safetensors",
+    "transformer_blocks.21.ff.net.2.weight_tensor_scale": "diffusion_pytorch_model-00005-of-00014.safetensors",
+    "transformer_blocks.21.norm1.weight": "diffusion_pytorch_model-00005-of-00014.safetensors",
+    "transformer_blocks.21.norm2.weight": "diffusion_pytorch_model-00005-of-00014.safetensors",
+    "transformer_blocks.22.adaln_proj.linear.bias": "diffusion_pytorch_model-00005-of-00014.safetensors",
+    "transformer_blocks.22.adaln_proj.linear.weight": "diffusion_pytorch_model-00005-of-00014.safetensors",
+    "transformer_blocks.22.attn.norm_k.weight": "diffusion_pytorch_model-00005-of-00014.safetensors",
+    "transformer_blocks.22.attn.norm_q.weight": "diffusion_pytorch_model-00005-of-00014.safetensors",
+    "transformer_blocks.22.attn.to_gate_compress.weight": "diffusion_pytorch_model-00005-of-00014.safetensors",
+    "transformer_blocks.22.attn.to_k.weight": "diffusion_pytorch_model-00005-of-00014.safetensors",
+    "transformer_blocks.22.attn.to_out.0.weight": "diffusion_pytorch_model-00005-of-00014.safetensors",
+    "transformer_blocks.22.attn.to_q.weight": "diffusion_pytorch_model-00005-of-00014.safetensors",
+    "transformer_blocks.22.attn.to_v.weight": "diffusion_pytorch_model-00005-of-00014.safetensors",
+    "transformer_blocks.22.ff.net.0.proj.weight_packed": "diffusion_pytorch_model-00005-of-00014.safetensors",
+    "transformer_blocks.22.ff.net.0.proj.weight_scale": "diffusion_pytorch_model-00005-of-00014.safetensors",
+    "transformer_blocks.22.ff.net.0.proj.weight_tensor_scale": "diffusion_pytorch_model-00005-of-00014.safetensors",
+    "transformer_blocks.22.ff.net.2.weight_packed": "diffusion_pytorch_model-00005-of-00014.safetensors",
+    "transformer_blocks.22.ff.net.2.weight_scale": "diffusion_pytorch_model-00005-of-00014.safetensors",
+    "transformer_blocks.22.ff.net.2.weight_tensor_scale": "diffusion_pytorch_model-00005-of-00014.safetensors",
+    "transformer_blocks.22.norm1.weight": "diffusion_pytorch_model-00005-of-00014.safetensors",
+    "transformer_blocks.22.norm2.weight": "diffusion_pytorch_model-00005-of-00014.safetensors",
+    "transformer_blocks.23.adaln_proj.linear.bias": "diffusion_pytorch_model-00005-of-00014.safetensors",
+    "transformer_blocks.23.adaln_proj.linear.weight": "diffusion_pytorch_model-00005-of-00014.safetensors",
+    "transformer_blocks.23.attn.norm_k.weight": "diffusion_pytorch_model-00005-of-00014.safetensors",
+    "transformer_blocks.23.attn.norm_q.weight": "diffusion_pytorch_model-00005-of-00014.safetensors",
+    "transformer_blocks.23.attn.to_gate_compress.weight": "diffusion_pytorch_model-00005-of-00014.safetensors",
+    "transformer_blocks.23.attn.to_k.weight": "diffusion_pytorch_model-00005-of-00014.safetensors",
+    "transformer_blocks.23.attn.to_out.0.weight": "diffusion_pytorch_model-00005-of-00014.safetensors",
+    "transformer_blocks.23.attn.to_q.weight": "diffusion_pytorch_model-00005-of-00014.safetensors",
+    "transformer_blocks.23.attn.to_v.weight": "diffusion_pytorch_model-00005-of-00014.safetensors",
+    "transformer_blocks.23.ff.net.0.proj.weight_packed": "diffusion_pytorch_model-00005-of-00014.safetensors",
+    "transformer_blocks.23.ff.net.0.proj.weight_scale": "diffusion_pytorch_model-00005-of-00014.safetensors",
+    "transformer_blocks.23.ff.net.0.proj.weight_tensor_scale": "diffusion_pytorch_model-00005-of-00014.safetensors",
+    "transformer_blocks.23.ff.net.2.weight_packed": "diffusion_pytorch_model-00005-of-00014.safetensors",
+    "transformer_blocks.23.ff.net.2.weight_scale": "diffusion_pytorch_model-00005-of-00014.safetensors",
+    "transformer_blocks.23.ff.net.2.weight_tensor_scale": "diffusion_pytorch_model-00005-of-00014.safetensors",
+    "transformer_blocks.23.norm1.weight": "diffusion_pytorch_model-00005-of-00014.safetensors",
+    "transformer_blocks.23.norm2.weight": "diffusion_pytorch_model-00005-of-00014.safetensors",
+    "transformer_blocks.24.adaln_proj.linear.bias": "diffusion_pytorch_model-00005-of-00014.safetensors",
+    "transformer_blocks.24.adaln_proj.linear.weight": "diffusion_pytorch_model-00005-of-00014.safetensors",
+    "transformer_blocks.24.attn.norm_k.weight": "diffusion_pytorch_model-00005-of-00014.safetensors",
+    "transformer_blocks.24.attn.norm_q.weight": "diffusion_pytorch_model-00005-of-00014.safetensors",
+    "transformer_blocks.24.attn.to_gate_compress.weight": "diffusion_pytorch_model-00005-of-00014.safetensors",
+    "transformer_blocks.24.attn.to_k.weight": "diffusion_pytorch_model-00005-of-00014.safetensors",
+    "transformer_blocks.24.attn.to_out.0.weight": "diffusion_pytorch_model-00005-of-00014.safetensors",
+    "transformer_blocks.24.attn.to_q.weight": "diffusion_pytorch_model-00005-of-00014.safetensors",
+    "transformer_blocks.24.attn.to_v.weight": "diffusion_pytorch_model-00005-of-00014.safetensors",
+    "transformer_blocks.24.ff.net.0.proj.weight_packed": "diffusion_pytorch_model-00005-of-00014.safetensors",
+    "transformer_blocks.24.ff.net.0.proj.weight_scale": "diffusion_pytorch_model-00005-of-00014.safetensors",
+    "transformer_blocks.24.ff.net.0.proj.weight_tensor_scale": "diffusion_pytorch_model-00005-of-00014.safetensors",
+    "transformer_blocks.24.ff.net.2.weight_packed": "diffusion_pytorch_model-00006-of-00014.safetensors",
+    "transformer_blocks.24.ff.net.2.weight_scale": "diffusion_pytorch_model-00006-of-00014.safetensors",
+    "transformer_blocks.24.ff.net.2.weight_tensor_scale": "diffusion_pytorch_model-00006-of-00014.safetensors",
+    "transformer_blocks.24.norm1.weight": "diffusion_pytorch_model-00006-of-00014.safetensors",
+    "transformer_blocks.24.norm2.weight": "diffusion_pytorch_model-00006-of-00014.safetensors",
+    "transformer_blocks.25.adaln_proj.linear.bias": "diffusion_pytorch_model-00006-of-00014.safetensors",
+    "transformer_blocks.25.adaln_proj.linear.weight": "diffusion_pytorch_model-00006-of-00014.safetensors",
+    "transformer_blocks.25.attn.norm_k.weight": "diffusion_pytorch_model-00006-of-00014.safetensors",
+    "transformer_blocks.25.attn.norm_q.weight": "diffusion_pytorch_model-00006-of-00014.safetensors",
+    "transformer_blocks.25.attn.to_gate_compress.weight": "diffusion_pytorch_model-00006-of-00014.safetensors",
+    "transformer_blocks.25.attn.to_k.weight": "diffusion_pytorch_model-00006-of-00014.safetensors",
+    "transformer_blocks.25.attn.to_out.0.weight": "diffusion_pytorch_model-00006-of-00014.safetensors",
+    "transformer_blocks.25.attn.to_q.weight": "diffusion_pytorch_model-00006-of-00014.safetensors",
+    "transformer_blocks.25.attn.to_v.weight": "diffusion_pytorch_model-00006-of-00014.safetensors",
+    "transformer_blocks.25.ff.net.0.proj.weight_packed": "diffusion_pytorch_model-00006-of-00014.safetensors",
+    "transformer_blocks.25.ff.net.0.proj.weight_scale": "diffusion_pytorch_model-00006-of-00014.safetensors",
+    "transformer_blocks.25.ff.net.0.proj.weight_tensor_scale": "diffusion_pytorch_model-00006-of-00014.safetensors",
+    "transformer_blocks.25.ff.net.2.weight_packed": "diffusion_pytorch_model-00006-of-00014.safetensors",
+    "transformer_blocks.25.ff.net.2.weight_scale": "diffusion_pytorch_model-00006-of-00014.safetensors",
+    "transformer_blocks.25.ff.net.2.weight_tensor_scale": "diffusion_pytorch_model-00006-of-00014.safetensors",
+    "transformer_blocks.25.norm1.weight": "diffusion_pytorch_model-00006-of-00014.safetensors",
+    "transformer_blocks.25.norm2.weight": "diffusion_pytorch_model-00006-of-00014.safetensors",
+    "transformer_blocks.26.adaln_proj.linear.bias": "diffusion_pytorch_model-00006-of-00014.safetensors",
+    "transformer_blocks.26.adaln_proj.linear.weight": "diffusion_pytorch_model-00006-of-00014.safetensors",
+    "transformer_blocks.26.attn.norm_k.weight": "diffusion_pytorch_model-00006-of-00014.safetensors",
+    "transformer_blocks.26.attn.norm_q.weight": "diffusion_pytorch_model-00006-of-00014.safetensors",
+    "transformer_blocks.26.attn.to_gate_compress.weight": "diffusion_pytorch_model-00006-of-00014.safetensors",
+    "transformer_blocks.26.attn.to_k.weight": "diffusion_pytorch_model-00006-of-00014.safetensors",
+    "transformer_blocks.26.attn.to_out.0.weight": "diffusion_pytorch_model-00006-of-00014.safetensors",
+    "transformer_blocks.26.attn.to_q.weight": "diffusion_pytorch_model-00006-of-00014.safetensors",
+    "transformer_blocks.26.attn.to_v.weight": "diffusion_pytorch_model-00006-of-00014.safetensors",
+    "transformer_blocks.26.ff.net.0.proj.weight_packed": "diffusion_pytorch_model-00006-of-00014.safetensors",
+    "transformer_blocks.26.ff.net.0.proj.weight_scale": "diffusion_pytorch_model-00006-of-00014.safetensors",
+    "transformer_blocks.26.ff.net.0.proj.weight_tensor_scale": "diffusion_pytorch_model-00006-of-00014.safetensors",
+    "transformer_blocks.26.ff.net.2.weight_packed": "diffusion_pytorch_model-00006-of-00014.safetensors",
+    "transformer_blocks.26.ff.net.2.weight_scale": "diffusion_pytorch_model-00006-of-00014.safetensors",
+    "transformer_blocks.26.ff.net.2.weight_tensor_scale": "diffusion_pytorch_model-00006-of-00014.safetensors",
+    "transformer_blocks.26.norm1.weight": "diffusion_pytorch_model-00006-of-00014.safetensors",
+    "transformer_blocks.26.norm2.weight": "diffusion_pytorch_model-00006-of-00014.safetensors",
+    "transformer_blocks.27.adaln_proj.linear.bias": "diffusion_pytorch_model-00006-of-00014.safetensors",
+    "transformer_blocks.27.adaln_proj.linear.weight": "diffusion_pytorch_model-00006-of-00014.safetensors",
+    "transformer_blocks.27.attn.norm_k.weight": "diffusion_pytorch_model-00006-of-00014.safetensors",
+    "transformer_blocks.27.attn.norm_q.weight": "diffusion_pytorch_model-00006-of-00014.safetensors",
+    "transformer_blocks.27.attn.to_gate_compress.weight": "diffusion_pytorch_model-00006-of-00014.safetensors",
+    "transformer_blocks.27.attn.to_k.weight": "diffusion_pytorch_model-00006-of-00014.safetensors",
+    "transformer_blocks.27.attn.to_out.0.weight": "diffusion_pytorch_model-00006-of-00014.safetensors",
+    "transformer_blocks.27.attn.to_q.weight": "diffusion_pytorch_model-00006-of-00014.safetensors",
+    "transformer_blocks.27.attn.to_v.weight": "diffusion_pytorch_model-00006-of-00014.safetensors",
+    "transformer_blocks.27.ff.net.0.proj.weight_packed": "diffusion_pytorch_model-00006-of-00014.safetensors",
+    "transformer_blocks.27.ff.net.0.proj.weight_scale": "diffusion_pytorch_model-00006-of-00014.safetensors",
+    "transformer_blocks.27.ff.net.0.proj.weight_tensor_scale": "diffusion_pytorch_model-00006-of-00014.safetensors",
+    "transformer_blocks.27.ff.net.2.weight_packed": "diffusion_pytorch_model-00006-of-00014.safetensors",
+    "transformer_blocks.27.ff.net.2.weight_scale": "diffusion_pytorch_model-00006-of-00014.safetensors",
+    "transformer_blocks.27.ff.net.2.weight_tensor_scale": "diffusion_pytorch_model-00006-of-00014.safetensors",
+    "transformer_blocks.27.norm1.weight": "diffusion_pytorch_model-00006-of-00014.safetensors",
+    "transformer_blocks.27.norm2.weight": "diffusion_pytorch_model-00006-of-00014.safetensors",
+    "transformer_blocks.28.adaln_proj.linear.bias": "diffusion_pytorch_model-00006-of-00014.safetensors",
+    "transformer_blocks.28.adaln_proj.linear.weight": "diffusion_pytorch_model-00006-of-00014.safetensors",
+    "transformer_blocks.28.attn.norm_k.weight": "diffusion_pytorch_model-00006-of-00014.safetensors",
+    "transformer_blocks.28.attn.norm_q.weight": "diffusion_pytorch_model-00006-of-00014.safetensors",
+    "transformer_blocks.28.attn.to_gate_compress.weight": "diffusion_pytorch_model-00006-of-00014.safetensors",
+    "transformer_blocks.28.attn.to_k.weight": "diffusion_pytorch_model-00006-of-00014.safetensors",
+    "transformer_blocks.28.attn.to_out.0.weight": "diffusion_pytorch_model-00006-of-00014.safetensors",
+    "transformer_blocks.28.attn.to_q.weight": "diffusion_pytorch_model-00006-of-00014.safetensors",
+    "transformer_blocks.28.attn.to_v.weight": "diffusion_pytorch_model-00006-of-00014.safetensors",
+    "transformer_blocks.28.ff.net.0.proj.weight_packed": "diffusion_pytorch_model-00007-of-00014.safetensors",
+    "transformer_blocks.28.ff.net.0.proj.weight_scale": "diffusion_pytorch_model-00007-of-00014.safetensors",
+    "transformer_blocks.28.ff.net.0.proj.weight_tensor_scale": "diffusion_pytorch_model-00007-of-00014.safetensors",
+    "transformer_blocks.28.ff.net.2.weight_packed": "diffusion_pytorch_model-00007-of-00014.safetensors",
+    "transformer_blocks.28.ff.net.2.weight_scale": "diffusion_pytorch_model-00007-of-00014.safetensors",
+    "transformer_blocks.28.ff.net.2.weight_tensor_scale": "diffusion_pytorch_model-00007-of-00014.safetensors",
+    "transformer_blocks.28.norm1.weight": "diffusion_pytorch_model-00007-of-00014.safetensors",
+    "transformer_blocks.28.norm2.weight": "diffusion_pytorch_model-00007-of-00014.safetensors",
+    "transformer_blocks.29.adaln_proj.linear.bias": "diffusion_pytorch_model-00007-of-00014.safetensors",
+    "transformer_blocks.29.adaln_proj.linear.weight": "diffusion_pytorch_model-00007-of-00014.safetensors",
+    "transformer_blocks.29.attn.norm_k.weight": "diffusion_pytorch_model-00007-of-00014.safetensors",
+    "transformer_blocks.29.attn.norm_q.weight": "diffusion_pytorch_model-00007-of-00014.safetensors",
+    "transformer_blocks.29.attn.to_gate_compress.weight": "diffusion_pytorch_model-00007-of-00014.safetensors",
+    "transformer_blocks.29.attn.to_k.weight": "diffusion_pytorch_model-00007-of-00014.safetensors",
+    "transformer_blocks.29.attn.to_out.0.weight": "diffusion_pytorch_model-00007-of-00014.safetensors",
+    "transformer_blocks.29.attn.to_q.weight": "diffusion_pytorch_model-00007-of-00014.safetensors",
+    "transformer_blocks.29.attn.to_v.weight": "diffusion_pytorch_model-00007-of-00014.safetensors",
+    "transformer_blocks.29.ff.net.0.proj.weight_packed": "diffusion_pytorch_model-00007-of-00014.safetensors",
+    "transformer_blocks.29.ff.net.0.proj.weight_scale": "diffusion_pytorch_model-00007-of-00014.safetensors",
+    "transformer_blocks.29.ff.net.0.proj.weight_tensor_scale": "diffusion_pytorch_model-00007-of-00014.safetensors",
+    "transformer_blocks.29.ff.net.2.weight_packed": "diffusion_pytorch_model-00007-of-00014.safetensors",
+    "transformer_blocks.29.ff.net.2.weight_scale": "diffusion_pytorch_model-00007-of-00014.safetensors",
+    "transformer_blocks.29.ff.net.2.weight_tensor_scale": "diffusion_pytorch_model-00007-of-00014.safetensors",
+    "transformer_blocks.29.norm1.weight": "diffusion_pytorch_model-00007-of-00014.safetensors",
+    "transformer_blocks.29.norm2.weight": "diffusion_pytorch_model-00007-of-00014.safetensors",
+    "transformer_blocks.3.adaln_proj.linear.bias": "diffusion_pytorch_model-00007-of-00014.safetensors",
+    "transformer_blocks.3.adaln_proj.linear.weight": "diffusion_pytorch_model-00007-of-00014.safetensors",
+    "transformer_blocks.3.attn.norm_k.weight": "diffusion_pytorch_model-00007-of-00014.safetensors",
+    "transformer_blocks.3.attn.norm_q.weight": "diffusion_pytorch_model-00007-of-00014.safetensors",
+    "transformer_blocks.3.attn.to_gate_compress.weight": "diffusion_pytorch_model-00007-of-00014.safetensors",
+    "transformer_blocks.3.attn.to_k.weight": "diffusion_pytorch_model-00007-of-00014.safetensors",
+    "transformer_blocks.3.attn.to_out.0.weight": "diffusion_pytorch_model-00007-of-00014.safetensors",
+    "transformer_blocks.3.attn.to_q.weight": "diffusion_pytorch_model-00007-of-00014.safetensors",
+    "transformer_blocks.3.attn.to_v.weight": "diffusion_pytorch_model-00007-of-00014.safetensors",
+    "transformer_blocks.3.ff.net.0.proj.weight_packed": "diffusion_pytorch_model-00007-of-00014.safetensors",
+    "transformer_blocks.3.ff.net.0.proj.weight_scale": "diffusion_pytorch_model-00007-of-00014.safetensors",
+    "transformer_blocks.3.ff.net.0.proj.weight_tensor_scale": "diffusion_pytorch_model-00007-of-00014.safetensors",
+    "transformer_blocks.3.ff.net.2.weight_packed": "diffusion_pytorch_model-00007-of-00014.safetensors",
+    "transformer_blocks.3.ff.net.2.weight_scale": "diffusion_pytorch_model-00007-of-00014.safetensors",
+    "transformer_blocks.3.ff.net.2.weight_tensor_scale": "diffusion_pytorch_model-00007-of-00014.safetensors",
+    "transformer_blocks.3.norm1.weight": "diffusion_pytorch_model-00007-of-00014.safetensors",
+    "transformer_blocks.3.norm2.weight": "diffusion_pytorch_model-00007-of-00014.safetensors",
+    "transformer_blocks.30.adaln_proj.linear.bias": "diffusion_pytorch_model-00007-of-00014.safetensors",
+    "transformer_blocks.30.adaln_proj.linear.weight": "diffusion_pytorch_model-00007-of-00014.safetensors",
+    "transformer_blocks.30.attn.norm_k.weight": "diffusion_pytorch_model-00007-of-00014.safetensors",
+    "transformer_blocks.30.attn.norm_q.weight": "diffusion_pytorch_model-00007-of-00014.safetensors",
+    "transformer_blocks.30.attn.to_gate_compress.weight": "diffusion_pytorch_model-00007-of-00014.safetensors",
+    "transformer_blocks.30.attn.to_k.weight": "diffusion_pytorch_model-00007-of-00014.safetensors",
+    "transformer_blocks.30.attn.to_out.0.weight": "diffusion_pytorch_model-00007-of-00014.safetensors",
+    "transformer_blocks.30.attn.to_q.weight": "diffusion_pytorch_model-00007-of-00014.safetensors",
+    "transformer_blocks.30.attn.to_v.weight": "diffusion_pytorch_model-00007-of-00014.safetensors",
+    "transformer_blocks.30.ff.net.0.proj.weight_packed": "diffusion_pytorch_model-00007-of-00014.safetensors",
+    "transformer_blocks.30.ff.net.0.proj.weight_scale": "diffusion_pytorch_model-00007-of-00014.safetensors",
+    "transformer_blocks.30.ff.net.0.proj.weight_tensor_scale": "diffusion_pytorch_model-00007-of-00014.safetensors",
+    "transformer_blocks.30.ff.net.2.weight_packed": "diffusion_pytorch_model-00007-of-00014.safetensors",
+    "transformer_blocks.30.ff.net.2.weight_scale": "diffusion_pytorch_model-00007-of-00014.safetensors",
+    "transformer_blocks.30.ff.net.2.weight_tensor_scale": "diffusion_pytorch_model-00007-of-00014.safetensors",
+    "transformer_blocks.30.norm1.weight": "diffusion_pytorch_model-00007-of-00014.safetensors",
+    "transformer_blocks.30.norm2.weight": "diffusion_pytorch_model-00007-of-00014.safetensors",
+    "transformer_blocks.31.adaln_proj.linear.bias": "diffusion_pytorch_model-00007-of-00014.safetensors",
+    "transformer_blocks.31.adaln_proj.linear.weight": "diffusion_pytorch_model-00007-of-00014.safetensors",
+    "transformer_blocks.31.attn.norm_k.weight": "diffusion_pytorch_model-00007-of-00014.safetensors",
+    "transformer_blocks.31.attn.norm_q.weight": "diffusion_pytorch_model-00007-of-00014.safetensors",
+    "transformer_blocks.31.attn.to_gate_compress.weight": "diffusion_pytorch_model-00007-of-00014.safetensors",
+    "transformer_blocks.31.attn.to_k.weight": "diffusion_pytorch_model-00007-of-00014.safetensors",
+    "transformer_blocks.31.attn.to_out.0.weight": "diffusion_pytorch_model-00007-of-00014.safetensors",
+    "transformer_blocks.31.attn.to_q.weight": "diffusion_pytorch_model-00008-of-00014.safetensors",
+    "transformer_blocks.31.attn.to_v.weight": "diffusion_pytorch_model-00008-of-00014.safetensors",
+    "transformer_blocks.31.ff.net.0.proj.weight_packed": "diffusion_pytorch_model-00008-of-00014.safetensors",
+    "transformer_blocks.31.ff.net.0.proj.weight_scale": "diffusion_pytorch_model-00008-of-00014.safetensors",
+    "transformer_blocks.31.ff.net.0.proj.weight_tensor_scale": "diffusion_pytorch_model-00008-of-00014.safetensors",
+    "transformer_blocks.31.ff.net.2.weight_packed": "diffusion_pytorch_model-00008-of-00014.safetensors",
+    "transformer_blocks.31.ff.net.2.weight_scale": "diffusion_pytorch_model-00008-of-00014.safetensors",
+    "transformer_blocks.31.ff.net.2.weight_tensor_scale": "diffusion_pytorch_model-00008-of-00014.safetensors",
+    "transformer_blocks.31.norm1.weight": "diffusion_pytorch_model-00008-of-00014.safetensors",
+    "transformer_blocks.31.norm2.weight": "diffusion_pytorch_model-00008-of-00014.safetensors",
+    "transformer_blocks.32.adaln_proj.linear.bias": "diffusion_pytorch_model-00008-of-00014.safetensors",
+    "transformer_blocks.32.adaln_proj.linear.weight": "diffusion_pytorch_model-00008-of-00014.safetensors",
+    "transformer_blocks.32.attn.norm_k.weight": "diffusion_pytorch_model-00008-of-00014.safetensors",
+    "transformer_blocks.32.attn.norm_q.weight": "diffusion_pytorch_model-00008-of-00014.safetensors",
+    "transformer_blocks.32.attn.to_gate_compress.weight": "diffusion_pytorch_model-00008-of-00014.safetensors",
+    "transformer_blocks.32.attn.to_k.weight": "diffusion_pytorch_model-00008-of-00014.safetensors",
+    "transformer_blocks.32.attn.to_out.0.weight": "diffusion_pytorch_model-00008-of-00014.safetensors",
