Upload folder using huggingface_hub

.gitattributes

@@ -1,35 +1,52 @@
 *.7z filter=lfs diff=lfs merge=lfs -text
 *.arrow filter=lfs diff=lfs merge=lfs -text
 *.bin filter=lfs diff=lfs merge=lfs -text
+*.bin.* filter=lfs diff=lfs merge=lfs -text
 *.bz2 filter=lfs diff=lfs merge=lfs -text
-*.ckpt filter=lfs diff=lfs merge=lfs -text
 *.ftz filter=lfs diff=lfs merge=lfs -text
 *.gz filter=lfs diff=lfs merge=lfs -text
 *.h5 filter=lfs diff=lfs merge=lfs -text
 *.joblib filter=lfs diff=lfs merge=lfs -text
 *.lfs.* filter=lfs diff=lfs merge=lfs -text
-*.mlmodel filter=lfs diff=lfs merge=lfs -text
 *.model filter=lfs diff=lfs merge=lfs -text
 *.msgpack filter=lfs diff=lfs merge=lfs -text
-*.npy filter=lfs diff=lfs merge=lfs -text
-*.npz filter=lfs diff=lfs merge=lfs -text
 *.onnx filter=lfs diff=lfs merge=lfs -text
 *.ot filter=lfs diff=lfs merge=lfs -text
 *.parquet filter=lfs diff=lfs merge=lfs -text
 *.pb filter=lfs diff=lfs merge=lfs -text
-*.pickle filter=lfs diff=lfs merge=lfs -text
-*.pkl filter=lfs diff=lfs merge=lfs -text
-*.pt filter=lfs diff=lfs merge=lfs -text
 *.pth filter=lfs diff=lfs merge=lfs -text
 *.rar filter=lfs diff=lfs merge=lfs -text
-*.safetensors filter=lfs diff=lfs merge=lfs -text
 saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.tar.* filter=lfs diff=lfs merge=lfs -text
-*.tar filter=lfs diff=lfs merge=lfs -text
 *.tflite filter=lfs diff=lfs merge=lfs -text
 *.tgz filter=lfs diff=lfs merge=lfs -text
-*.wasm filter=lfs diff=lfs merge=lfs -text
 *.xz filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
+*.zstandard filter=lfs diff=lfs merge=lfs -text
+*.tfevents* filter=lfs diff=lfs merge=lfs -text
+*.db* filter=lfs diff=lfs merge=lfs -text
+*.ark* filter=lfs diff=lfs merge=lfs -text
+**/*ckpt*data* filter=lfs diff=lfs merge=lfs -text
+**/*ckpt*.meta filter=lfs diff=lfs merge=lfs -text
+**/*ckpt*.index filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.gguf* filter=lfs diff=lfs merge=lfs -text
+*.ggml filter=lfs diff=lfs merge=lfs -text
+*.llamafile* filter=lfs diff=lfs merge=lfs -text
+*.pt2 filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+checkpoints/evo2_nemo_7b/weights/__0_1.distcp filter=lfs diff=lfs merge=lfs -text
+checkpoints/evo2_nemo_7b/weights/__0_0.distcp filter=lfs diff=lfs merge=lfs -text
+checkpoints/evo2_nemo_7b/weights/common.pt filter=lfs diff=lfs merge=lfs -text
+*.fa filter=lfs diff=lfs merge=lfs -text
+*.fa.gz filter=lfs diff=lfs merge=lfs -text
+checkpoints/evo2_nemo_7b/weights/.metadata filter=lfs diff=lfs merge=lfs -text