+    "transformer_blocks.32.attn.to_q.weight": "diffusion_pytorch_model-00008-of-00014.safetensors",
+    "transformer_blocks.32.attn.to_v.weight": "diffusion_pytorch_model-00008-of-00014.safetensors",
+    "transformer_blocks.32.ff.net.0.proj.weight_packed": "diffusion_pytorch_model-00008-of-00014.safetensors",
+    "transformer_blocks.32.ff.net.0.proj.weight_scale": "diffusion_pytorch_model-00008-of-00014.safetensors",
+    "transformer_blocks.32.ff.net.0.proj.weight_tensor_scale": "diffusion_pytorch_model-00008-of-00014.safetensors",
+    "transformer_blocks.32.ff.net.2.weight_packed": "diffusion_pytorch_model-00008-of-00014.safetensors",
+    "transformer_blocks.32.ff.net.2.weight_scale": "diffusion_pytorch_model-00008-of-00014.safetensors",
+    "transformer_blocks.32.ff.net.2.weight_tensor_scale": "diffusion_pytorch_model-00008-of-00014.safetensors",
+    "transformer_blocks.32.norm1.weight": "diffusion_pytorch_model-00008-of-00014.safetensors",
+    "transformer_blocks.32.norm2.weight": "diffusion_pytorch_model-00008-of-00014.safetensors",
+    "transformer_blocks.33.adaln_proj.linear.bias": "diffusion_pytorch_model-00008-of-00014.safetensors",
+    "transformer_blocks.33.adaln_proj.linear.weight": "diffusion_pytorch_model-00008-of-00014.safetensors",
+    "transformer_blocks.33.attn.norm_k.weight": "diffusion_pytorch_model-00008-of-00014.safetensors",
+    "transformer_blocks.33.attn.norm_q.weight": "diffusion_pytorch_model-00008-of-00014.safetensors",
+    "transformer_blocks.33.attn.to_gate_compress.weight": "diffusion_pytorch_model-00008-of-00014.safetensors",
+    "transformer_blocks.33.attn.to_k.weight": "diffusion_pytorch_model-00008-of-00014.safetensors",
+    "transformer_blocks.33.attn.to_out.0.weight": "diffusion_pytorch_model-00008-of-00014.safetensors",
+    "transformer_blocks.33.attn.to_q.weight": "diffusion_pytorch_model-00008-of-00014.safetensors",
+    "transformer_blocks.33.attn.to_v.weight": "diffusion_pytorch_model-00008-of-00014.safetensors",
+    "transformer_blocks.33.ff.net.0.proj.weight_packed": "diffusion_pytorch_model-00008-of-00014.safetensors",
+    "transformer_blocks.33.ff.net.0.proj.weight_scale": "diffusion_pytorch_model-00008-of-00014.safetensors",
+    "transformer_blocks.33.ff.net.0.proj.weight_tensor_scale": "diffusion_pytorch_model-00008-of-00014.safetensors",
+    "transformer_blocks.33.ff.net.2.weight_packed": "diffusion_pytorch_model-00008-of-00014.safetensors",
+    "transformer_blocks.33.ff.net.2.weight_scale": "diffusion_pytorch_model-00008-of-00014.safetensors",
+    "transformer_blocks.33.ff.net.2.weight_tensor_scale": "diffusion_pytorch_model-00008-of-00014.safetensors",
+    "transformer_blocks.33.norm1.weight": "diffusion_pytorch_model-00008-of-00014.safetensors",
+    "transformer_blocks.33.norm2.weight": "diffusion_pytorch_model-00008-of-00014.safetensors",
+    "transformer_blocks.34.adaln_proj.linear.bias": "diffusion_pytorch_model-00008-of-00014.safetensors",
+    "transformer_blocks.34.adaln_proj.linear.weight": "diffusion_pytorch_model-00008-of-00014.safetensors",
+    "transformer_blocks.34.attn.norm_k.weight": "diffusion_pytorch_model-00008-of-00014.safetensors",
+    "transformer_blocks.34.attn.norm_q.weight": "diffusion_pytorch_model-00008-of-00014.safetensors",
+    "transformer_blocks.34.attn.to_gate_compress.weight": "diffusion_pytorch_model-00008-of-00014.safetensors",
+    "transformer_blocks.34.attn.to_k.weight": "diffusion_pytorch_model-00008-of-00014.safetensors",
+    "transformer_blocks.34.attn.to_out.0.weight": "diffusion_pytorch_model-00008-of-00014.safetensors",
+    "transformer_blocks.34.attn.to_q.weight": "diffusion_pytorch_model-00008-of-00014.safetensors",
+    "transformer_blocks.34.attn.to_v.weight": "diffusion_pytorch_model-00008-of-00014.safetensors",
+    "transformer_blocks.34.ff.net.0.proj.weight_packed": "diffusion_pytorch_model-00008-of-00014.safetensors",
+    "transformer_blocks.34.ff.net.0.proj.weight_scale": "diffusion_pytorch_model-00008-of-00014.safetensors",
+    "transformer_blocks.34.ff.net.0.proj.weight_tensor_scale": "diffusion_pytorch_model-00008-of-00014.safetensors",
+    "transformer_blocks.34.ff.net.2.weight_packed": "diffusion_pytorch_model-00008-of-00014.safetensors",
+    "transformer_blocks.34.ff.net.2.weight_scale": "diffusion_pytorch_model-00008-of-00014.safetensors",
+    "transformer_blocks.34.ff.net.2.weight_tensor_scale": "diffusion_pytorch_model-00008-of-00014.safetensors",
+    "transformer_blocks.34.norm1.weight": "diffusion_pytorch_model-00008-of-00014.safetensors",
+    "transformer_blocks.34.norm2.weight": "diffusion_pytorch_model-00008-of-00014.safetensors",
+    "transformer_blocks.35.adaln_proj.linear.bias": "diffusion_pytorch_model-00008-of-00014.safetensors",
+    "transformer_blocks.35.adaln_proj.linear.weight": "diffusion_pytorch_model-00008-of-00014.safetensors",
+    "transformer_blocks.35.attn.norm_k.weight": "diffusion_pytorch_model-00008-of-00014.safetensors",
+    "transformer_blocks.35.attn.norm_q.weight": "diffusion_pytorch_model-00008-of-00014.safetensors",
+    "transformer_blocks.35.attn.to_gate_compress.weight": "diffusion_pytorch_model-00008-of-00014.safetensors",
+    "transformer_blocks.35.attn.to_k.weight": "diffusion_pytorch_model-00009-of-00014.safetensors",
+    "transformer_blocks.35.attn.to_out.0.weight": "diffusion_pytorch_model-00009-of-00014.safetensors",
+    "transformer_blocks.35.attn.to_q.weight": "diffusion_pytorch_model-00009-of-00014.safetensors",
+    "transformer_blocks.35.attn.to_v.weight": "diffusion_pytorch_model-00009-of-00014.safetensors",
+    "transformer_blocks.35.ff.net.0.proj.weight_packed": "diffusion_pytorch_model-00009-of-00014.safetensors",
+    "transformer_blocks.35.ff.net.0.proj.weight_scale": "diffusion_pytorch_model-00009-of-00014.safetensors",
+    "transformer_blocks.35.ff.net.0.proj.weight_tensor_scale": "diffusion_pytorch_model-00009-of-00014.safetensors",
+    "transformer_blocks.35.ff.net.2.weight_packed": "diffusion_pytorch_model-00009-of-00014.safetensors",
+    "transformer_blocks.35.ff.net.2.weight_scale": "diffusion_pytorch_model-00009-of-00014.safetensors",
+    "transformer_blocks.35.ff.net.2.weight_tensor_scale": "diffusion_pytorch_model-00009-of-00014.safetensors",
+    "transformer_blocks.35.norm1.weight": "diffusion_pytorch_model-00009-of-00014.safetensors",
+    "transformer_blocks.35.norm2.weight": "diffusion_pytorch_model-00009-of-00014.safetensors",
+    "transformer_blocks.36.adaln_proj.linear.bias": "diffusion_pytorch_model-00009-of-00014.safetensors",
+    "transformer_blocks.36.adaln_proj.linear.weight": "diffusion_pytorch_model-00009-of-00014.safetensors",
+    "transformer_blocks.36.attn.norm_k.weight": "diffusion_pytorch_model-00009-of-00014.safetensors",
+    "transformer_blocks.36.attn.norm_q.weight": "diffusion_pytorch_model-00009-of-00014.safetensors",
+    "transformer_blocks.36.attn.to_gate_compress.weight": "diffusion_pytorch_model-00009-of-00014.safetensors",
+    "transformer_blocks.36.attn.to_k.weight": "diffusion_pytorch_model-00009-of-00014.safetensors",
+    "transformer_blocks.36.attn.to_out.0.weight": "diffusion_pytorch_model-00009-of-00014.safetensors",
+    "transformer_blocks.36.attn.to_q.weight": "diffusion_pytorch_model-00009-of-00014.safetensors",
+    "transformer_blocks.36.attn.to_v.weight": "diffusion_pytorch_model-00009-of-00014.safetensors",
+    "transformer_blocks.36.ff.net.0.proj.weight_packed": "diffusion_pytorch_model-00009-of-00014.safetensors",
+    "transformer_blocks.36.ff.net.0.proj.weight_scale": "diffusion_pytorch_model-00009-of-00014.safetensors",
+    "transformer_blocks.36.ff.net.0.proj.weight_tensor_scale": "diffusion_pytorch_model-00009-of-00014.safetensors",
+    "transformer_blocks.36.ff.net.2.weight_packed": "diffusion_pytorch_model-00009-of-00014.safetensors",
+    "transformer_blocks.36.ff.net.2.weight_scale": "diffusion_pytorch_model-00009-of-00014.safetensors",
+    "transformer_blocks.36.ff.net.2.weight_tensor_scale": "diffusion_pytorch_model-00009-of-00014.safetensors",
+    "transformer_blocks.36.norm1.weight": "diffusion_pytorch_model-00009-of-00014.safetensors",
+    "transformer_blocks.36.norm2.weight": "diffusion_pytorch_model-00009-of-00014.safetensors",
+    "transformer_blocks.37.adaln_proj.linear.bias": "diffusion_pytorch_model-00009-of-00014.safetensors",
+    "transformer_blocks.37.adaln_proj.linear.weight": "diffusion_pytorch_model-00009-of-00014.safetensors",
+    "transformer_blocks.37.attn.norm_k.weight": "diffusion_pytorch_model-00009-of-00014.safetensors",
+    "transformer_blocks.37.attn.norm_q.weight": "diffusion_pytorch_model-00009-of-00014.safetensors",
+    "transformer_blocks.37.attn.to_gate_compress.weight": "diffusion_pytorch_model-00009-of-00014.safetensors",
+    "transformer_blocks.37.attn.to_k.weight": "diffusion_pytorch_model-00009-of-00014.safetensors",
+    "transformer_blocks.37.attn.to_out.0.weight": "diffusion_pytorch_model-00009-of-00014.safetensors",
+    "transformer_blocks.37.attn.to_q.weight": "diffusion_pytorch_model-00009-of-00014.safetensors",
+    "transformer_blocks.37.attn.to_v.weight": "diffusion_pytorch_model-00009-of-00014.safetensors",
+    "transformer_blocks.37.ff.net.0.proj.weight_packed": "diffusion_pytorch_model-00009-of-00014.safetensors",
+    "transformer_blocks.37.ff.net.0.proj.weight_scale": "diffusion_pytorch_model-00009-of-00014.safetensors",
+    "transformer_blocks.37.ff.net.0.proj.weight_tensor_scale": "diffusion_pytorch_model-00009-of-00014.safetensors",
+    "transformer_blocks.37.ff.net.2.weight_packed": "diffusion_pytorch_model-00009-of-00014.safetensors",
+    "transformer_blocks.37.ff.net.2.weight_scale": "diffusion_pytorch_model-00009-of-00014.safetensors",
+    "transformer_blocks.37.ff.net.2.weight_tensor_scale": "diffusion_pytorch_model-00009-of-00014.safetensors",
+    "transformer_blocks.37.norm1.weight": "diffusion_pytorch_model-00009-of-00014.safetensors",
+    "transformer_blocks.37.norm2.weight": "diffusion_pytorch_model-00009-of-00014.safetensors",
+    "transformer_blocks.38.adaln_proj.linear.bias": "diffusion_pytorch_model-00009-of-00014.safetensors",
+    "transformer_blocks.38.adaln_proj.linear.weight": "diffusion_pytorch_model-00009-of-00014.safetensors",
+    "transformer_blocks.38.attn.norm_k.weight": "diffusion_pytorch_model-00009-of-00014.safetensors",
+    "transformer_blocks.38.attn.norm_q.weight": "diffusion_pytorch_model-00009-of-00014.safetensors",
+    "transformer_blocks.38.attn.to_gate_compress.weight": "diffusion_pytorch_model-00009-of-00014.safetensors",
+    "transformer_blocks.38.attn.to_k.weight": "diffusion_pytorch_model-00009-of-00014.safetensors",
+    "transformer_blocks.38.attn.to_out.0.weight": "diffusion_pytorch_model-00009-of-00014.safetensors",
+    "transformer_blocks.38.attn.to_q.weight": "diffusion_pytorch_model-00009-of-00014.safetensors",
+    "transformer_blocks.38.attn.to_v.weight": "diffusion_pytorch_model-00009-of-00014.safetensors",
+    "transformer_blocks.38.ff.net.0.proj.weight_packed": "diffusion_pytorch_model-00009-of-00014.safetensors",
+    "transformer_blocks.38.ff.net.0.proj.weight_scale": "diffusion_pytorch_model-00009-of-00014.safetensors",
+    "transformer_blocks.38.ff.net.0.proj.weight_tensor_scale": "diffusion_pytorch_model-00009-of-00014.safetensors",
+    "transformer_blocks.38.ff.net.2.weight_packed": "diffusion_pytorch_model-00009-of-00014.safetensors",
+    "transformer_blocks.38.ff.net.2.weight_scale": "diffusion_pytorch_model-00009-of-00014.safetensors",
+    "transformer_blocks.38.ff.net.2.weight_tensor_scale": "diffusion_pytorch_model-00009-of-00014.safetensors",
+    "transformer_blocks.38.norm1.weight": "diffusion_pytorch_model-00009-of-00014.safetensors",
+    "transformer_blocks.38.norm2.weight": "diffusion_pytorch_model-00009-of-00014.safetensors",
+    "transformer_blocks.39.adaln_proj.linear.bias": "diffusion_pytorch_model-00009-of-00014.safetensors",
+    "transformer_blocks.39.adaln_proj.linear.weight": "diffusion_pytorch_model-00010-of-00014.safetensors",
+    "transformer_blocks.39.attn.norm_k.weight": "diffusion_pytorch_model-00010-of-00014.safetensors",
+    "transformer_blocks.39.attn.norm_q.weight": "diffusion_pytorch_model-00010-of-00014.safetensors",
+    "transformer_blocks.39.attn.to_gate_compress.weight": "diffusion_pytorch_model-00010-of-00014.safetensors",
+    "transformer_blocks.39.attn.to_k.weight": "diffusion_pytorch_model-00010-of-00014.safetensors",
+    "transformer_blocks.39.attn.to_out.0.weight": "diffusion_pytorch_model-00010-of-00014.safetensors",
+    "transformer_blocks.39.attn.to_q.weight": "diffusion_pytorch_model-00010-of-00014.safetensors",
+    "transformer_blocks.39.attn.to_v.weight": "diffusion_pytorch_model-00010-of-00014.safetensors",
+    "transformer_blocks.39.ff.net.0.proj.weight_packed": "diffusion_pytorch_model-00010-of-00014.safetensors",
+    "transformer_blocks.39.ff.net.0.proj.weight_scale": "diffusion_pytorch_model-00010-of-00014.safetensors",
+    "transformer_blocks.39.ff.net.0.proj.weight_tensor_scale": "diffusion_pytorch_model-00010-of-00014.safetensors",
+    "transformer_blocks.39.ff.net.2.weight_packed": "diffusion_pytorch_model-00010-of-00014.safetensors",
+    "transformer_blocks.39.ff.net.2.weight_scale": "diffusion_pytorch_model-00010-of-00014.safetensors",
+    "transformer_blocks.39.ff.net.2.weight_tensor_scale": "diffusion_pytorch_model-00010-of-00014.safetensors",
+    "transformer_blocks.39.norm1.weight": "diffusion_pytorch_model-00010-of-00014.safetensors",
+    "transformer_blocks.39.norm2.weight": "diffusion_pytorch_model-00010-of-00014.safetensors",
+    "transformer_blocks.4.adaln_proj.linear.bias": "diffusion_pytorch_model-00010-of-00014.safetensors",
+    "transformer_blocks.4.adaln_proj.linear.weight": "diffusion_pytorch_model-00010-of-00014.safetensors",
+    "transformer_blocks.4.attn.norm_k.weight": "diffusion_pytorch_model-00010-of-00014.safetensors",
+    "transformer_blocks.4.attn.norm_q.weight": "diffusion_pytorch_model-00010-of-00014.safetensors",
+    "transformer_blocks.4.attn.to_gate_compress.weight": "diffusion_pytorch_model-00010-of-00014.safetensors",
+    "transformer_blocks.4.attn.to_k.weight": "diffusion_pytorch_model-00010-of-00014.safetensors",
+    "transformer_blocks.4.attn.to_out.0.weight": "diffusion_pytorch_model-00010-of-00014.safetensors",
+    "transformer_blocks.4.attn.to_q.weight": "diffusion_pytorch_model-00010-of-00014.safetensors",
+    "transformer_blocks.4.attn.to_v.weight": "diffusion_pytorch_model-00010-of-00014.safetensors",
+    "transformer_blocks.4.ff.net.0.proj.weight_packed": "diffusion_pytorch_model-00010-of-00014.safetensors",
+    "transformer_blocks.4.ff.net.0.proj.weight_scale": "diffusion_pytorch_model-00010-of-00014.safetensors",
+    "transformer_blocks.4.ff.net.0.proj.weight_tensor_scale": "diffusion_pytorch_model-00010-of-00014.safetensors",
+    "transformer_blocks.4.ff.net.2.weight_packed": "diffusion_pytorch_model-00010-of-00014.safetensors",
+    "transformer_blocks.4.ff.net.2.weight_scale": "diffusion_pytorch_model-00010-of-00014.safetensors",
+    "transformer_blocks.4.ff.net.2.weight_tensor_scale": "diffusion_pytorch_model-00010-of-00014.safetensors",
+    "transformer_blocks.4.norm1.weight": "diffusion_pytorch_model-00010-of-00014.safetensors",
+    "transformer_blocks.4.norm2.weight": "diffusion_pytorch_model-00010-of-00014.safetensors",
+    "transformer_blocks.40.adaln_proj.linear.bias": "diffusion_pytorch_model-00010-of-00014.safetensors",
+    "transformer_blocks.40.adaln_proj.linear.weight": "diffusion_pytorch_model-00010-of-00014.safetensors",
+    "transformer_blocks.40.attn.norm_k.weight": "diffusion_pytorch_model-00010-of-00014.safetensors",
+    "transformer_blocks.40.attn.norm_q.weight": "diffusion_pytorch_model-00010-of-00014.safetensors",
+    "transformer_blocks.40.attn.to_gate_compress.weight": "diffusion_pytorch_model-00010-of-00014.safetensors",
+    "transformer_blocks.40.attn.to_k.weight": "diffusion_pytorch_model-00010-of-00014.safetensors",
+    "transformer_blocks.40.attn.to_out.0.weight": "diffusion_pytorch_model-00010-of-00014.safetensors",
+    "transformer_blocks.40.attn.to_q.weight": "diffusion_pytorch_model-00010-of-00014.safetensors",
+    "transformer_blocks.40.attn.to_v.weight": "diffusion_pytorch_model-00010-of-00014.safetensors",
+    "transformer_blocks.40.ff.net.0.proj.weight_packed": "diffusion_pytorch_model-00010-of-00014.safetensors",
+    "transformer_blocks.40.ff.net.0.proj.weight_scale": "diffusion_pytorch_model-00010-of-00014.safetensors",
+    "transformer_blocks.40.ff.net.0.proj.weight_tensor_scale": "diffusion_pytorch_model-00010-of-00014.safetensors",
+    "transformer_blocks.40.ff.net.2.weight_packed": "diffusion_pytorch_model-00010-of-00014.safetensors",
+    "transformer_blocks.40.ff.net.2.weight_scale": "diffusion_pytorch_model-00010-of-00014.safetensors",
+    "transformer_blocks.40.ff.net.2.weight_tensor_scale": "diffusion_pytorch_model-00010-of-00014.safetensors",
+    "transformer_blocks.40.norm1.weight": "diffusion_pytorch_model-00010-of-00014.safetensors",
+    "transformer_blocks.40.norm2.weight": "diffusion_pytorch_model-00010-of-00014.safetensors",
+    "transformer_blocks.41.adaln_proj.linear.bias": "diffusion_pytorch_model-00010-of-00014.safetensors",
+    "transformer_blocks.41.adaln_proj.linear.weight": "diffusion_pytorch_model-00010-of-00014.safetensors",
+    "transformer_blocks.41.attn.norm_k.weight": "diffusion_pytorch_model-00010-of-00014.safetensors",
+    "transformer_blocks.41.attn.norm_q.weight": "diffusion_pytorch_model-00010-of-00014.safetensors",
+    "transformer_blocks.41.attn.to_gate_compress.weight": "diffusion_pytorch_model-00010-of-00014.safetensors",
+    "transformer_blocks.41.attn.to_k.weight": "diffusion_pytorch_model-00010-of-00014.safetensors",
+    "transformer_blocks.41.attn.to_out.0.weight": "diffusion_pytorch_model-00010-of-00014.safetensors",
+    "transformer_blocks.41.attn.to_q.weight": "diffusion_pytorch_model-00010-of-00014.safetensors",
+    "transformer_blocks.41.attn.to_v.weight": "diffusion_pytorch_model-00010-of-00014.safetensors",
+    "transformer_blocks.41.ff.net.0.proj.weight_packed": "diffusion_pytorch_model-00010-of-00014.safetensors",
+    "transformer_blocks.41.ff.net.0.proj.weight_scale": "diffusion_pytorch_model-00010-of-00014.safetensors",
+    "transformer_blocks.41.ff.net.0.proj.weight_tensor_scale": "diffusion_pytorch_model-00010-of-00014.safetensors",
+    "transformer_blocks.41.ff.net.2.weight_packed": "diffusion_pytorch_model-00011-of-00014.safetensors",
+    "transformer_blocks.41.ff.net.2.weight_scale": "diffusion_pytorch_model-00011-of-00014.safetensors",
+    "transformer_blocks.41.ff.net.2.weight_tensor_scale": "diffusion_pytorch_model-00011-of-00014.safetensors",
+    "transformer_blocks.41.norm1.weight": "diffusion_pytorch_model-00011-of-00014.safetensors",
+    "transformer_blocks.41.norm2.weight": "diffusion_pytorch_model-00011-of-00014.safetensors",
+    "transformer_blocks.42.adaln_proj.linear.bias": "diffusion_pytorch_model-00011-of-00014.safetensors",
+    "transformer_blocks.42.adaln_proj.linear.weight": "diffusion_pytorch_model-00011-of-00014.safetensors",
+    "transformer_blocks.42.attn.norm_k.weight": "diffusion_pytorch_model-00011-of-00014.safetensors",
+    "transformer_blocks.42.attn.norm_q.weight": "diffusion_pytorch_model-00011-of-00014.safetensors",
+    "transformer_blocks.42.attn.to_gate_compress.weight": "diffusion_pytorch_model-00011-of-00014.safetensors",
+    "transformer_blocks.42.attn.to_k.weight": "diffusion_pytorch_model-00011-of-00014.safetensors",
+    "transformer_blocks.42.attn.to_out.0.weight": "diffusion_pytorch_model-00011-of-00014.safetensors",
+    "transformer_blocks.42.attn.to_q.weight": "diffusion_pytorch_model-00011-of-00014.safetensors",
+    "transformer_blocks.42.attn.to_v.weight": "diffusion_pytorch_model-00011-of-00014.safetensors",
+    "transformer_blocks.42.ff.net.0.proj.weight_packed": "diffusion_pytorch_model-00011-of-00014.safetensors",
+    "transformer_blocks.42.ff.net.0.proj.weight_scale": "diffusion_pytorch_model-00011-of-00014.safetensors",
+    "transformer_blocks.42.ff.net.0.proj.weight_tensor_scale": "diffusion_pytorch_model-00011-of-00014.safetensors",
+    "transformer_blocks.42.ff.net.2.weight_packed": "diffusion_pytorch_model-00011-of-00014.safetensors",
+    "transformer_blocks.42.ff.net.2.weight_scale": "diffusion_pytorch_model-00011-of-00014.safetensors",
+    "transformer_blocks.42.ff.net.2.weight_tensor_scale": "diffusion_pytorch_model-00011-of-00014.safetensors",
+    "transformer_blocks.42.norm1.weight": "diffusion_pytorch_model-00011-of-00014.safetensors",
+    "transformer_blocks.42.norm2.weight": "diffusion_pytorch_model-00011-of-00014.safetensors",
+    "transformer_blocks.43.adaln_proj.linear.bias": "diffusion_pytorch_model-00011-of-00014.safetensors",
+    "transformer_blocks.43.adaln_proj.linear.weight": "diffusion_pytorch_model-00011-of-00014.safetensors",
+    "transformer_blocks.43.attn.norm_k.weight": "diffusion_pytorch_model-00011-of-00014.safetensors",
+    "transformer_blocks.43.attn.norm_q.weight": "diffusion_pytorch_model-00011-of-00014.safetensors",
+    "transformer_blocks.43.attn.to_gate_compress.weight": "diffusion_pytorch_model-00011-of-00014.safetensors",
+    "transformer_blocks.43.attn.to_k.weight": "diffusion_pytorch_model-00011-of-00014.safetensors",
+    "transformer_blocks.43.attn.to_out.0.weight": "diffusion_pytorch_model-00011-of-00014.safetensors",
+    "transformer_blocks.43.attn.to_q.weight": "diffusion_pytorch_model-00011-of-00014.safetensors",
+    "transformer_blocks.43.attn.to_v.weight": "diffusion_pytorch_model-00011-of-00014.safetensors",
+    "transformer_blocks.43.ff.net.0.proj.weight_packed": "diffusion_pytorch_model-00011-of-00014.safetensors",
+    "transformer_blocks.43.ff.net.0.proj.weight_scale": "diffusion_pytorch_model-00011-of-00014.safetensors",
+    "transformer_blocks.43.ff.net.0.proj.weight_tensor_scale": "diffusion_pytorch_model-00011-of-00014.safetensors",
+    "transformer_blocks.43.ff.net.2.weight_packed": "diffusion_pytorch_model-00011-of-00014.safetensors",
+    "transformer_blocks.43.ff.net.2.weight_scale": "diffusion_pytorch_model-00011-of-00014.safetensors",
+    "transformer_blocks.43.ff.net.2.weight_tensor_scale": "diffusion_pytorch_model-00011-of-00014.safetensors",
+    "transformer_blocks.43.norm1.weight": "diffusion_pytorch_model-00011-of-00014.safetensors",
+    "transformer_blocks.43.norm2.weight": "diffusion_pytorch_model-00011-of-00014.safetensors",
+    "transformer_blocks.44.adaln_proj.linear.bias": "diffusion_pytorch_model-00011-of-00014.safetensors",
+    "transformer_blocks.44.adaln_proj.linear.weight": "diffusion_pytorch_model-00011-of-00014.safetensors",
+    "transformer_blocks.44.attn.norm_k.weight": "diffusion_pytorch_model-00011-of-00014.safetensors",
+    "transformer_blocks.44.attn.norm_q.weight": "diffusion_pytorch_model-00011-of-00014.safetensors",
+    "transformer_blocks.44.attn.to_gate_compress.weight": "diffusion_pytorch_model-00011-of-00014.safetensors",
+    "transformer_blocks.44.attn.to_k.weight": "diffusion_pytorch_model-00011-of-00014.safetensors",
+    "transformer_blocks.44.attn.to_out.0.weight": "diffusion_pytorch_model-00011-of-00014.safetensors",
+    "transformer_blocks.44.attn.to_q.weight": "diffusion_pytorch_model-00011-of-00014.safetensors",
+    "transformer_blocks.44.attn.to_v.weight": "diffusion_pytorch_model-00011-of-00014.safetensors",
+    "transformer_blocks.44.ff.net.0.proj.weight_packed": "diffusion_pytorch_model-00011-of-00014.safetensors",
+    "transformer_blocks.44.ff.net.0.proj.weight_scale": "diffusion_pytorch_model-00011-of-00014.safetensors",
+    "transformer_blocks.44.ff.net.0.proj.weight_tensor_scale": "diffusion_pytorch_model-00011-of-00014.safetensors",
+    "transformer_blocks.44.ff.net.2.weight_packed": "diffusion_pytorch_model-00011-of-00014.safetensors",
+    "transformer_blocks.44.ff.net.2.weight_scale": "diffusion_pytorch_model-00011-of-00014.safetensors",
+    "transformer_blocks.44.ff.net.2.weight_tensor_scale": "diffusion_pytorch_model-00011-of-00014.safetensors",
+    "transformer_blocks.44.norm1.weight": "diffusion_pytorch_model-00011-of-00014.safetensors",
+    "transformer_blocks.44.norm2.weight": "diffusion_pytorch_model-00011-of-00014.safetensors",
+    "transformer_blocks.45.adaln_proj.linear.bias": "diffusion_pytorch_model-00011-of-00014.safetensors",
+    "transformer_blocks.45.adaln_proj.linear.weight": "diffusion_pytorch_model-00011-of-00014.safetensors",
+    "transformer_blocks.45.attn.norm_k.weight": "diffusion_pytorch_model-00011-of-00014.safetensors",
+    "transformer_blocks.45.attn.norm_q.weight": "diffusion_pytorch_model-00011-of-00014.safetensors",
+    "transformer_blocks.45.attn.to_gate_compress.weight": "diffusion_pytorch_model-00011-of-00014.safetensors",
+    "transformer_blocks.45.attn.to_k.weight": "diffusion_pytorch_model-00011-of-00014.safetensors",
+    "transformer_blocks.45.attn.to_out.0.weight": "diffusion_pytorch_model-00011-of-00014.safetensors",
+    "transformer_blocks.45.attn.to_q.weight": "diffusion_pytorch_model-00011-of-00014.safetensors",
+    "transformer_blocks.45.attn.to_v.weight": "diffusion_pytorch_model-00011-of-00014.safetensors",
+    "transformer_blocks.45.ff.net.0.proj.weight_packed": "diffusion_pytorch_model-00012-of-00014.safetensors",
+    "transformer_blocks.45.ff.net.0.proj.weight_scale": "diffusion_pytorch_model-00012-of-00014.safetensors",
+    "transformer_blocks.45.ff.net.0.proj.weight_tensor_scale": "diffusion_pytorch_model-00012-of-00014.safetensors",
+    "transformer_blocks.45.ff.net.2.weight_packed": "diffusion_pytorch_model-00012-of-00014.safetensors",
+    "transformer_blocks.45.ff.net.2.weight_scale": "diffusion_pytorch_model-00012-of-00014.safetensors",
+    "transformer_blocks.45.ff.net.2.weight_tensor_scale": "diffusion_pytorch_model-00012-of-00014.safetensors",
+    "transformer_blocks.45.norm1.weight": "diffusion_pytorch_model-00012-of-00014.safetensors",
+    "transformer_blocks.45.norm2.weight": "diffusion_pytorch_model-00012-of-00014.safetensors",
+    "transformer_blocks.46.adaln_proj.linear.bias": "diffusion_pytorch_model-00012-of-00014.safetensors",
+    "transformer_blocks.46.adaln_proj.linear.weight": "diffusion_pytorch_model-00012-of-00014.safetensors",
+    "transformer_blocks.46.attn.norm_k.weight": "diffusion_pytorch_model-00012-of-00014.safetensors",
+    "transformer_blocks.46.attn.norm_q.weight": "diffusion_pytorch_model-00012-of-00014.safetensors",
+    "transformer_blocks.46.attn.to_gate_compress.weight": "diffusion_pytorch_model-00012-of-00014.safetensors",
+    "transformer_blocks.46.attn.to_k.weight": "diffusion_pytorch_model-00012-of-00014.safetensors",
+    "transformer_blocks.46.attn.to_out.0.weight": "diffusion_pytorch_model-00012-of-00014.safetensors",
+    "transformer_blocks.46.attn.to_q.weight": "diffusion_pytorch_model-00012-of-00014.safetensors",
+    "transformer_blocks.46.attn.to_v.weight": "diffusion_pytorch_model-00012-of-00014.safetensors",
+    "transformer_blocks.46.ff.net.0.proj.weight_packed": "diffusion_pytorch_model-00012-of-00014.safetensors",
+    "transformer_blocks.46.ff.net.0.proj.weight_scale": "diffusion_pytorch_model-00012-of-00014.safetensors",
+    "transformer_blocks.46.ff.net.0.proj.weight_tensor_scale": "diffusion_pytorch_model-00012-of-00014.safetensors",
+    "transformer_blocks.46.ff.net.2.weight_packed": "diffusion_pytorch_model-00012-of-00014.safetensors",
+    "transformer_blocks.46.ff.net.2.weight_scale": "diffusion_pytorch_model-00012-of-00014.safetensors",
+    "transformer_blocks.46.ff.net.2.weight_tensor_scale": "diffusion_pytorch_model-00012-of-00014.safetensors",
+    "transformer_blocks.46.norm1.weight": "diffusion_pytorch_model-00012-of-00014.safetensors",
+    "transformer_blocks.46.norm2.weight": "diffusion_pytorch_model-00012-of-00014.safetensors",
+    "transformer_blocks.47.adaln_proj.linear.bias": "diffusion_pytorch_model-00012-of-00014.safetensors",
+    "transformer_blocks.47.adaln_proj.linear.weight": "diffusion_pytorch_model-00012-of-00014.safetensors",
+    "transformer_blocks.47.attn.norm_k.weight": "diffusion_pytorch_model-00012-of-00014.safetensors",
+    "transformer_blocks.47.attn.norm_q.weight": "diffusion_pytorch_model-00012-of-00014.safetensors",
+    "transformer_blocks.47.attn.to_gate_compress.weight": "diffusion_pytorch_model-00012-of-00014.safetensors",
+    "transformer_blocks.47.attn.to_k.weight": "diffusion_pytorch_model-00012-of-00014.safetensors",
+    "transformer_blocks.47.attn.to_out.0.weight": "diffusion_pytorch_model-00012-of-00014.safetensors",
+    "transformer_blocks.47.attn.to_q.weight": "diffusion_pytorch_model-00012-of-00014.safetensors",
+    "transformer_blocks.47.attn.to_v.weight": "diffusion_pytorch_model-00012-of-00014.safetensors",
+    "transformer_blocks.47.ff.net.0.proj.weight_packed": "diffusion_pytorch_model-00012-of-00014.safetensors",
+    "transformer_blocks.47.ff.net.0.proj.weight_scale": "diffusion_pytorch_model-00012-of-00014.safetensors",
+    "transformer_blocks.47.ff.net.0.proj.weight_tensor_scale": "diffusion_pytorch_model-00012-of-00014.safetensors",
+    "transformer_blocks.47.ff.net.2.weight_packed": "diffusion_pytorch_model-00012-of-00014.safetensors",
+    "transformer_blocks.47.ff.net.2.weight_scale": "diffusion_pytorch_model-00012-of-00014.safetensors",
+    "transformer_blocks.47.ff.net.2.weight_tensor_scale": "diffusion_pytorch_model-00012-of-00014.safetensors",
+    "transformer_blocks.47.norm1.weight": "diffusion_pytorch_model-00012-of-00014.safetensors",
+    "transformer_blocks.47.norm2.weight": "diffusion_pytorch_model-00012-of-00014.safetensors",
+    "transformer_blocks.48.adaln_proj.linear.bias": "diffusion_pytorch_model-00012-of-00014.safetensors",
+    "transformer_blocks.48.adaln_proj.linear.weight": "diffusion_pytorch_model-00012-of-00014.safetensors",
+    "transformer_blocks.48.attn.norm_k.weight": "diffusion_pytorch_model-00012-of-00014.safetensors",
+    "transformer_blocks.48.attn.norm_q.weight": "diffusion_pytorch_model-00012-of-00014.safetensors",
+    "transformer_blocks.48.attn.to_gate_compress.weight": "diffusion_pytorch_model-00012-of-00014.safetensors",
+    "transformer_blocks.48.attn.to_k.weight": "diffusion_pytorch_model-00012-of-00014.safetensors",
+    "transformer_blocks.48.attn.to_out.0.weight": "diffusion_pytorch_model-00012-of-00014.safetensors",
+    "transformer_blocks.48.attn.to_q.weight": "diffusion_pytorch_model-00012-of-00014.safetensors",
+    "transformer_blocks.48.attn.to_v.weight": "diffusion_pytorch_model-00012-of-00014.safetensors",
+    "transformer_blocks.48.ff.net.0.proj.weight_packed": "diffusion_pytorch_model-00012-of-00014.safetensors",
+    "transformer_blocks.48.ff.net.0.proj.weight_scale": "diffusion_pytorch_model-00012-of-00014.safetensors",
+    "transformer_blocks.48.ff.net.0.proj.weight_tensor_scale": "diffusion_pytorch_model-00012-of-00014.safetensors",
+    "transformer_blocks.48.ff.net.2.weight_packed": "diffusion_pytorch_model-00012-of-00014.safetensors",
+    "transformer_blocks.48.ff.net.2.weight_scale": "diffusion_pytorch_model-00012-of-00014.safetensors",
+    "transformer_blocks.48.ff.net.2.weight_tensor_scale": "diffusion_pytorch_model-00012-of-00014.safetensors",
+    "transformer_blocks.48.norm1.weight": "diffusion_pytorch_model-00012-of-00014.safetensors",
+    "transformer_blocks.48.norm2.weight": "diffusion_pytorch_model-00012-of-00014.safetensors",
+    "transformer_blocks.49.adaln_proj.linear.bias": "diffusion_pytorch_model-00012-of-00014.safetensors",
+    "transformer_blocks.49.adaln_proj.linear.weight": "diffusion_pytorch_model-00012-of-00014.safetensors",
+    "transformer_blocks.49.attn.norm_k.weight": "diffusion_pytorch_model-00012-of-00014.safetensors",
+    "transformer_blocks.49.attn.norm_q.weight": "diffusion_pytorch_model-00012-of-00014.safetensors",
+    "transformer_blocks.49.attn.to_gate_compress.weight": "diffusion_pytorch_model-00012-of-00014.safetensors",
+    "transformer_blocks.49.attn.to_k.weight": "diffusion_pytorch_model-00012-of-00014.safetensors",
+    "transformer_blocks.49.attn.to_out.0.weight": "diffusion_pytorch_model-00012-of-00014.safetensors",
+    "transformer_blocks.49.attn.to_q.weight": "diffusion_pytorch_model-00013-of-00014.safetensors",
+    "transformer_blocks.49.attn.to_v.weight": "diffusion_pytorch_model-00013-of-00014.safetensors",
+    "transformer_blocks.49.ff.net.0.proj.weight_packed": "diffusion_pytorch_model-00013-of-00014.safetensors",
+    "transformer_blocks.49.ff.net.0.proj.weight_scale": "diffusion_pytorch_model-00013-of-00014.safetensors",
+    "transformer_blocks.49.ff.net.0.proj.weight_tensor_scale": "diffusion_pytorch_model-00013-of-00014.safetensors",
+    "transformer_blocks.49.ff.net.2.weight_packed": "diffusion_pytorch_model-00013-of-00014.safetensors",
+    "transformer_blocks.49.ff.net.2.weight_scale": "diffusion_pytorch_model-00013-of-00014.safetensors",
+    "transformer_blocks.49.ff.net.2.weight_tensor_scale": "diffusion_pytorch_model-00013-of-00014.safetensors",
+    "transformer_blocks.49.norm1.weight": "diffusion_pytorch_model-00013-of-00014.safetensors",
+    "transformer_blocks.49.norm2.weight": "diffusion_pytorch_model-00013-of-00014.safetensors",
+    "transformer_blocks.5.adaln_proj.linear.bias": "diffusion_pytorch_model-00013-of-00014.safetensors",
+    "transformer_blocks.5.adaln_proj.linear.weight": "diffusion_pytorch_model-00013-of-00014.safetensors",
+    "transformer_blocks.5.attn.norm_k.weight": "diffusion_pytorch_model-00013-of-00014.safetensors",
+    "transformer_blocks.5.attn.norm_q.weight": "diffusion_pytorch_model-00013-of-00014.safetensors",
+    "transformer_blocks.5.attn.to_gate_compress.weight": "diffusion_pytorch_model-00013-of-00014.safetensors",
+    "transformer_blocks.5.attn.to_k.weight": "diffusion_pytorch_model-00013-of-00014.safetensors",
+    "transformer_blocks.5.attn.to_out.0.weight": "diffusion_pytorch_model-00013-of-00014.safetensors",
+    "transformer_blocks.5.attn.to_q.weight": "diffusion_pytorch_model-00013-of-00014.safetensors",
+    "transformer_blocks.5.attn.to_v.weight": "diffusion_pytorch_model-00013-of-00014.safetensors",
+    "transformer_blocks.5.ff.net.0.proj.weight_packed": "diffusion_pytorch_model-00013-of-00014.safetensors",
+    "transformer_blocks.5.ff.net.0.proj.weight_scale": "diffusion_pytorch_model-00013-of-00014.safetensors",
+    "transformer_blocks.5.ff.net.0.proj.weight_tensor_scale": "diffusion_pytorch_model-00013-of-00014.safetensors",
+    "transformer_blocks.5.ff.net.2.weight_packed": "diffusion_pytorch_model-00013-of-00014.safetensors",
+    "transformer_blocks.5.ff.net.2.weight_scale": "diffusion_pytorch_model-00013-of-00014.safetensors",
+    "transformer_blocks.5.ff.net.2.weight_tensor_scale": "diffusion_pytorch_model-00013-of-00014.safetensors",
+    "transformer_blocks.5.norm1.weight": "diffusion_pytorch_model-00013-of-00014.safetensors",
+    "transformer_blocks.5.norm2.weight": "diffusion_pytorch_model-00013-of-00014.safetensors",
+    "transformer_blocks.6.adaln_proj.linear.bias": "diffusion_pytorch_model-00013-of-00014.safetensors",
+    "transformer_blocks.6.adaln_proj.linear.weight": "diffusion_pytorch_model-00013-of-00014.safetensors",
+    "transformer_blocks.6.attn.norm_k.weight": "diffusion_pytorch_model-00013-of-00014.safetensors",
+    "transformer_blocks.6.attn.norm_q.weight": "diffusion_pytorch_model-00013-of-00014.safetensors",
+    "transformer_blocks.6.attn.to_gate_compress.weight": "diffusion_pytorch_model-00013-of-00014.safetensors",
+    "transformer_blocks.6.attn.to_k.weight": "diffusion_pytorch_model-00013-of-00014.safetensors",
+    "transformer_blocks.6.attn.to_out.0.weight": "diffusion_pytorch_model-00013-of-00014.safetensors",
+    "transformer_blocks.6.attn.to_q.weight": "diffusion_pytorch_model-00013-of-00014.safetensors",
+    "transformer_blocks.6.attn.to_v.weight": "diffusion_pytorch_model-00013-of-00014.safetensors",
+    "transformer_blocks.6.ff.net.0.proj.weight_packed": "diffusion_pytorch_model-00013-of-00014.safetensors",
+    "transformer_blocks.6.ff.net.0.proj.weight_scale": "diffusion_pytorch_model-00013-of-00014.safetensors",
+    "transformer_blocks.6.ff.net.0.proj.weight_tensor_scale": "diffusion_pytorch_model-00013-of-00014.safetensors",
+    "transformer_blocks.6.ff.net.2.weight_packed": "diffusion_pytorch_model-00013-of-00014.safetensors",
+    "transformer_blocks.6.ff.net.2.weight_scale": "diffusion_pytorch_model-00013-of-00014.safetensors",
+    "transformer_blocks.6.ff.net.2.weight_tensor_scale": "diffusion_pytorch_model-00013-of-00014.safetensors",
+    "transformer_blocks.6.norm1.weight": "diffusion_pytorch_model-00013-of-00014.safetensors",
+    "transformer_blocks.6.norm2.weight": "diffusion_pytorch_model-00013-of-00014.safetensors",
+    "transformer_blocks.7.adaln_proj.linear.bias": "diffusion_pytorch_model-00013-of-00014.safetensors",
+    "transformer_blocks.7.adaln_proj.linear.weight": "diffusion_pytorch_model-00013-of-00014.safetensors",
+    "transformer_blocks.7.attn.norm_k.weight": "diffusion_pytorch_model-00013-of-00014.safetensors",
+    "transformer_blocks.7.attn.norm_q.weight": "diffusion_pytorch_model-00013-of-00014.safetensors",
+    "transformer_blocks.7.attn.to_gate_compress.weight": "diffusion_pytorch_model-00013-of-00014.safetensors",
+    "transformer_blocks.7.attn.to_k.weight": "diffusion_pytorch_model-00013-of-00014.safetensors",
+    "transformer_blocks.7.attn.to_out.0.weight": "diffusion_pytorch_model-00013-of-00014.safetensors",
+    "transformer_blocks.7.attn.to_q.weight": "diffusion_pytorch_model-00013-of-00014.safetensors",
+    "transformer_blocks.7.attn.to_v.weight": "diffusion_pytorch_model-00013-of-00014.safetensors",
+    "transformer_blocks.7.ff.net.0.proj.weight_packed": "diffusion_pytorch_model-00013-of-00014.safetensors",
+    "transformer_blocks.7.ff.net.0.proj.weight_scale": "diffusion_pytorch_model-00013-of-00014.safetensors",
+    "transformer_blocks.7.ff.net.0.proj.weight_tensor_scale": "diffusion_pytorch_model-00013-of-00014.safetensors",
+    "transformer_blocks.7.ff.net.2.weight_packed": "diffusion_pytorch_model-00013-of-00014.safetensors",
+    "transformer_blocks.7.ff.net.2.weight_scale": "diffusion_pytorch_model-00013-of-00014.safetensors",
+    "transformer_blocks.7.ff.net.2.weight_tensor_scale": "diffusion_pytorch_model-00013-of-00014.safetensors",
+    "transformer_blocks.7.norm1.weight": "diffusion_pytorch_model-00013-of-00014.safetensors",
+    "transformer_blocks.7.norm2.weight": "diffusion_pytorch_model-00013-of-00014.safetensors",
+    "transformer_blocks.8.adaln_proj.linear.bias": "diffusion_pytorch_model-00013-of-00014.safetensors",
+    "transformer_blocks.8.adaln_proj.linear.weight": "diffusion_pytorch_model-00013-of-00014.safetensors",
+    "transformer_blocks.8.attn.norm_k.weight": "diffusion_pytorch_model-00013-of-00014.safetensors",
+    "transformer_blocks.8.attn.norm_q.weight": "diffusion_pytorch_model-00013-of-00014.safetensors",
+    "transformer_blocks.8.attn.to_gate_compress.weight": "diffusion_pytorch_model-00013-of-00014.safetensors",
+    "transformer_blocks.8.attn.to_k.weight": "diffusion_pytorch_model-00014-of-00014.safetensors",
+    "transformer_blocks.8.attn.to_out.0.weight": "diffusion_pytorch_model-00014-of-00014.safetensors",
+    "transformer_blocks.8.attn.to_q.weight": "diffusion_pytorch_model-00014-of-00014.safetensors",
+    "transformer_blocks.8.attn.to_v.weight": "diffusion_pytorch_model-00014-of-00014.safetensors",
+    "transformer_blocks.8.ff.net.0.proj.weight_packed": "diffusion_pytorch_model-00014-of-00014.safetensors",
+    "transformer_blocks.8.ff.net.0.proj.weight_scale": "diffusion_pytorch_model-00014-of-00014.safetensors",
+    "transformer_blocks.8.ff.net.0.proj.weight_tensor_scale": "diffusion_pytorch_model-00014-of-00014.safetensors",
+    "transformer_blocks.8.ff.net.2.weight_packed": "diffusion_pytorch_model-00014-of-00014.safetensors",
+    "transformer_blocks.8.ff.net.2.weight_scale": "diffusion_pytorch_model-00014-of-00014.safetensors",
+    "transformer_blocks.8.ff.net.2.weight_tensor_scale": "diffusion_pytorch_model-00014-of-00014.safetensors",
+    "transformer_blocks.8.norm1.weight": "diffusion_pytorch_model-00014-of-00014.safetensors",
+    "transformer_blocks.8.norm2.weight": "diffusion_pytorch_model-00014-of-00014.safetensors",
+    "transformer_blocks.9.adaln_proj.linear.bias": "diffusion_pytorch_model-00014-of-00014.safetensors",
+    "transformer_blocks.9.adaln_proj.linear.weight": "diffusion_pytorch_model-00014-of-00014.safetensors",
+    "transformer_blocks.9.attn.norm_k.weight": "diffusion_pytorch_model-00014-of-00014.safetensors",
+    "transformer_blocks.9.attn.norm_q.weight": "diffusion_pytorch_model-00014-of-00014.safetensors",
+    "transformer_blocks.9.attn.to_gate_compress.weight": "diffusion_pytorch_model-00014-of-00014.safetensors",
+    "transformer_blocks.9.attn.to_k.weight": "diffusion_pytorch_model-00014-of-00014.safetensors",
+    "transformer_blocks.9.attn.to_out.0.weight": "diffusion_pytorch_model-00014-of-00014.safetensors",
+    "transformer_blocks.9.attn.to_q.weight": "diffusion_pytorch_model-00014-of-00014.safetensors",
+    "transformer_blocks.9.attn.to_v.weight": "diffusion_pytorch_model-00014-of-00014.safetensors",