LICENSE

@@ -0,0 +1,467 @@
+                             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.
+
+--
+
+This repository also contains code from Hugging Face Inc., Google Research,
+and Facebook (from their Fairseq project). Files from these
+organizations have notices at the top of each file. Below are licenses
+used in those files, as indicated.
+
+
+------------- LICENSE FOR NVIDIA code  --------------
+
+
+# Copyright (c) 2020, NVIDIA CORPORATION. All rights reserved.
+#
+# Redistribution and use in source and binary forms, with or without
+# modification, are permitted provided that the following conditions
+# are met:
+#  * Redistributions of source code must retain the above copyright
+#    notice, this list of conditions and the following disclaimer.
+#  * Redistributions in binary form must reproduce the above copyright
+#    notice, this list of conditions and the following disclaimer in the
+#    documentation and/or other materials provided with the distribution.
+#  * Neither the name of NVIDIA CORPORATION nor the names of its
+#    contributors may be used to endorse or promote products derived
+#    from this software without specific prior written permission.
+#
+# THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS ``AS IS'' AND ANY
+# EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+# IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR
+# PURPOSE ARE DISCLAIMED.  IN NO EVENT SHALL THE COPYRIGHT OWNER OR
+# CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL,
+# EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO,
+# PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR
+# PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY
+# OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+# (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
+# OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+
+------------- LICENSE FOR huggingface and Google Research code  --------------
+
+
+                                 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.
+
+------------- LICENSE FOR Facebook Fairseq code --------------
+
+MIT License
+
+Copyright (c) Facebook, Inc. and its affiliates.
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.