+    "transformer_blocks.9.ff.net.0.proj.weight_packed": "diffusion_pytorch_model-00014-of-00014.safetensors",
+    "transformer_blocks.9.ff.net.0.proj.weight_scale": "diffusion_pytorch_model-00014-of-00014.safetensors",
+    "transformer_blocks.9.ff.net.0.proj.weight_tensor_scale": "diffusion_pytorch_model-00014-of-00014.safetensors",
+    "transformer_blocks.9.ff.net.2.weight_packed": "diffusion_pytorch_model-00014-of-00014.safetensors",
+    "transformer_blocks.9.ff.net.2.weight_scale": "diffusion_pytorch_model-00014-of-00014.safetensors",
+    "transformer_blocks.9.ff.net.2.weight_tensor_scale": "diffusion_pytorch_model-00014-of-00014.safetensors",
+    "transformer_blocks.9.norm1.weight": "diffusion_pytorch_model-00014-of-00014.safetensors",
+    "transformer_blocks.9.norm2.weight": "diffusion_pytorch_model-00014-of-00014.safetensors"
+  }
+}

transformer/modelopt-component-manifest.json

@@ -0,0 +1,1483 @@
+{
+  "component": "denoiser",
+  "files": {
+    "config.json": {
+      "bytes": 546,
+      "sha256": "74c11bff524336576096993cbfcdcdc2ef4fa2fa4409df693bdcbc6c666282ae"
+    },
+    "diffusion_pytorch_model-00001-of-00014.safetensors": {
+      "bytes": 4666277856,
+      "sha256": "f3a79f3595b95742c9c6e5a3724e77a0fe0aaca4ae537ebfcade89308c166665"
+    },
+    "diffusion_pytorch_model-00002-of-00014.safetensors": {
+      "bytes": 3989259848,
+      "sha256": "fdb4db67af50e554d63f6107eb25dffe05436b93d010fe7c73365a0daef7a495"
+    },
+    "diffusion_pytorch_model-00003-of-00014.safetensors": {
+      "bytes": 3989259864,
+      "sha256": "56589eb613578fc3b7630eccfe7f2c2096b063369aa7d4ed0328f0d378567a06"
+    },
+    "diffusion_pytorch_model-00004-of-00014.safetensors": {
+      "bytes": 3546104664,
+      "sha256": "f038d4150846450ac163758d0635118c6c36bb2f3c79bf488b0494a76ad74ddb"
+    },
+    "diffusion_pytorch_model-00005-of-00014.safetensors": {
+      "bytes": 4099832988,
+      "sha256": "4fe3e9e0a089af378667cc44b2fa19441db52eedd6a793d581cfc3f819ad520d"
+    },
+    "diffusion_pytorch_model-00006-of-00014.safetensors": {
+      "bytes": 4056696260,
+      "sha256": "7db50a3eb46b0de753c004bbaa1721a7b435029b5e2c1b9e3c0b17a87e733162"
+    },
+    "diffusion_pytorch_model-00007-of-00014.safetensors": {
+      "bytes": 3989259832,
+      "sha256": "14d416a288d5254035e76e42d5eb3b8cf56602bbcc595beb0c157124bb8e7044"
+    },
+    "diffusion_pytorch_model-00008-of-00014.safetensors": {
+      "bytes": 3989259864,
+      "sha256": "4f8e479a96a692f1a04bdb4bd26c3ad2369c0bd076052067b8d613e0adcf7877"
+    },
+    "diffusion_pytorch_model-00009-of-00014.safetensors": {
+      "bytes": 3546104680,
+      "sha256": "7daad24c9223ddfc42877366db947c8169f7f85d8f05dc415452a31e80c38c03"
+    },
+    "diffusion_pytorch_model-00010-of-00014.safetensors": {
+      "bytes": 4099832972,
+      "sha256": "b22e6dec4f82b45cffc9d9b6e4120b3a079e77091e15372a887b2100c9eeb106"
+    },
+    "diffusion_pytorch_model-00011-of-00014.safetensors": {
+      "bytes": 4056696260,
+      "sha256": "98cae8b90b04fe4bcba477743bc22962548d48121f6af3162f8f305f1a6bdb3f"
+    },
+    "diffusion_pytorch_model-00012-of-00014.safetensors": {
+      "bytes": 3989259848,
+      "sha256": "a18ffec34c86f2ecb912c331b4abed52954a5d2457e3c41e9fb2047889449c2b"
+    },
+    "diffusion_pytorch_model-00013-of-00014.safetensors": {
+      "bytes": 3989259808,
+      "sha256": "bb17854e105c6ec6c2bbed886f2d0b83eb6ab85141d075cfe42ae87b84140d2c"
+    },
+    "diffusion_pytorch_model-00014-of-00014.safetensors": {
+      "bytes": 1474210592,
+      "sha256": "76381efde9e6fc799a43bc8026dad9fbc8d69c1bb530a6f6783c7645967aee8e"
+    },
+    "diffusion_pytorch_model.safetensors.index.json": {
+      "bytes": 92939,
+      "sha256": "af2cfa36eeae8bc371c908b658526d9599a548663e6a87eb3495a1f32377aa98"
+    }
+  },
+  "modelopt_commit": "6a4b3f147e14a6fec690fedbced8df402344085d",
+  "numerical_format": {
+    "activation": "a4",
+    "block_scale": "fp8_e4m3",
+    "block_size": 16,
+    "output": "bf16",
+    "tensor_scale": "fp32",
+    "values": "e2m1",
+    "weight": "w4"
+  },
+  "source": "/workspace/models/FastVideo-FastH3-8-Step-V2/transformer",
+  "target_weights": 100,
+  "weights": {
+    "transformer_blocks.0.ff.net.0.proj.weight": {
+      "block_scale_max": 448.0,
+      "block_scale_mean": 16.472810745239258,
+      "block_scale_min": 0.375,
+      "calibration": "static_mse_fp8_e4m3_scale_sweep_126_candidates",
+      "shape": [
+        28672,
+        5376
+      ],
+      "source_dtype": "bfloat16",
+      "weight_global_amax": 8.375,
+      "weight_saturation_rate": 0.0635531023144722,
+      "weight_tensor_scale": 0.0031156993936747313
+    },
+    "transformer_blocks.0.ff.net.2.weight": {
+      "block_scale_max": 448.0,
+      "block_scale_mean": 33.92570114135742,
+      "block_scale_min": 5.0,
+      "calibration": "static_mse_fp8_e4m3_scale_sweep_126_candidates",
+      "shape": [
+        5376,
+        14336
+      ],
+      "source_dtype": "bfloat16",
+      "weight_global_amax": 4.8125,
+      "weight_saturation_rate": 0.06495505571365356,
+      "weight_tensor_scale": 0.0017903646221384406
+    },
+    "transformer_blocks.1.ff.net.0.proj.weight": {
+      "block_scale_max": 448.0,
+      "block_scale_mean": 28.016780853271484,
+      "block_scale_min": 0.6875,
+      "calibration": "static_mse_fp8_e4m3_scale_sweep_126_candidates",
+      "shape": [
+        28672,
+        5376
+      ],
+      "source_dtype": "bfloat16",
+      "weight_global_amax": 4.40625,
+      "weight_saturation_rate": 0.06361329555511475,
+      "weight_tensor_scale": 0.0016392299439758062
+    },
+    "transformer_blocks.1.ff.net.2.weight": {
+      "block_scale_max": 448.0,
+      "block_scale_mean": 17.47043800354004,
+      "block_scale_min": 2.25,
+      "calibration": "static_mse_fp8_e4m3_scale_sweep_126_candidates",
+      "shape": [
+        5376,
+        14336
+      ],
+      "source_dtype": "bfloat16",
+      "weight_global_amax": 8.4375,
+      "weight_saturation_rate": 0.06422059237957001,
+      "weight_tensor_scale": 0.003138951025903225
+    },
+    "transformer_blocks.10.ff.net.0.proj.weight": {
+      "block_scale_max": 448.0,
+      "block_scale_mean": 44.30693054199219,
+      "block_scale_min": 1.375,
+      "calibration": "static_mse_fp8_e4m3_scale_sweep_126_candidates",
+      "shape": [
+        28672,
+        5376
+      ],
+      "source_dtype": "bfloat16",
+      "weight_global_amax": 3.609375,
+      "weight_saturation_rate": 0.0634210854768753,
+      "weight_tensor_scale": 0.0013427734375
+    },
+    "transformer_blocks.10.ff.net.2.weight": {
+      "block_scale_max": 448.0,
+      "block_scale_mean": 70.12564849853516,
+      "block_scale_min": 8.0,
+      "calibration": "static_mse_fp8_e4m3_scale_sweep_126_candidates",
+      "shape": [
+        5376,
+        14336
+      ],
+      "source_dtype": "bfloat16",
+      "weight_global_amax": 2.40625,
+      "weight_saturation_rate": 0.06392490118741989,
+      "weight_tensor_scale": 0.0008951823110692203
+    },
+    "transformer_blocks.11.ff.net.0.proj.weight": {
+      "block_scale_max": 448.0,
+      "block_scale_mean": 26.48586654663086,
+      "block_scale_min": 0.75,
+      "calibration": "static_mse_fp8_e4m3_scale_sweep_126_candidates",
+      "shape": [
+        28672,
+        5376
+      ],
+      "source_dtype": "bfloat16",
+      "weight_global_amax": 5.9375,
+      "weight_saturation_rate": 0.06343300640583038,
+      "weight_tensor_scale": 0.002208891324698925
+    },
+    "transformer_blocks.11.ff.net.2.weight": {
+      "block_scale_max": 448.0,
+      "block_scale_mean": 36.13872146606445,
+      "block_scale_min": 3.0,
+      "calibration": "static_mse_fp8_e4m3_scale_sweep_126_candidates",
+      "shape": [
+        5376,
+        14336
+      ],
+      "source_dtype": "bfloat16",
+      "weight_global_amax": 4.5625,
+      "weight_saturation_rate": 0.06391296535730362,
+      "weight_tensor_scale": 0.001697358675301075
+    },
+    "transformer_blocks.12.ff.net.0.proj.weight": {
+      "block_scale_max": 448.0,
+      "block_scale_mean": 38.98491287231445,
+      "block_scale_min": 1.125,
+      "calibration": "static_mse_fp8_e4m3_scale_sweep_126_candidates",
+      "shape": [
+        28672,
+        5376
+      ],
+      "source_dtype": "bfloat16",
+      "weight_global_amax": 3.953125,
+      "weight_saturation_rate": 0.06354884803295135,
+      "weight_tensor_scale": 0.0014706565998494625
+    },
+    "transformer_blocks.12.ff.net.2.weight": {
+      "block_scale_max": 448.0,
+      "block_scale_mean": 41.33897399902344,
+      "block_scale_min": 3.25,
+      "calibration": "static_mse_fp8_e4m3_scale_sweep_126_candidates",
+      "shape": [
+        5376,
+        14336
+      ],
+      "source_dtype": "bfloat16",
+      "weight_global_amax": 3.921875,
+      "weight_saturation_rate": 0.06375382840633392,
+      "weight_tensor_scale": 0.0014590309001505375
+    },
+    "transformer_blocks.13.ff.net.0.proj.weight": {
+      "block_scale_max": 448.0,
+      "block_scale_mean": 12.657387733459473,
+      "block_scale_min": 0.375,
+      "calibration": "static_mse_fp8_e4m3_scale_sweep_126_candidates",
+      "shape": [
+        28672,
+        5376
+      ],
+      "source_dtype": "bfloat16",
+      "weight_global_amax": 12.125,
+      "weight_saturation_rate": 0.06352940201759338,
+      "weight_tensor_scale": 0.0045107887126505375
+    },
+    "transformer_blocks.13.ff.net.2.weight": {
+      "block_scale_max": 448.0,
+      "block_scale_mean": 10.395673751831055,
+      "block_scale_min": 0.625,
+      "calibration": "static_mse_fp8_e4m3_scale_sweep_126_candidates",
+      "shape": [
+        5376,
+        14336
+      ],
+      "source_dtype": "bfloat16",
+      "weight_global_amax": 15.375,
+      "weight_saturation_rate": 0.06361401826143265,
+      "weight_tensor_scale": 0.0057198661379516125
+    },
+    "transformer_blocks.14.ff.net.0.proj.weight": {
+      "block_scale_max": 448.0,
+      "block_scale_mean": 32.54780578613281,
+      "block_scale_min": 0.9375,
+      "calibration": "static_mse_fp8_e4m3_scale_sweep_126_candidates",
+      "shape": [
+        28672,
+        5376
+      ],
+      "source_dtype": "bfloat16",
+      "weight_global_amax": 4.75,
+      "weight_saturation_rate": 0.06362705677747726,
+      "weight_tensor_scale": 0.0017671131063252687
+    },
+    "transformer_blocks.14.ff.net.2.weight": {
+      "block_scale_max": 448.0,
+      "block_scale_mean": 40.63705062866211,
+      "block_scale_min": 2.5,
+      "calibration": "static_mse_fp8_e4m3_scale_sweep_126_candidates",
+      "shape": [
+        5376,
+        14336
+      ],
+      "source_dtype": "bfloat16",
+      "weight_global_amax": 3.921875,
+      "weight_saturation_rate": 0.06358229368925095,
+      "weight_tensor_scale": 0.0014590309001505375
+    },
+    "transformer_blocks.15.ff.net.0.proj.weight": {
+      "block_scale_max": 448.0,
+      "block_scale_mean": 26.840002059936523,
+      "block_scale_min": 0.75,
+      "calibration": "static_mse_fp8_e4m3_scale_sweep_126_candidates",
+      "shape": [
+        28672,
+        5376
+      ],
+      "source_dtype": "bfloat16",
+      "weight_global_amax": 5.71875,
+      "weight_saturation_rate": 0.06362160295248032,
+      "weight_tensor_scale": 0.0021275111939758062
+    },
+    "transformer_blocks.15.ff.net.2.weight": {
+      "block_scale_max": 448.0,
+      "block_scale_mean": 30.485427856445312,
+      "block_scale_min": 1.375,
+      "calibration": "static_mse_fp8_e4m3_scale_sweep_126_candidates",
+      "shape": [
+        5376,
+        14336
+      ],
+      "source_dtype": "bfloat16",
+      "weight_global_amax": 5.0625,
+      "weight_saturation_rate": 0.06376612931489944,
+      "weight_tensor_scale": 0.0018833705689758062
+    },
+    "transformer_blocks.16.ff.net.0.proj.weight": {
+      "block_scale_max": 448.0,
+      "block_scale_mean": 29.40296173095703,
+      "block_scale_min": 0.9375,
+      "calibration": "static_mse_fp8_e4m3_scale_sweep_126_candidates",
+      "shape": [
+        28672,
+        5376
+      ],
+      "source_dtype": "bfloat16",
+      "weight_global_amax": 5.21875,
+      "weight_saturation_rate": 0.06359194219112396,
+      "weight_tensor_scale": 0.001941499300301075
+    },
+    "transformer_blocks.16.ff.net.2.weight": {
+      "block_scale_max": 448.0,
+      "block_scale_mean": 41.52627182006836,
+      "block_scale_min": 2.5,
+      "calibration": "static_mse_fp8_e4m3_scale_sweep_126_candidates",
+      "shape": [
+        5376,
+        14336
+      ],
+      "source_dtype": "bfloat16",
+      "weight_global_amax": 3.671875,
+      "weight_saturation_rate": 0.06345530599355698,
+      "weight_tensor_scale": 0.0013660249533131719
+    },
+    "transformer_blocks.17.ff.net.0.proj.weight": {
+      "block_scale_max": 448.0,
+      "block_scale_mean": 35.89411163330078,
+      "block_scale_min": 0.9375,
+      "calibration": "static_mse_fp8_e4m3_scale_sweep_126_candidates",
+      "shape": [
+        28672,
+        5376
+      ],
+      "source_dtype": "bfloat16",
+      "weight_global_amax": 4.34375,
+      "weight_saturation_rate": 0.06361914426088333,
+      "weight_tensor_scale": 0.0016159784281626344
+    },
+    "transformer_blocks.17.ff.net.2.weight": {
+      "block_scale_max": 448.0,
+      "block_scale_mean": 34.49273681640625,
+      "block_scale_min": 1.875,
+      "calibration": "static_mse_fp8_e4m3_scale_sweep_126_candidates",
+      "shape": [
+        5376,
+        14336
+      ],
+      "source_dtype": "bfloat16",
+      "weight_global_amax": 4.46875,
+      "weight_saturation_rate": 0.0636821910738945,
+      "weight_tensor_scale": 0.001662481459788978
+    },
+    "transformer_blocks.18.ff.net.0.proj.weight": {
+      "block_scale_max": 448.0,
+      "block_scale_mean": 37.41980743408203,
+      "block_scale_min": 1.0,
+      "calibration": "static_mse_fp8_e4m3_scale_sweep_126_candidates",
+      "shape": [
+        28672,
+        5376
+      ],
+      "source_dtype": "bfloat16",
+      "weight_global_amax": 4.28125,
+      "weight_saturation_rate": 0.06366817653179169,
+      "weight_tensor_scale": 0.0015927269123494625
+    },
+    "transformer_blocks.18.ff.net.2.weight": {
+      "block_scale_max": 448.0,
+      "block_scale_mean": 17.07464027404785,
+      "block_scale_min": 1.125,
+      "calibration": "static_mse_fp8_e4m3_scale_sweep_126_candidates",
+      "shape": [
+        5376,
+        14336
+      ],
+      "source_dtype": "bfloat16",
+      "weight_global_amax": 9.3125,
+      "weight_saturation_rate": 0.0635707899928093,
+      "weight_tensor_scale": 0.0034644717816263437
+    },
+    "transformer_blocks.19.ff.net.0.proj.weight": {
+      "block_scale_max": 448.0,
+      "block_scale_mean": 53.71031951904297,
+      "block_scale_min": 1.625,
+      "calibration": "static_mse_fp8_e4m3_scale_sweep_126_candidates",
+      "shape": [
+        28672,
+        5376
+      ],
+      "source_dtype": "bfloat16",
+      "weight_global_amax": 3.03125,
+      "weight_saturation_rate": 0.06346447020769119,
+      "weight_tensor_scale": 0.0011276971781626344
+    },
+    "transformer_blocks.19.ff.net.2.weight": {
+      "block_scale_max": 448.0,
+      "block_scale_mean": 44.21475601196289,
+      "block_scale_min": 3.25,
+      "calibration": "static_mse_fp8_e4m3_scale_sweep_126_candidates",
+      "shape": [
+        5376,
+        14336
+      ],
+      "source_dtype": "bfloat16",
+      "weight_global_amax": 3.640625,
+      "weight_saturation_rate": 0.06315609812736511,
+      "weight_tensor_scale": 0.0013543992536142468
+    },
+    "transformer_blocks.2.ff.net.0.proj.weight": {
+      "block_scale_max": 448.0,
+      "block_scale_mean": 33.50969696044922,
+      "block_scale_min": 0.875,
+      "calibration": "static_mse_fp8_e4m3_scale_sweep_126_candidates",
+      "shape": [
+        28672,
+        5376
+      ],
+      "source_dtype": "bfloat16",
+      "weight_global_amax": 4.34375,
+      "weight_saturation_rate": 0.06351633369922638,
+      "weight_tensor_scale": 0.0016159784281626344
+    },
+    "transformer_blocks.2.ff.net.2.weight": {
+      "block_scale_max": 448.0,
+      "block_scale_mean": 23.832735061645508,
+      "block_scale_min": 4.0,
+      "calibration": "static_mse_fp8_e4m3_scale_sweep_126_candidates",
+      "shape": [
+        5376,
+        14336
+      ],
+      "source_dtype": "bfloat16",
+      "weight_global_amax": 7.21875,
+      "weight_saturation_rate": 0.06375302374362946,
+      "weight_tensor_scale": 0.002685546875
+    },
+    "transformer_blocks.20.ff.net.0.proj.weight": {
+      "block_scale_max": 448.0,
+      "block_scale_mean": 36.75448989868164,
+      "block_scale_min": 1.5,
+      "calibration": "static_mse_fp8_e4m3_scale_sweep_126_candidates",
+      "shape": [
+        28672,
+        5376
+      ],
+      "source_dtype": "bfloat16",
+      "weight_global_amax": 4.46875,
+      "weight_saturation_rate": 0.06357189267873764,
+      "weight_tensor_scale": 0.001662481459788978
+    },
+    "transformer_blocks.20.ff.net.2.weight": {
+      "block_scale_max": 448.0,
+      "block_scale_mean": 40.20512008666992,
+      "block_scale_min": 4.5,
+      "calibration": "static_mse_fp8_e4m3_scale_sweep_126_candidates",
+      "shape": [
+        5376,
+        14336
+      ],
+      "source_dtype": "bfloat16",
+      "weight_global_amax": 4.03125,
+      "weight_saturation_rate": 0.06329139322042465,
+      "weight_tensor_scale": 0.0014997209655120969
+    },
+    "transformer_blocks.21.ff.net.0.proj.weight": {
+      "block_scale_max": 448.0,
+      "block_scale_mean": 28.327739715576172,
+      "block_scale_min": 0.875,
+      "calibration": "static_mse_fp8_e4m3_scale_sweep_126_candidates",
+      "shape": [
+        28672,
+        5376
+      ],
+      "source_dtype": "bfloat16",
+      "weight_global_amax": 5.90625,
+      "weight_saturation_rate": 0.0633908212184906,
+      "weight_tensor_scale": 0.002197265625
+    },
+    "transformer_blocks.21.ff.net.2.weight": {
+      "block_scale_max": 448.0,
+      "block_scale_mean": 34.72657012939453,
+      "block_scale_min": 3.5,
+      "calibration": "static_mse_fp8_e4m3_scale_sweep_126_candidates",
+      "shape": [
+        5376,
+        14336
+      ],
+      "source_dtype": "bfloat16",
+      "weight_global_amax": 4.6875,
+      "weight_saturation_rate": 0.06354440748691559,
+      "weight_tensor_scale": 0.0017438615905120969
+    },
+    "transformer_blocks.22.ff.net.0.proj.weight": {
+      "block_scale_max": 448.0,
+      "block_scale_mean": 46.91795349121094,
+      "block_scale_min": 1.375,
+      "calibration": "static_mse_fp8_e4m3_scale_sweep_126_candidates",
+      "shape": [
+        28672,
+        5376
+      ],
+      "source_dtype": "bfloat16",
+      "weight_global_amax": 3.640625,
+      "weight_saturation_rate": 0.06337294727563858,
+      "weight_tensor_scale": 0.0013543992536142468
+    },
+    "transformer_blocks.22.ff.net.2.weight": {
+      "block_scale_max": 448.0,
+      "block_scale_mean": 54.79737091064453,
+      "block_scale_min": 5.5,
+      "calibration": "static_mse_fp8_e4m3_scale_sweep_126_candidates",
+      "shape": [
+        5376,
+        14336
+      ],
+      "source_dtype": "bfloat16",
+      "weight_global_amax": 3.015625,
+      "weight_saturation_rate": 0.06334823369979858,
+      "weight_tensor_scale": 0.0011218843283131719
+    },
+    "transformer_blocks.23.ff.net.0.proj.weight": {
+      "block_scale_max": 448.0,
+      "block_scale_mean": 32.75905227661133,
+      "block_scale_min": 2.25,
+      "calibration": "static_mse_fp8_e4m3_scale_sweep_126_candidates",
+      "shape": [
+        28672,
+        5376
+      ],
+      "source_dtype": "bfloat16",
+      "weight_global_amax": 5.3125,
+      "weight_saturation_rate": 0.06352945417165756,
+      "weight_tensor_scale": 0.0019763766322284937
+    },
+    "transformer_blocks.23.ff.net.2.weight": {
+      "block_scale_max": 448.0,
+      "block_scale_mean": 61.83649444580078,
+      "block_scale_min": 7.0,
+      "calibration": "static_mse_fp8_e4m3_scale_sweep_126_candidates",
+      "shape": [
+        5376,
+        14336
+      ],
+      "source_dtype": "bfloat16",
+      "weight_global_amax": 2.71875,
+      "weight_saturation_rate": 0.06354671716690063,
+      "weight_tensor_scale": 0.0010114397155120969
+    },
+    "transformer_blocks.24.ff.net.0.proj.weight": {
+      "block_scale_max": 448.0,
+      "block_scale_mean": 27.764474868774414,
+      "block_scale_min": 2.5,
+      "calibration": "static_mse_fp8_e4m3_scale_sweep_126_candidates",
+      "shape": [
+        28672,
+        5376
+      ],
+      "source_dtype": "bfloat16",
+      "weight_global_amax": 6.375,
+      "weight_saturation_rate": 0.0633118748664856,
+      "weight_tensor_scale": 0.0023716518189758062
+    },
+    "transformer_blocks.24.ff.net.2.weight": {
+      "block_scale_max": 448.0,
+      "block_scale_mean": 55.93125534057617,
+      "block_scale_min": 5.5,
+      "calibration": "static_mse_fp8_e4m3_scale_sweep_126_candidates",
+      "shape": [
+        5376,
+        14336
+      ],
+      "source_dtype": "bfloat16",
+      "weight_global_amax": 3.03125,
+      "weight_saturation_rate": 0.06340514868497849,
+      "weight_tensor_scale": 0.0011276971781626344
+    },
+    "transformer_blocks.25.ff.net.0.proj.weight": {
+      "block_scale_max": 448.0,
+      "block_scale_mean": 39.748191833496094,
+      "block_scale_min": 4.5,
+      "calibration": "static_mse_fp8_e4m3_scale_sweep_126_candidates",
+      "shape": [
+        28672,
+        5376
+      ],
+      "source_dtype": "bfloat16",
+      "weight_global_amax": 4.53125,
+      "weight_saturation_rate": 0.06359779834747314,
+      "weight_tensor_scale": 0.00168573297560215
+    },
+    "transformer_blocks.25.ff.net.2.weight": {
+      "block_scale_max": 448.0,
+      "block_scale_mean": 53.71021270751953,
+      "block_scale_min": 5.0,
+      "calibration": "static_mse_fp8_e4m3_scale_sweep_126_candidates",
+      "shape": [
+        5376,
+        14336
+      ],
+      "source_dtype": "bfloat16",
+      "weight_global_amax": 3.21875,
+      "weight_saturation_rate": 0.0632067546248436,
+      "weight_tensor_scale": 0.0011974516091868281
+    },
+    "transformer_blocks.26.ff.net.0.proj.weight": {
+      "block_scale_max": 448.0,
+      "block_scale_mean": 41.97430419921875,
+      "block_scale_min": 1.125,
+      "calibration": "static_mse_fp8_e4m3_scale_sweep_126_candidates",
+      "shape": [
+        28672,
+        5376
+      ],
+      "source_dtype": "bfloat16",
+      "weight_global_amax": 4.375,
+      "weight_saturation_rate": 0.06354731321334839,
+      "weight_tensor_scale": 0.0016276042442768812
+    },
+    "transformer_blocks.26.ff.net.2.weight": {
+      "block_scale_max": 448.0,
+      "block_scale_mean": 31.096267700195312,
+      "block_scale_min": 3.75,
+      "calibration": "static_mse_fp8_e4m3_scale_sweep_126_candidates",
+      "shape": [
+        5376,
+        14336
+      ],
+      "source_dtype": "bfloat16",
+      "weight_global_amax": 5.6875,
+      "weight_saturation_rate": 0.0635245144367218,
+      "weight_tensor_scale": 0.0021158854942768812
+    },
+    "transformer_blocks.27.ff.net.0.proj.weight": {
+      "block_scale_max": 448.0,
+      "block_scale_mean": 38.585418701171875,
+      "block_scale_min": 1.75,
+      "calibration": "static_mse_fp8_e4m3_scale_sweep_126_candidates",
+      "shape": [
+        28672,
+        5376
+      ],
+      "source_dtype": "bfloat16",
+      "weight_global_amax": 4.8125,
+      "weight_saturation_rate": 0.06368626654148102,
+      "weight_tensor_scale": 0.0017903646221384406
+    },
+    "transformer_blocks.27.ff.net.2.weight": {
+      "block_scale_max": 448.0,
+      "block_scale_mean": 17.185791015625,
+      "block_scale_min": 2.25,
+      "calibration": "static_mse_fp8_e4m3_scale_sweep_126_candidates",
+      "shape": [
+        5376,
+        14336
+      ],
+      "source_dtype": "bfloat16",
+      "weight_global_amax": 10.5,
+      "weight_saturation_rate": 0.06366415321826935,
+      "weight_tensor_scale": 0.00390625
+    },
+    "transformer_blocks.28.ff.net.0.proj.weight": {
+      "block_scale_max": 448.0,
+      "block_scale_mean": 26.90459442138672,
+      "block_scale_min": 1.625,
+      "calibration": "static_mse_fp8_e4m3_scale_sweep_126_candidates",
+      "shape": [
+        28672,
+        5376
+      ],
+      "source_dtype": "bfloat16",
+      "weight_global_amax": 7.09375,
+      "weight_saturation_rate": 0.0631420835852623,
+      "weight_tensor_scale": 0.0026390438433736563
+    },
+    "transformer_blocks.28.ff.net.2.weight": {
+      "block_scale_max": 448.0,
+      "block_scale_mean": 25.527729034423828,
+      "block_scale_min": 3.5,
+      "calibration": "static_mse_fp8_e4m3_scale_sweep_126_candidates",
+      "shape": [
+        5376,
+        14336
+      ],
+      "source_dtype": "bfloat16",
+      "weight_global_amax": 7.3125,
+      "weight_saturation_rate": 0.06289058923721313,
+      "weight_tensor_scale": 0.0027204242069274187
+    },
+    "transformer_blocks.29.ff.net.0.proj.weight": {
+      "block_scale_max": 448.0,
+      "block_scale_mean": 27.099689483642578,
+      "block_scale_min": 4.5,
+      "calibration": "static_mse_fp8_e4m3_scale_sweep_126_candidates",
+      "shape": [
+        28672,
+        5376
+      ],
+      "source_dtype": "bfloat16",
+      "weight_global_amax": 7.0625,
+      "weight_saturation_rate": 0.06317268311977386,
+      "weight_tensor_scale": 0.0026274181436747313
+    },
+    "transformer_blocks.29.ff.net.2.weight": {
+      "block_scale_max": 448.0,
+      "block_scale_mean": 39.74492263793945,
+      "block_scale_min": 6.0,
+      "calibration": "static_mse_fp8_e4m3_scale_sweep_126_candidates",
+      "shape": [
+        5376,
+        14336
+      ],
+      "source_dtype": "bfloat16",
+      "weight_global_amax": 4.78125,
+      "weight_saturation_rate": 0.06351079046726227,
+      "weight_tensor_scale": 0.0017787389224395156
+    },
+    "transformer_blocks.3.ff.net.0.proj.weight": {
+      "block_scale_max": 448.0,
+      "block_scale_mean": 37.32854461669922,
+      "block_scale_min": 1.125,
+      "calibration": "static_mse_fp8_e4m3_scale_sweep_126_candidates",
+      "shape": [
+        28672,
+        5376
+      ],
+      "source_dtype": "bfloat16",
+      "weight_global_amax": 4.3125,
+      "weight_saturation_rate": 0.06356970965862274,
+      "weight_tensor_scale": 0.0016043527284637094
+    },
+    "transformer_blocks.3.ff.net.2.weight": {
+      "block_scale_max": 448.0,
+      "block_scale_mean": 61.829490661621094,
+      "block_scale_min": 11.0,
+      "calibration": "static_mse_fp8_e4m3_scale_sweep_126_candidates",
+      "shape": [
+        5376,
+        14336
+      ],
+      "source_dtype": "bfloat16",
+      "weight_global_amax": 2.859375,
+      "weight_saturation_rate": 0.06367290019989014,
+      "weight_tensor_scale": 0.0010637555969879031
+    },
+    "transformer_blocks.30.ff.net.0.proj.weight": {
+      "block_scale_max": 448.0,
+      "block_scale_mean": 30.47406005859375,
+      "block_scale_min": 5.0,
+      "calibration": "static_mse_fp8_e4m3_scale_sweep_126_candidates",
+      "shape": [
+        28672,
+        5376
+      ],
+      "source_dtype": "bfloat16",
+      "weight_global_amax": 6.3125,
+      "weight_saturation_rate": 0.06351572275161743,
+      "weight_tensor_scale": 0.002348400419577956
+    },
+    "transformer_blocks.30.ff.net.2.weight": {
+      "block_scale_max": 448.0,
+      "block_scale_mean": 15.345965385437012,
+      "block_scale_min": 2.25,
+      "calibration": "static_mse_fp8_e4m3_scale_sweep_126_candidates",
+      "shape": [
+        5376,
+        14336
+      ],
+      "source_dtype": "bfloat16",
+      "weight_global_amax": 12.3125,
+      "weight_saturation_rate": 0.0635567456483841,
+      "weight_tensor_scale": 0.004580543376505375
+    },
+    "transformer_blocks.31.ff.net.0.proj.weight": {
+      "block_scale_max": 448.0,
+      "block_scale_mean": 27.601680755615234,
+      "block_scale_min": 4.5,
+      "calibration": "static_mse_fp8_e4m3_scale_sweep_126_candidates",
+      "shape": [
+        28672,
+        5376
+      ],
+      "source_dtype": "bfloat16",
+      "weight_global_amax": 7.0,
+      "weight_saturation_rate": 0.0632418766617775,
+      "weight_tensor_scale": 0.0026041667442768812
+    },
+    "transformer_blocks.31.ff.net.2.weight": {
+      "block_scale_max": 448.0,
+      "block_scale_mean": 25.32246971130371,
+      "block_scale_min": 3.5,
+      "calibration": "static_mse_fp8_e4m3_scale_sweep_126_candidates",
+      "shape": [
+        5376,
+        14336
+      ],
+      "source_dtype": "bfloat16",
+      "weight_global_amax": 7.5,
+      "weight_saturation_rate": 0.06294618546962738,
+      "weight_tensor_scale": 0.0027901786379516125
+    },
+    "transformer_blocks.32.ff.net.0.proj.weight": {
+      "block_scale_max": 448.0,
+      "block_scale_mean": 15.44709587097168,
+      "block_scale_min": 2.75,
+      "calibration": "static_mse_fp8_e4m3_scale_sweep_126_candidates",
+      "shape": [
+        28672,
+        5376
+      ],
+      "source_dtype": "bfloat16",
+      "weight_global_amax": 12.5,
+      "weight_saturation_rate": 0.0635404884815216,
+      "weight_tensor_scale": 0.004650297574698925
+    },
+    "transformer_blocks.32.ff.net.2.weight": {
+      "block_scale_max": 448.0,
+      "block_scale_mean": 24.05265998840332,
+      "block_scale_min": 4.0,
+      "calibration": "static_mse_fp8_e4m3_scale_sweep_126_candidates",
+      "shape": [
+        5376,
+        14336
+      ],
+      "source_dtype": "bfloat16",
+      "weight_global_amax": 8.0,
+      "weight_saturation_rate": 0.06287529319524765,
+      "weight_tensor_scale": 0.0029761905316263437
+    },
+    "transformer_blocks.33.ff.net.0.proj.weight": {
+      "block_scale_max": 448.0,
+      "block_scale_mean": 23.434585571289062,
+      "block_scale_min": 4.5,
+      "calibration": "static_mse_fp8_e4m3_scale_sweep_126_candidates",
+      "shape": [
+        28672,
+        5376
+      ],
+      "source_dtype": "bfloat16",
+      "weight_global_amax": 8.3125,
+      "weight_saturation_rate": 0.06324472278356552,
+      "weight_tensor_scale": 0.0030924479942768812
+    },
+    "transformer_blocks.33.ff.net.2.weight": {
+      "block_scale_max": 448.0,
+      "block_scale_mean": 17.680030822753906,
+      "block_scale_min": 3.25,
+      "calibration": "static_mse_fp8_e4m3_scale_sweep_126_candidates",
+      "shape": [
+        5376,
+        14336
+      ],
+      "source_dtype": "bfloat16",
+      "weight_global_amax": 10.875,
+      "weight_saturation_rate": 0.06367697566747665,
+      "weight_tensor_scale": 0.0040457588620483875
+    },
+    "transformer_blocks.34.ff.net.0.proj.weight": {
+      "block_scale_max": 448.0,
+      "block_scale_mean": 23.52639389038086,
+      "block_scale_min": 3.75,
+      "calibration": "static_mse_fp8_e4m3_scale_sweep_126_candidates",
+      "shape": [
+        28672,
+        5376
+      ],
+      "source_dtype": "bfloat16",
+      "weight_global_amax": 8.3125,
+      "weight_saturation_rate": 0.06323325634002686,
+      "weight_tensor_scale": 0.0030924479942768812
+    },
+    "transformer_blocks.34.ff.net.2.weight": {
+      "block_scale_max": 448.0,
+      "block_scale_mean": 30.29164695739746,
+      "block_scale_min": 5.5,
+      "calibration": "static_mse_fp8_e4m3_scale_sweep_126_candidates",
+      "shape": [
+        5376,
+        14336
+      ],
+      "source_dtype": "bfloat16",
+      "weight_global_amax": 6.375,
+      "weight_saturation_rate": 0.06337087601423264,
+      "weight_tensor_scale": 0.0023716518189758062
+    },
+    "transformer_blocks.35.ff.net.0.proj.weight": {
+      "block_scale_max": 448.0,
+      "block_scale_mean": 25.029024124145508,
+      "block_scale_min": 4.0,
+      "calibration": "static_mse_fp8_e4m3_scale_sweep_126_candidates",
+      "shape": [
+        28672,
+        5376
+      ],
+      "source_dtype": "bfloat16",
+      "weight_global_amax": 7.875,
+      "weight_saturation_rate": 0.0632198303937912,
+      "weight_tensor_scale": 0.0029296875
+    },
+    "transformer_blocks.35.ff.net.2.weight": {
+      "block_scale_max": 448.0,
+      "block_scale_mean": 29.030969619750977,
+      "block_scale_min": 5.0,
+      "calibration": "static_mse_fp8_e4m3_scale_sweep_126_candidates",
+      "shape": [
+        5376,
+        14336
+      ],
+      "source_dtype": "bfloat16",
+      "weight_global_amax": 6.75,
+      "weight_saturation_rate": 0.0631941705942154,
+      "weight_tensor_scale": 0.0025111606810241938
+    },
+    "transformer_blocks.36.ff.net.0.proj.weight": {
+      "block_scale_max": 448.0,
+      "block_scale_mean": 16.119003295898438,
+      "block_scale_min": 2.25,
+      "calibration": "static_mse_fp8_e4m3_scale_sweep_126_candidates",
+      "shape": [
+        28672,
+        5376
+      ],
+      "source_dtype": "bfloat16",
+      "weight_global_amax": 12.1875,
+      "weight_saturation_rate": 0.06349044293165207,
+      "weight_tensor_scale": 0.0045340401120483875
+    },
+    "transformer_blocks.36.ff.net.2.weight": {
+      "block_scale_max": 448.0,
+      "block_scale_mean": 13.287566184997559,
+      "block_scale_min": 2.25,
+      "calibration": "static_mse_fp8_e4m3_scale_sweep_126_candidates",
+      "shape": [
+        5376,
+        14336
+      ],
+      "source_dtype": "bfloat16",
+      "weight_global_amax": 15.0,
+      "weight_saturation_rate": 0.06300721317529678,
+      "weight_tensor_scale": 0.005580357275903225
+    },
+    "transformer_blocks.37.ff.net.0.proj.weight": {
+      "block_scale_max": 448.0,
+      "block_scale_mean": 22.187801361083984,
+      "block_scale_min": 2.75,
+      "calibration": "static_mse_fp8_e4m3_scale_sweep_126_candidates",
+      "shape": [
+        28672,
+        5376
+      ],
+      "source_dtype": "bfloat16",
+      "weight_global_amax": 8.875,
+      "weight_saturation_rate": 0.06334291398525238,
+      "weight_tensor_scale": 0.0033017112873494625
+    },
+    "transformer_blocks.37.ff.net.2.weight": {
+      "block_scale_max": 448.0,
+      "block_scale_mean": 20.606719970703125,
+      "block_scale_min": 3.5,
+      "calibration": "static_mse_fp8_e4m3_scale_sweep_126_candidates",
+      "shape": [
+        5376,
+        14336
+      ],
+      "source_dtype": "bfloat16",
+      "weight_global_amax": 9.875,
+      "weight_saturation_rate": 0.06330295652151108,
+      "weight_tensor_scale": 0.003673735074698925
+    },
+    "transformer_blocks.38.ff.net.0.proj.weight": {
+      "block_scale_max": 448.0,
+      "block_scale_mean": 25.024084091186523,
+      "block_scale_min": 3.5,
+      "calibration": "static_mse_fp8_e4m3_scale_sweep_126_candidates",
+      "shape": [
+        28672,
+        5376
+      ],
+      "source_dtype": "bfloat16",
+      "weight_global_amax": 7.84375,
+      "weight_saturation_rate": 0.06324666738510132,
+      "weight_tensor_scale": 0.002918061800301075
+    },
+    "transformer_blocks.38.ff.net.2.weight": {
+      "block_scale_max": 448.0,
+      "block_scale_mean": 20.838666915893555,
+      "block_scale_min": 3.5,
+      "calibration": "static_mse_fp8_e4m3_scale_sweep_126_candidates",
+      "shape": [
+        5376,
+        14336
+      ],
+      "source_dtype": "bfloat16",
+      "weight_global_amax": 9.6875,
+      "weight_saturation_rate": 0.06329508870840073,
+      "weight_tensor_scale": 0.0036039806436747313
+    },
+    "transformer_blocks.39.ff.net.0.proj.weight": {
+      "block_scale_max": 448.0,
+      "block_scale_mean": 16.792165756225586,
+      "block_scale_min": 2.5,
+      "calibration": "static_mse_fp8_e4m3_scale_sweep_126_candidates",
+      "shape": [
+        28672,
+        5376
+      ],
+      "source_dtype": "bfloat16",
+      "weight_global_amax": 11.75,
+      "weight_saturation_rate": 0.0635409727692604,
+      "weight_tensor_scale": 0.00437127985060215
+    },
+    "transformer_blocks.39.ff.net.2.weight": {
+      "block_scale_max": 448.0,
+      "block_scale_mean": 12.181222915649414,
+      "block_scale_min": 1.875,
+      "calibration": "static_mse_fp8_e4m3_scale_sweep_126_candidates",
+      "shape": [
+        5376,
+        14336
+      ],
+      "source_dtype": "bfloat16",
+      "weight_global_amax": 16.75,
+      "weight_saturation_rate": 0.06287138909101486,
+      "weight_tensor_scale": 0.0062313987873494625
+    },
+    "transformer_blocks.4.ff.net.0.proj.weight": {
+      "block_scale_max": 448.0,
+      "block_scale_mean": 52.5825080871582,
+      "block_scale_min": 1.5,
+      "calibration": "static_mse_fp8_e4m3_scale_sweep_126_candidates",
+      "shape": [
+        28672,
+        5376
+      ],
+      "source_dtype": "bfloat16",
+      "weight_global_amax": 3.140625,
+      "weight_saturation_rate": 0.06332661956548691,
+      "weight_tensor_scale": 0.0011683872435241938
+    },
+    "transformer_blocks.4.ff.net.2.weight": {
+      "block_scale_max": 448.0,
+      "block_scale_mean": 66.93856048583984,
+      "block_scale_min": 10.0,
+      "calibration": "static_mse_fp8_e4m3_scale_sweep_126_candidates",
+      "shape": [
+        5376,
+        14336
+      ],
+      "source_dtype": "bfloat16",
+      "weight_global_amax": 2.640625,
+      "weight_saturation_rate": 0.06381122022867203,
+      "weight_tensor_scale": 0.0009823753498494625
+    },
+    "transformer_blocks.40.ff.net.0.proj.weight": {
+      "block_scale_max": 448.0,
+      "block_scale_mean": 18.87808609008789,
+      "block_scale_min": 2.75,
+      "calibration": "static_mse_fp8_e4m3_scale_sweep_126_candidates",
+      "shape": [
+        28672,
+        5376
+      ],
+      "source_dtype": "bfloat16",
+      "weight_global_amax": 10.4375,
+      "weight_saturation_rate": 0.06349419802427292,
+      "weight_tensor_scale": 0.00388299860060215
+    },
+    "transformer_blocks.40.ff.net.2.weight": {
+      "block_scale_max": 448.0,
+      "block_scale_mean": 21.494401931762695,
+      "block_scale_min": 3.75,
+      "calibration": "static_mse_fp8_e4m3_scale_sweep_126_candidates",
+      "shape": [
+        5376,
+        14336
+      ],
+      "source_dtype": "bfloat16",
+      "weight_global_amax": 9.4375,
+      "weight_saturation_rate": 0.0632006973028183,
+      "weight_tensor_scale": 0.0035109748132526875
+    },
+    "transformer_blocks.41.ff.net.0.proj.weight": {
+      "block_scale_max": 448.0,
+      "block_scale_mean": 13.759920120239258,
+      "block_scale_min": 2.0,
+      "calibration": "static_mse_fp8_e4m3_scale_sweep_126_candidates",
+      "shape": [
+        28672,
+        5376
+      ],
+      "source_dtype": "bfloat16",
+      "weight_global_amax": 14.3125,
+      "weight_saturation_rate": 0.06333687901496887,
+      "weight_tensor_scale": 0.0053245909512043
+    },
+    "transformer_blocks.41.ff.net.2.weight": {
+      "block_scale_max": 448.0,
+      "block_scale_mean": 18.74883460998535,
+      "block_scale_min": 2.0,
+      "calibration": "static_mse_fp8_e4m3_scale_sweep_126_candidates",
+      "shape": [
+        5376,
+        14336
+      ],
+      "source_dtype": "bfloat16",
+      "weight_global_amax": 10.8125,
+      "weight_saturation_rate": 0.06360317021608353,
+      "weight_tensor_scale": 0.0040225074626505375
+    },
+    "transformer_blocks.42.ff.net.0.proj.weight": {
+      "block_scale_max": 448.0,
+      "block_scale_mean": 14.955082893371582,
+      "block_scale_min": 1.25,
+      "calibration": "static_mse_fp8_e4m3_scale_sweep_126_candidates",
+      "shape": [
+        28672,
+        5376
+      ],
+      "source_dtype": "bfloat16",
+      "weight_global_amax": 12.9375,
+      "weight_saturation_rate": 0.06348460912704468,
+      "weight_tensor_scale": 0.00481305830180645
+    },
+    "transformer_blocks.42.ff.net.2.weight": {
+      "block_scale_max": 448.0,
+      "block_scale_mean": 20.942235946655273,
+      "block_scale_min": 3.0,
+      "calibration": "static_mse_fp8_e4m3_scale_sweep_126_candidates",
+      "shape": [
+        5376,
+        14336
+      ],
+      "source_dtype": "bfloat16",
+      "weight_global_amax": 9.8125,
+      "weight_saturation_rate": 0.06326696276664734,
+      "weight_tensor_scale": 0.003650483675301075
+    },
+    "transformer_blocks.43.ff.net.0.proj.weight": {
+      "block_scale_max": 448.0,
+      "block_scale_mean": 9.634349822998047,
+      "block_scale_min": 0.625,
+      "calibration": "static_mse_fp8_e4m3_scale_sweep_126_candidates",
+      "shape": [
+        28672,
+        5376
+      ],
+      "source_dtype": "bfloat16",
+      "weight_global_amax": 20.0,
+      "weight_saturation_rate": 0.06337322294712067,
+      "weight_tensor_scale": 0.0074404762126505375
+    },
+    "transformer_blocks.43.ff.net.2.weight": {
+      "block_scale_max": 448.0,
+      "block_scale_mean": 11.070377349853516,
+      "block_scale_min": 1.375,
+      "calibration": "static_mse_fp8_e4m3_scale_sweep_126_candidates",
+      "shape": [
+        5376,
+        14336
+      ],
+      "source_dtype": "bfloat16",
+      "weight_global_amax": 19.0,
+      "weight_saturation_rate": 0.06310083717107773,
+      "weight_tensor_scale": 0.007068452425301075
+    },
+    "transformer_blocks.44.ff.net.0.proj.weight": {
+      "block_scale_max": 448.0,
+      "block_scale_mean": 24.597610473632812,
+      "block_scale_min": 1.25,
+      "calibration": "static_mse_fp8_e4m3_scale_sweep_126_candidates",
+      "shape": [
+        28672,
+        5376
+      ],
+      "source_dtype": "bfloat16",
+      "weight_global_amax": 7.75,
+      "weight_saturation_rate": 0.06331908702850342,
+      "weight_tensor_scale": 0.0028831844683736563
+    },
+    "transformer_blocks.44.ff.net.2.weight": {
+      "block_scale_max": 448.0,
+      "block_scale_mean": 14.781803131103516,
+      "block_scale_min": 1.75,
+      "calibration": "static_mse_fp8_e4m3_scale_sweep_126_candidates",
+      "shape": [
+        5376,
+        14336
+      ],
+      "source_dtype": "bfloat16",
+      "weight_global_amax": 14.3125,
+      "weight_saturation_rate": 0.06344391405582428,
+      "weight_tensor_scale": 0.0053245909512043
+    },
+    "transformer_blocks.45.ff.net.0.proj.weight": {
+      "block_scale_max": 448.0,
+      "block_scale_mean": 23.468597412109375,
+      "block_scale_min": 1.625,
+      "calibration": "static_mse_fp8_e4m3_scale_sweep_126_candidates",
+      "shape": [
+        28672,
+        5376
+      ],
+      "source_dtype": "bfloat16",
+      "weight_global_amax": 8.0625,
+      "weight_saturation_rate": 0.06321724504232407,
+      "weight_tensor_scale": 0.0029994419310241938
+    },
+    "transformer_blocks.45.ff.net.2.weight": {
+      "block_scale_max": 448.0,
+      "block_scale_mean": 12.229371070861816,
+      "block_scale_min": 1.625,
+      "calibration": "static_mse_fp8_e4m3_scale_sweep_126_candidates",
+      "shape": [
+        5376,
+        14336
+      ],
+      "source_dtype": "bfloat16",
+      "weight_global_amax": 17.375,
+      "weight_saturation_rate": 0.06304023414850235,
+      "weight_tensor_scale": 0.0064639137126505375
+    },
+    "transformer_blocks.46.ff.net.0.proj.weight": {
+      "block_scale_max": 448.0,
+      "block_scale_mean": 18.223373413085938,
+      "block_scale_min": 1.0,
+      "calibration": "static_mse_fp8_e4m3_scale_sweep_126_candidates",
+      "shape": [
+        28672,
+        5376
+      ],
+      "source_dtype": "bfloat16",
+      "weight_global_amax": 10.25,
+      "weight_saturation_rate": 0.06341905146837234,
+      "weight_tensor_scale": 0.003813244169577956
+    },
+    "transformer_blocks.46.ff.net.2.weight": {
+      "block_scale_max": 448.0,
+      "block_scale_mean": 15.13412094116211,
+      "block_scale_min": 1.875,
+      "calibration": "static_mse_fp8_e4m3_scale_sweep_126_candidates",
+      "shape": [
+        5376,
+        14336
+      ],
+      "source_dtype": "bfloat16",
+      "weight_global_amax": 13.75,
+      "weight_saturation_rate": 0.06356246024370193,
+      "weight_tensor_scale": 0.005115327425301075
+    },
+    "transformer_blocks.47.ff.net.0.proj.weight": {
+      "block_scale_max": 448.0,
+      "block_scale_mean": 12.56476879119873,
+      "block_scale_min": 0.8125,
+      "calibration": "static_mse_fp8_e4m3_scale_sweep_126_candidates",
+      "shape": [
+        28672,
+        5376
+      ],
+      "source_dtype": "bfloat16",
+      "weight_global_amax": 14.375,
+      "weight_saturation_rate": 0.0632820799946785,
+      "weight_tensor_scale": 0.00534784235060215
+    },
+    "transformer_blocks.47.ff.net.2.weight": {
+      "block_scale_max": 448.0,
+      "block_scale_mean": 10.440226554870605,
+      "block_scale_min": 1.0,
+      "calibration": "static_mse_fp8_e4m3_scale_sweep_126_candidates",
+      "shape": [
+        5376,
+        14336
+      ],
+      "source_dtype": "bfloat16",
+      "weight_global_amax": 19.5,
+      "weight_saturation_rate": 0.06381946802139282,
+      "weight_tensor_scale": 0.00725446455180645
+    },
+    "transformer_blocks.48.ff.net.0.proj.weight": {
+      "block_scale_max": 448.0,
+      "block_scale_mean": 16.88715362548828,
+      "block_scale_min": 0.9375,
+      "calibration": "static_mse_fp8_e4m3_scale_sweep_126_candidates",
+      "shape": [
+        28672,
+        5376
+      ],
+      "source_dtype": "bfloat16",
+      "weight_global_amax": 10.25,
+      "weight_saturation_rate": 0.06342049688100815,
+      "weight_tensor_scale": 0.003813244169577956
+    },
+    "transformer_blocks.48.ff.net.2.weight": {
+      "block_scale_max": 448.0,
+      "block_scale_mean": 13.379511833190918,
+      "block_scale_min": 0.8125,
+      "calibration": "static_mse_fp8_e4m3_scale_sweep_126_candidates",
+      "shape": [
+        5376,
+        14336
+      ],
+      "source_dtype": "bfloat16",
+      "weight_global_amax": 14.125,
+      "weight_saturation_rate": 0.06343971192836761,
+      "weight_tensor_scale": 0.0052548362873494625
+    },
+    "transformer_blocks.49.ff.net.0.proj.weight": {
+      "block_scale_max": 448.0,
+      "block_scale_mean": 11.566972732543945,
+      "block_scale_min": 0.875,
+      "calibration": "static_mse_fp8_e4m3_scale_sweep_126_candidates",
+      "shape": [
+        28672,
+        5376
+      ],
+      "source_dtype": "bfloat16",
+      "weight_global_amax": 13.1875,
+      "weight_saturation_rate": 0.0632794201374054,
+      "weight_tensor_scale": 0.00490606389939785
+    },
+    "transformer_blocks.49.ff.net.2.weight": {
+      "block_scale_max": 448.0,
+      "block_scale_mean": 7.344248294830322,
+      "block_scale_min": 0.5625,
+      "calibration": "static_mse_fp8_e4m3_scale_sweep_126_candidates",
+      "shape": [
+        5376,
+        14336
+      ],
+      "source_dtype": "bfloat16",
+      "weight_global_amax": 7.8125,
+      "weight_saturation_rate": 0.06335751712322235,
+      "weight_tensor_scale": 0.00290643610060215
+    },
+    "transformer_blocks.5.ff.net.0.proj.weight": {
+      "block_scale_max": 448.0,
+      "block_scale_mean": 40.42057800292969,
+      "block_scale_min": 1.25,
+      "calibration": "static_mse_fp8_e4m3_scale_sweep_126_candidates",
+      "shape": [
+        28672,
+        5376
+      ],
+      "source_dtype": "bfloat16",
+      "weight_global_amax": 4.15625,
+      "weight_saturation_rate": 0.06342287361621857,
+      "weight_tensor_scale": 0.0015462239971384406
+    },
+    "transformer_blocks.5.ff.net.2.weight": {
+      "block_scale_max": 448.0,
+      "block_scale_mean": 50.37886428833008,
+      "block_scale_min": 7.0,
+      "calibration": "static_mse_fp8_e4m3_scale_sweep_126_candidates",
+      "shape": [
+        5376,
+        14336
+      ],
+      "source_dtype": "bfloat16",
+      "weight_global_amax": 3.515625,
+      "weight_saturation_rate": 0.06323392689228058,
+      "weight_tensor_scale": 0.0013078962219879031
+    },
+    "transformer_blocks.6.ff.net.0.proj.weight": {
+      "block_scale_max": 448.0,
+      "block_scale_mean": 44.86915588378906,
+      "block_scale_min": 1.5,
+      "calibration": "static_mse_fp8_e4m3_scale_sweep_126_candidates",
+      "shape": [
+        28672,
+        5376
+      ],
+      "source_dtype": "bfloat16",
+      "weight_global_amax": 3.734375,
+      "weight_saturation_rate": 0.06323476135730743,
+      "weight_tensor_scale": 0.0013892764691263437
+    },
+    "transformer_blocks.6.ff.net.2.weight": {
+      "block_scale_max": 448.0,
+      "block_scale_mean": 34.11444854736328,
+      "block_scale_min": 3.75,
+      "calibration": "static_mse_fp8_e4m3_scale_sweep_126_candidates",
+      "shape": [
+        5376,
+        14336
+      ],
+      "source_dtype": "bfloat16",
+      "weight_global_amax": 5.15625,
+      "weight_saturation_rate": 0.06395499408245087,
+      "weight_tensor_scale": 0.0019182477844879031
+    },
+    "transformer_blocks.7.ff.net.0.proj.weight": {
+      "block_scale_max": 448.0,
+      "block_scale_mean": 36.13459396362305,
+      "block_scale_min": 1.0,
+      "calibration": "static_mse_fp8_e4m3_scale_sweep_126_candidates",
+      "shape": [
+        28672,
+        5376
+      ],
+      "source_dtype": "bfloat16",
+      "weight_global_amax": 4.625,
+      "weight_saturation_rate": 0.06365320831537247,
+      "weight_tensor_scale": 0.0017206101911142468
+    },
+    "transformer_blocks.7.ff.net.2.weight": {
+      "block_scale_max": 448.0,
+      "block_scale_mean": 36.49217224121094,
+      "block_scale_min": 6.0,
+      "calibration": "static_mse_fp8_e4m3_scale_sweep_126_candidates",
+      "shape": [
+        5376,
+        14336
+      ],
+      "source_dtype": "bfloat16",
+      "weight_global_amax": 4.8125,
+      "weight_saturation_rate": 0.06392399966716766,
+      "weight_tensor_scale": 0.0017903646221384406
+    },
+    "transformer_blocks.8.ff.net.0.proj.weight": {
+      "block_scale_max": 448.0,
+      "block_scale_mean": 59.09828567504883,
+      "block_scale_min": 1.375,
+      "calibration": "static_mse_fp8_e4m3_scale_sweep_126_candidates",
+      "shape": [
+        28672,
+        5376
+      ],
+      "source_dtype": "bfloat16",
+      "weight_global_amax": 2.796875,
+      "weight_saturation_rate": 0.06344044208526611,
+      "weight_tensor_scale": 0.0010405040811747313
+    },
+    "transformer_blocks.8.ff.net.2.weight": {
+      "block_scale_max": 448.0,
+      "block_scale_mean": 73.22042083740234,
+      "block_scale_min": 9.0,
+      "calibration": "static_mse_fp8_e4m3_scale_sweep_126_candidates",
+      "shape": [
+        5376,
+        14336
+      ],
+      "source_dtype": "bfloat16",
+      "weight_global_amax": 2.359375,
+      "weight_saturation_rate": 0.06389103829860687,
+      "weight_tensor_scale": 0.0008777437033131719
+    },
+    "transformer_blocks.9.ff.net.0.proj.weight": {
+      "block_scale_max": 448.0,
+      "block_scale_mean": 34.58192443847656,
+      "block_scale_min": 0.875,
+      "calibration": "static_mse_fp8_e4m3_scale_sweep_126_candidates",
+      "shape": [
+        28672,
+        5376
+      ],
+      "source_dtype": "bfloat16",
+      "weight_global_amax": 4.65625,
+      "weight_saturation_rate": 0.06360290199518204,
+      "weight_tensor_scale": 0.0017322358908131719
+    },
+    "transformer_blocks.9.ff.net.2.weight": {
+      "block_scale_max": 448.0,
+      "block_scale_mean": 50.91958236694336,
+      "block_scale_min": 6.0,
+      "calibration": "static_mse_fp8_e4m3_scale_sweep_126_candidates",
+      "shape": [
+        5376,
+        14336
+      ],
+      "source_dtype": "bfloat16",
+      "weight_global_amax": 3.3125,
+      "weight_saturation_rate": 0.0634537786245346,
+      "weight_tensor_scale": 0.0012323289411142468
+    }
+  }
+}

vae/config.json

@@ -0,0 +1,97 @@
+{
+  "_class_name": "AutoencoderKLMiniMaxH3",
+  "_diffusers_version": "0.36.0.dev0",
+  "in_channels": 3,
+  "out_channels": 3,
+  "latent_channels": 24,
+  "block_out_channels": [
+    128,
+    256,
+    256,
+    512,
+    512,
+    1024
+  ],
+  "layers_per_block": 2,
+  "spatial_downsample_factors": [
+    2,
+    2,
+    2,
+    2,
+    1,
+    1
+  ],
+  "temporal_downsample_factors": [
+    1,
+    2,
+    2,
+    1,
+    1,
+    1
+  ],
+  "norm_num_groups": 32,
+  "norm_eps": 1e-06,
+  "spatial_padding_mode": "reflect",
+  "decoder_num_layers": 36,
+  "decoder_num_attention_heads": 32,
+  "decoder_attention_head_dim": 64,
+  "decoder_num_register_tokens": 4,
+  "decoder_ffn_mult": 4,
+  "decoder_rope_theta": 100.0,
+  "decoder_rope_dim_ratio": 0.75,
+  "decoder_norm_eps": 1e-05,
+  "clip_length": 17,
+  "token_drop": 3,
+  "latents_mean": [
+    0.858090341091156,
+    -0.9606591463088989,
+    1.0661640167236328,
+    -0.5090325474739075,
+    -0.2727581858634949,
+    -1.3675414323806763,
+    -0.2553254961967468,
+    -0.26907554268836975,
+    -0.5376840829849243,
+    -0.0464097298681736,
+    0.6657370328903198,
+    0.19690127670764923,
+    -0.5460608005523682,
+    -0.4035342037677765,
+    -0.23683024942874908,
+    0.25928452610969543,
+    -0.30133944749832153,
+    0.211341992020607,
+    -1.1206848621368408,
+    0.3581933379173279,
+    -0.04225143790245056,
+    0.2604829967021942,
+    0.22864092886447906,
+    0.7056031823158264
+  ],
+  "latents_std": [
+    1.2223774194717407,
+    1.2767263650894165,
+    1.6831774711608887,
+    1.7549455165863037,
+    1.5636216402053833,
+    2.194143533706665,
+    0.9653137922286987,
+    1.0569885969161987,
+    0.841948926448822,
+    0.7729952931404114,
+    1.8955937623977661,
+    0.946841835975647,
+    0.7996809482574463,
+    0.44988900423049927,
+    0.7197399735450745,
+    0.6936293244361877,
+    2.961095094680786,
+    2.7694199085235596,
+    3.0496184825897217,
+    2.1088054180145264,
+    3.276226282119751,
+    3.1627357006073,
+    2.2816812992095947,
+    2.6127843856811523
+  ]
+}

vae/diffusion_pytorch_model.safetensors.index.json

@@ -0,0 +1,710 @@
+{
+  "metadata": {
+    "total_size": 10415475936
+  },
+  "weight_map": {
+    "decoder.norm_out.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.norm_out.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.proj_in.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.proj_in.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.proj_out.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.proj_out.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.register_tokens": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.0.attn.to_k.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.0.attn.to_k.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.0.attn.to_out.0.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.0.attn.to_out.0.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.0.attn.to_q.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.0.attn.to_q.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.0.attn.to_v.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.0.attn.to_v.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.0.ff.net.0.proj.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.0.ff.net.0.proj.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.0.ff.net.2.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.0.ff.net.2.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.0.norm1.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.0.norm2.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.0.scale1": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.0.scale2": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.1.attn.to_k.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.1.attn.to_k.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.1.attn.to_out.0.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.1.attn.to_out.0.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.1.attn.to_q.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.1.attn.to_q.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.1.attn.to_v.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.1.attn.to_v.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.1.ff.net.0.proj.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.1.ff.net.0.proj.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.1.ff.net.2.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.1.ff.net.2.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.1.norm1.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.1.norm2.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.1.scale1": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.1.scale2": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.10.attn.to_k.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.10.attn.to_k.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.10.attn.to_out.0.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.10.attn.to_out.0.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.10.attn.to_q.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.10.attn.to_q.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.10.attn.to_v.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.10.attn.to_v.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.10.ff.net.0.proj.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.10.ff.net.0.proj.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.10.ff.net.2.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.10.ff.net.2.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.10.norm1.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.10.norm2.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.10.scale1": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.10.scale2": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.11.attn.to_k.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.11.attn.to_k.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.11.attn.to_out.0.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.11.attn.to_out.0.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.11.attn.to_q.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.11.attn.to_q.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.11.attn.to_v.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.11.attn.to_v.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.11.ff.net.0.proj.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.11.ff.net.0.proj.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.11.ff.net.2.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.11.ff.net.2.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.11.norm1.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.11.norm2.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.11.scale1": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.11.scale2": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.12.attn.to_k.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.12.attn.to_k.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.12.attn.to_out.0.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.12.attn.to_out.0.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.12.attn.to_q.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.12.attn.to_q.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.12.attn.to_v.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.12.attn.to_v.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.12.ff.net.0.proj.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.12.ff.net.0.proj.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.12.ff.net.2.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.12.ff.net.2.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.12.norm1.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.12.norm2.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.12.scale1": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.12.scale2": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.13.attn.to_k.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.13.attn.to_k.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.13.attn.to_out.0.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.13.attn.to_out.0.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.13.attn.to_q.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.13.attn.to_q.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.13.attn.to_v.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.13.attn.to_v.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.13.ff.net.0.proj.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.13.ff.net.0.proj.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.13.ff.net.2.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.13.ff.net.2.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.13.norm1.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.13.norm2.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.13.scale1": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.13.scale2": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.14.attn.to_k.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.14.attn.to_k.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.14.attn.to_out.0.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.14.attn.to_out.0.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.14.attn.to_q.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.14.attn.to_q.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.14.attn.to_v.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.14.attn.to_v.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.14.ff.net.0.proj.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.14.ff.net.0.proj.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.14.ff.net.2.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.14.ff.net.2.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.14.norm1.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.14.norm2.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.14.scale1": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.14.scale2": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.15.attn.to_k.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.15.attn.to_k.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.15.attn.to_out.0.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.15.attn.to_out.0.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.15.attn.to_q.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.15.attn.to_q.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.15.attn.to_v.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.15.attn.to_v.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.15.ff.net.0.proj.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.15.ff.net.0.proj.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.15.ff.net.2.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.15.ff.net.2.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.15.norm1.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.15.norm2.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.15.scale1": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.15.scale2": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.16.attn.to_k.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.16.attn.to_k.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.16.attn.to_out.0.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.16.attn.to_out.0.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.16.attn.to_q.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.16.attn.to_q.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.16.attn.to_v.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.16.attn.to_v.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.16.ff.net.0.proj.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.16.ff.net.0.proj.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.16.ff.net.2.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.16.ff.net.2.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.16.norm1.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.16.norm2.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.16.scale1": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.16.scale2": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.17.attn.to_k.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.17.attn.to_k.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.17.attn.to_out.0.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.17.attn.to_out.0.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.17.attn.to_q.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.17.attn.to_q.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.17.attn.to_v.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.17.attn.to_v.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.17.ff.net.0.proj.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.17.ff.net.0.proj.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.17.ff.net.2.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.17.ff.net.2.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.17.norm1.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.17.norm2.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.17.scale1": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.17.scale2": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.18.attn.to_k.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.18.attn.to_k.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.18.attn.to_out.0.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.18.attn.to_out.0.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.18.attn.to_q.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.18.attn.to_q.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.18.attn.to_v.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.18.attn.to_v.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.18.ff.net.0.proj.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.18.ff.net.0.proj.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.18.ff.net.2.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.18.ff.net.2.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.18.norm1.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.18.norm2.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.18.scale1": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.18.scale2": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.19.attn.to_k.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.19.attn.to_k.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.19.attn.to_out.0.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.19.attn.to_out.0.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.19.attn.to_q.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.19.attn.to_q.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.19.attn.to_v.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.19.attn.to_v.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.19.ff.net.0.proj.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.19.ff.net.0.proj.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.19.ff.net.2.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.19.ff.net.2.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.19.norm1.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.19.norm2.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.19.scale1": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.19.scale2": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.2.attn.to_k.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.2.attn.to_k.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.2.attn.to_out.0.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.2.attn.to_out.0.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.2.attn.to_q.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.2.attn.to_q.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.2.attn.to_v.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.2.attn.to_v.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.2.ff.net.0.proj.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.2.ff.net.0.proj.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.2.ff.net.2.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.2.ff.net.2.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.2.norm1.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.2.norm2.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.2.scale1": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.2.scale2": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.20.attn.to_k.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.20.attn.to_k.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.20.attn.to_out.0.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.20.attn.to_out.0.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.20.attn.to_q.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.20.attn.to_q.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.20.attn.to_v.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.20.attn.to_v.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.20.ff.net.0.proj.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.20.ff.net.0.proj.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.20.ff.net.2.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.20.ff.net.2.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.20.norm1.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.20.norm2.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.20.scale1": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.20.scale2": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.21.attn.to_k.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.21.attn.to_k.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.21.attn.to_out.0.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.21.attn.to_out.0.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.21.attn.to_q.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.21.attn.to_q.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.21.attn.to_v.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.21.attn.to_v.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.21.ff.net.0.proj.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.21.ff.net.0.proj.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.21.ff.net.2.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.21.ff.net.2.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.21.norm1.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.21.norm2.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.21.scale1": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.21.scale2": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.22.attn.to_k.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.22.attn.to_k.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.22.attn.to_out.0.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.22.attn.to_out.0.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.22.attn.to_q.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.22.attn.to_q.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.22.attn.to_v.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.22.attn.to_v.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.22.ff.net.0.proj.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.22.ff.net.0.proj.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.22.ff.net.2.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.22.ff.net.2.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.22.norm1.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.22.norm2.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.22.scale1": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.22.scale2": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.23.attn.to_k.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.23.attn.to_k.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.23.attn.to_out.0.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.23.attn.to_out.0.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.23.attn.to_q.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.23.attn.to_q.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.23.attn.to_v.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.23.attn.to_v.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.23.ff.net.0.proj.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.23.ff.net.0.proj.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.23.ff.net.2.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.23.ff.net.2.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.23.norm1.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.23.norm2.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.23.scale1": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.23.scale2": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.24.attn.to_k.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.24.attn.to_k.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.24.attn.to_out.0.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.24.attn.to_out.0.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.24.attn.to_q.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.24.attn.to_q.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.24.attn.to_v.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.24.attn.to_v.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.24.ff.net.0.proj.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.24.ff.net.0.proj.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.24.ff.net.2.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.24.ff.net.2.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.24.norm1.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.24.norm2.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.24.scale1": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.24.scale2": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.25.attn.to_k.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.25.attn.to_k.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.25.attn.to_out.0.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.25.attn.to_out.0.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.25.attn.to_q.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.25.attn.to_q.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.25.attn.to_v.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.25.attn.to_v.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.25.ff.net.0.proj.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.25.ff.net.0.proj.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.25.ff.net.2.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.25.ff.net.2.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.25.norm1.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.25.norm2.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.25.scale1": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.25.scale2": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.26.attn.to_k.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.26.attn.to_k.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.26.attn.to_out.0.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.26.attn.to_out.0.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.26.attn.to_q.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.26.attn.to_q.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.26.attn.to_v.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.26.attn.to_v.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.26.ff.net.0.proj.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.26.ff.net.0.proj.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.26.ff.net.2.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.26.ff.net.2.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.26.norm1.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.26.norm2.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.26.scale1": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.26.scale2": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.27.attn.to_k.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.27.attn.to_k.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.27.attn.to_out.0.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.27.attn.to_out.0.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.27.attn.to_q.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.27.attn.to_q.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.27.attn.to_v.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.27.attn.to_v.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.27.ff.net.0.proj.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.27.ff.net.0.proj.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.27.ff.net.2.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.27.ff.net.2.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.27.norm1.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.27.norm2.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.27.scale1": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.27.scale2": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.28.attn.to_k.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.28.attn.to_k.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.28.attn.to_out.0.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.28.attn.to_out.0.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.28.attn.to_q.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.28.attn.to_q.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.28.attn.to_v.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.28.attn.to_v.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.28.ff.net.0.proj.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.28.ff.net.0.proj.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.28.ff.net.2.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.28.ff.net.2.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.28.norm1.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.28.norm2.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.28.scale1": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.28.scale2": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.29.attn.to_k.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.29.attn.to_k.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.29.attn.to_out.0.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.29.attn.to_out.0.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.29.attn.to_q.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.29.attn.to_q.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.29.attn.to_v.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.29.attn.to_v.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.29.ff.net.0.proj.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.29.ff.net.0.proj.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.29.ff.net.2.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.29.ff.net.2.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.29.norm1.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.29.norm2.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.29.scale1": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.29.scale2": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.3.attn.to_k.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.3.attn.to_k.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.3.attn.to_out.0.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.3.attn.to_out.0.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.3.attn.to_q.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.3.attn.to_q.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.3.attn.to_v.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.3.attn.to_v.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.3.ff.net.0.proj.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.3.ff.net.0.proj.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.3.ff.net.2.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.3.ff.net.2.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.3.norm1.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.3.norm2.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.3.scale1": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.3.scale2": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.30.attn.to_k.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.30.attn.to_k.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.30.attn.to_out.0.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.30.attn.to_out.0.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.30.attn.to_q.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.30.attn.to_q.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.30.attn.to_v.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.30.attn.to_v.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.30.ff.net.0.proj.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.30.ff.net.0.proj.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.30.ff.net.2.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.30.ff.net.2.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.30.norm1.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.30.norm2.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.30.scale1": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.30.scale2": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.31.attn.to_k.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.31.attn.to_k.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.31.attn.to_out.0.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.31.attn.to_out.0.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.31.attn.to_q.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.31.attn.to_q.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.31.attn.to_v.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.31.attn.to_v.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.31.ff.net.0.proj.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.31.ff.net.0.proj.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.31.ff.net.2.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.31.ff.net.2.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.31.norm1.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.31.norm2.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.31.scale1": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.31.scale2": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.32.attn.to_k.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.32.attn.to_k.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.32.attn.to_out.0.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.32.attn.to_out.0.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.32.attn.to_q.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.32.attn.to_q.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.32.attn.to_v.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.32.attn.to_v.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.32.ff.net.0.proj.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.32.ff.net.0.proj.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.32.ff.net.2.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.32.ff.net.2.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.32.norm1.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.32.norm2.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.32.scale1": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.32.scale2": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.33.attn.to_k.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.33.attn.to_k.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.33.attn.to_out.0.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.33.attn.to_out.0.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.33.attn.to_q.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.33.attn.to_q.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.33.attn.to_v.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.33.attn.to_v.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.33.ff.net.0.proj.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.33.ff.net.0.proj.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.33.ff.net.2.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.33.ff.net.2.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.33.norm1.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.33.norm2.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.33.scale1": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.33.scale2": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.34.attn.to_k.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.34.attn.to_k.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.34.attn.to_out.0.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.34.attn.to_out.0.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.34.attn.to_q.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.34.attn.to_q.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.34.attn.to_v.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.34.attn.to_v.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.34.ff.net.0.proj.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.34.ff.net.0.proj.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.34.ff.net.2.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.34.ff.net.2.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.34.norm1.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.34.norm2.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.34.scale1": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.34.scale2": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.35.attn.to_k.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.35.attn.to_k.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.35.attn.to_out.0.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.35.attn.to_out.0.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.35.attn.to_q.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.35.attn.to_q.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.35.attn.to_v.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.35.attn.to_v.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.35.ff.net.0.proj.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.35.ff.net.0.proj.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.35.ff.net.2.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.35.ff.net.2.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.35.norm1.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.35.norm2.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.35.scale1": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.35.scale2": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.4.attn.to_k.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.4.attn.to_k.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.4.attn.to_out.0.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.4.attn.to_out.0.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.4.attn.to_q.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.4.attn.to_q.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.4.attn.to_v.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.4.attn.to_v.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.4.ff.net.0.proj.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.4.ff.net.0.proj.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.4.ff.net.2.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.4.ff.net.2.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.4.norm1.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.4.norm2.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.4.scale1": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.4.scale2": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.5.attn.to_k.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.5.attn.to_k.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.5.attn.to_out.0.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.5.attn.to_out.0.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.5.attn.to_q.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.5.attn.to_q.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.5.attn.to_v.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.5.attn.to_v.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.5.ff.net.0.proj.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.5.ff.net.0.proj.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.5.ff.net.2.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.5.ff.net.2.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.5.norm1.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.5.norm2.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.5.scale1": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.5.scale2": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.6.attn.to_k.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.6.attn.to_k.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.6.attn.to_out.0.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.6.attn.to_out.0.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.6.attn.to_q.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.6.attn.to_q.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.6.attn.to_v.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.6.attn.to_v.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.6.ff.net.0.proj.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.6.ff.net.0.proj.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.6.ff.net.2.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.6.ff.net.2.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.6.norm1.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.6.norm2.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.6.scale1": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.6.scale2": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.7.attn.to_k.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.7.attn.to_k.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.7.attn.to_out.0.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.7.attn.to_out.0.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.7.attn.to_q.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.7.attn.to_q.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.7.attn.to_v.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.7.attn.to_v.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.7.ff.net.0.proj.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.7.ff.net.0.proj.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.7.ff.net.2.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.7.ff.net.2.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.7.norm1.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.7.norm2.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.7.scale1": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.7.scale2": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.8.attn.to_k.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.8.attn.to_k.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.8.attn.to_out.0.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.8.attn.to_out.0.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.8.attn.to_q.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.8.attn.to_q.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.8.attn.to_v.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.8.attn.to_v.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.8.ff.net.0.proj.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.8.ff.net.0.proj.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.8.ff.net.2.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.8.ff.net.2.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.8.norm1.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.8.norm2.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.8.scale1": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.8.scale2": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.9.attn.to_k.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.9.attn.to_k.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.9.attn.to_out.0.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.9.attn.to_out.0.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.9.attn.to_q.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.9.attn.to_q.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.9.attn.to_v.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.9.attn.to_v.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.9.ff.net.0.proj.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.9.ff.net.0.proj.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.9.ff.net.2.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.9.ff.net.2.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.9.norm1.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.9.norm2.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.9.scale1": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.9.scale2": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "encoder.conv_in.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "encoder.conv_in.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "encoder.conv_out.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "encoder.conv_out.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "encoder.down_blocks.0.downsamplers.0.conv.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "encoder.down_blocks.0.downsamplers.0.conv.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "encoder.down_blocks.0.resnets.0.conv1.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "encoder.down_blocks.0.resnets.0.conv1.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "encoder.down_blocks.0.resnets.0.conv2.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "encoder.down_blocks.0.resnets.0.conv2.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "encoder.down_blocks.0.resnets.0.norm1.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "encoder.down_blocks.0.resnets.0.norm1.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "encoder.down_blocks.0.resnets.0.norm2.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "encoder.down_blocks.0.resnets.0.norm2.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "encoder.down_blocks.0.resnets.1.conv1.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "encoder.down_blocks.0.resnets.1.conv1.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "encoder.down_blocks.0.resnets.1.conv2.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "encoder.down_blocks.0.resnets.1.conv2.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "encoder.down_blocks.0.resnets.1.norm1.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "encoder.down_blocks.0.resnets.1.norm1.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "encoder.down_blocks.0.resnets.1.norm2.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "encoder.down_blocks.0.resnets.1.norm2.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "encoder.down_blocks.1.downsamplers.0.conv.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "encoder.down_blocks.1.downsamplers.0.conv.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "encoder.down_blocks.1.resnets.0.conv1.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "encoder.down_blocks.1.resnets.0.conv1.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "encoder.down_blocks.1.resnets.0.conv2.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "encoder.down_blocks.1.resnets.0.conv2.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "encoder.down_blocks.1.resnets.0.conv_shortcut.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "encoder.down_blocks.1.resnets.0.conv_shortcut.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "encoder.down_blocks.1.resnets.0.norm1.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "encoder.down_blocks.1.resnets.0.norm1.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "encoder.down_blocks.1.resnets.0.norm2.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "encoder.down_blocks.1.resnets.0.norm2.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "encoder.down_blocks.1.resnets.1.conv1.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "encoder.down_blocks.1.resnets.1.conv1.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "encoder.down_blocks.1.resnets.1.conv2.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "encoder.down_blocks.1.resnets.1.conv2.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "encoder.down_blocks.1.resnets.1.norm1.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "encoder.down_blocks.1.resnets.1.norm1.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "encoder.down_blocks.1.resnets.1.norm2.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "encoder.down_blocks.1.resnets.1.norm2.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "encoder.down_blocks.2.downsamplers.0.conv.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "encoder.down_blocks.2.downsamplers.0.conv.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "encoder.down_blocks.2.resnets.0.conv1.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "encoder.down_blocks.2.resnets.0.conv1.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "encoder.down_blocks.2.resnets.0.conv2.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "encoder.down_blocks.2.resnets.0.conv2.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "encoder.down_blocks.2.resnets.0.norm1.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "encoder.down_blocks.2.resnets.0.norm1.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "encoder.down_blocks.2.resnets.0.norm2.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "encoder.down_blocks.2.resnets.0.norm2.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "encoder.down_blocks.2.resnets.1.conv1.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "encoder.down_blocks.2.resnets.1.conv1.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "encoder.down_blocks.2.resnets.1.conv2.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "encoder.down_blocks.2.resnets.1.conv2.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "encoder.down_blocks.2.resnets.1.norm1.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "encoder.down_blocks.2.resnets.1.norm1.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "encoder.down_blocks.2.resnets.1.norm2.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "encoder.down_blocks.2.resnets.1.norm2.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "encoder.down_blocks.3.downsamplers.0.conv.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "encoder.down_blocks.3.downsamplers.0.conv.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "encoder.down_blocks.3.resnets.0.conv1.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "encoder.down_blocks.3.resnets.0.conv1.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "encoder.down_blocks.3.resnets.0.conv2.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "encoder.down_blocks.3.resnets.0.conv2.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "encoder.down_blocks.3.resnets.0.conv_shortcut.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "encoder.down_blocks.3.resnets.0.conv_shortcut.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "encoder.down_blocks.3.resnets.0.norm1.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "encoder.down_blocks.3.resnets.0.norm1.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "encoder.down_blocks.3.resnets.0.norm2.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "encoder.down_blocks.3.resnets.0.norm2.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "encoder.down_blocks.3.resnets.1.conv1.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "encoder.down_blocks.3.resnets.1.conv1.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "encoder.down_blocks.3.resnets.1.conv2.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "encoder.down_blocks.3.resnets.1.conv2.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "encoder.down_blocks.3.resnets.1.norm1.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "encoder.down_blocks.3.resnets.1.norm1.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "encoder.down_blocks.3.resnets.1.norm2.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "encoder.down_blocks.3.resnets.1.norm2.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "encoder.down_blocks.4.resnets.0.conv1.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "encoder.down_blocks.4.resnets.0.conv1.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "encoder.down_blocks.4.resnets.0.conv2.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "encoder.down_blocks.4.resnets.0.conv2.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "encoder.down_blocks.4.resnets.0.norm1.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "encoder.down_blocks.4.resnets.0.norm1.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "encoder.down_blocks.4.resnets.0.norm2.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "encoder.down_blocks.4.resnets.0.norm2.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "encoder.down_blocks.4.resnets.1.conv1.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "encoder.down_blocks.4.resnets.1.conv1.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "encoder.down_blocks.4.resnets.1.conv2.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "encoder.down_blocks.4.resnets.1.conv2.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "encoder.down_blocks.4.resnets.1.norm1.bias": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "encoder.down_blocks.4.resnets.1.norm1.weight": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "encoder.down_blocks.4.resnets.1.norm2.bias": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "encoder.down_blocks.4.resnets.1.norm2.weight": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "encoder.down_blocks.5.resnets.0.conv1.bias": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "encoder.down_blocks.5.resnets.0.conv1.weight": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "encoder.down_blocks.5.resnets.0.conv2.bias": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "encoder.down_blocks.5.resnets.0.conv2.weight": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "encoder.down_blocks.5.resnets.0.conv_shortcut.bias": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "encoder.down_blocks.5.resnets.0.conv_shortcut.weight": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "encoder.down_blocks.5.resnets.0.norm1.bias": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "encoder.down_blocks.5.resnets.0.norm1.weight": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "encoder.down_blocks.5.resnets.0.norm2.bias": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "encoder.down_blocks.5.resnets.0.norm2.weight": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "encoder.down_blocks.5.resnets.1.conv1.bias": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "encoder.down_blocks.5.resnets.1.conv1.weight": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "encoder.down_blocks.5.resnets.1.conv2.bias": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "encoder.down_blocks.5.resnets.1.conv2.weight": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "encoder.down_blocks.5.resnets.1.norm1.bias": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "encoder.down_blocks.5.resnets.1.norm1.weight": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "encoder.down_blocks.5.resnets.1.norm2.bias": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "encoder.down_blocks.5.resnets.1.norm2.weight": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "encoder.norm_out.bias": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "encoder.norm_out.weight": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "post_quant_conv.bias": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "post_quant_conv.weight": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "quant_conv.bias": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "quant_conv.weight": "diffusion_pytorch_model-00003-of-00003.safetensors"
+  }
+}