README.md

@@ -0,0 +1,321 @@
+---
+frameworks:
+- ""
+language:
+- en
+- zh
+license: apache-2.0
+tags:
+- OneScience
+- life-science
+- genomic-sequence-modeling
+- DNA/RNA
+tasks: []
+---
+
+<p align="center">
+  <strong><span style="font-size: 30px;">Evo2</span></strong>
+</p>
+
+# Model Introduction
+
+Evo2 is a large-scale foundation model for genomic sequences. It can generate, complete, and predict functions for DNA/RNA sequences. The model supports pretraining on large-scale genomic datasets and can be rapidly adapted to downstream tasks such as regulatory element prediction and variant effect assessment, providing a unified sequence modeling tool for genomics research.
+
+# Model Description
+
+Evo2 is built on a hybrid architecture that combines Hyena operators with convolutional gating, and supports context windows at the million-token scale. The model is pretrained on multi-species genomic data containing trillions of base pairs. It takes raw nucleotide sequences as input and supports autoregressive generation, sequence classification, and embedding extraction. Evo2 is compatible with multi-GPU distributed training and flexible data mixing, achieves leading performance on benchmarks such as GenBench, and is suitable for pretraining, fine-tuning, and downstream functional validation.
+
+# Applicable Scenarios
+
+| Scenario | Description |
+| --- | --- |
+| DNA/RNA sequence generation | Generate subsequent genomic sequence fragments from an input prompt |
+| FASTA sequence prediction | Read FASTA input and output sequence prediction results |
+| Local offline inference validation | Use the example inputs in this repository and a local checkpoint to verify the inference workflow end to end |
+| Mini training workflow validation | Use `data/data_mini/genome_data/` to validate the training scripts, data loading, and checkpoint workflow |
+| Cluster training adaptation | Use `scripts/train_slurm.py` to run training in a Slurm/cluster environment |
+| Data preprocessing | Generate the `.bin/.idx` data required by the Byte-Level tokenizer from FASTA/JSON data |
+
+
+# Usage
+
+## 1. Using OneCode
+
+You can try intelligent one-click AI4S programming through the OneCode online environment:
+
+[Try intelligent one-click AI4S programming](https://gitee.com/link?target=https%3A%2F%2Fweb-2069360198568017922-iaaj.ksai.scnet.cn%3A58043%2Fhome)
+
+## 2. Manual Installation and Usage
+
+**Hardware Requirements**
+
+- Running on a GPU or DCU is recommended.
+- A CPU can be used for import checks and small-configuration connectivity validation, but full training and inference will be slow.
+- DCU users need to install DTK in advance. DTK 25.04.2 or later is recommended, or the OneScience-recommended version that matches the current cluster.
+
+### Download the Model Package
+
+```bash
+modelscope download --model OneScience/evo2 --local_dir ./evo2
+cd evo2
+```
+
+### Install the Runtime Environment
+#### DCU Environment
+
+```bash
+# Activate DTK and CONDA first
+conda create -n onescience311 python=3.11 -y
+conda activate onescience311
+# uv installation is supported
+pip install onescience[bio] -i http://mirrors.onescience.ai:3141/pypi/simple/  --trusted-host mirrors.onescience.ai
+```
+
+If the scripts need to access the OneScience source code, set:
+
+```bash
+export ONESCIENCE_ROOT=/path/to/onescience
+```
+
+When run from this directory, the scripts automatically add the project root and `model/` to `sys.path`. You can also manually verify that the local package can be imported:
+
+```bash
+export PYTHONPATH=$(pwd)/model:${PYTHONPATH:-}
+python -c "import evo2; print('evo2 import ok')"
+```
+
+## 3. Quick Start
+
+### Quick Checks
+
+View the entry-point arguments:
+
+```bash
+python scripts/infer.py --help
+python scripts/predict.py --help
+python scripts/train.py --help
+python scripts/train_slurm.py --help
+```
+
+## 4. Data and Weights
+
+The example training data has been placed at:
+
+```text
+data/data_mini/genome_data/
+```
+
+It contains:
+
+* `chr20.fa`, `chr21.fa`, `chr22.fa`, and their compressed versions
+* Merged FASTA: `chr20_21_22.fa`
+* Preprocessed binary data for training, validation, and testing: `preprocessed_data/`
+
+The `dataset_prefix` in `config/genome_data_config.yaml` is a relative path. During actual runs, it should be used together with:
+
+```bash
+--dataset-dir data/data_mini/genome_data
+```
+
+By default, the 7B NeMo checkpoint is placed inside the repository:
+
+```text
+checkpoints/evo2_nemo_7b/
+```
+
+The inference and prediction entry points read this directory by default; training does not load a checkpoint by default. To fine-tune from existing weights or resume training, explicitly pass `--ckpt-dir checkpoints/evo2_nemo_7b` in the training command. You can also use `EVO2_CKPT_DIR` or `--ckpt-dir` to override it with another checkpoint path:
+
+```bash
+export EVO2_CKPT_DIR=/path/to/evo2_nemo_7b
+```
+
+The weight files are located under `/path/to/evo2/checkpoints/evo2_nemo_7b/weights`.
+
+## 5. Prompt-Based Generation Inference
+
+`infer.py` writes results to `--output-file`, but it does not automatically create the parent directory. Create the output directory before the first run:
+
+```bash
+mkdir -p outputs
+```
+
+Minimal example:
+
+```bash
+python scripts/infer.py \
+  --prompt "ATGCGT" \
+  --output-file outputs/evo2_generation.txt
+```
+
+Common parameters:
+
+| Parameter | Default | Description |
+| --- | --- | --- |
+| `--ckpt-dir` | `checkpoints/evo2_nemo_7b` | NeMo checkpoint directory; can be overridden with `EVO2_CKPT_DIR` |
+| `--prompt` | Built-in E. coli classification-label prompt | Input sequence or text prompt |
+| `--max-new-tokens` | `1024` | Maximum number of tokens to generate |
+| `--temperature` | `1.0` | Sampling temperature |
+| `--top-k` | `0` | top-k sampling |
+| `--top-p` | `0.0` | top-p sampling |
+| `--tensor-parallel-size` | `1` | Tensor parallel size |
+| `--output-file` | Empty | Write to a file when specified; otherwise print logs |
+
+## 6. FASTA Prediction
+
+The directory includes an example FASTA:
+
+```text
+data/predict_example.fa
+```
+
+Run prediction:
+
+```bash
+python scripts/predict.py \
+  --fasta data/predict_example.fa \
+  --output-dir outputs/predict
+```
+
+`predict.py` automatically creates `--output-dir`. If `--fasta` is not passed, it reads `data/predict_example.fa` by default; if `--output-dir` is not passed, it writes output to `outputs/predict` by default.
+
+Common parameters:
+
+| Parameter | Default | Description |
+| --- | --- | --- |
+| `--fasta` | `data/predict_example.fa` | Input FASTA file |
+| `--ckpt-dir` | `checkpoints/evo2_nemo_7b` | NeMo checkpoint directory; can be overridden with `EVO2_CKPT_DIR` |
+| `--output-dir` | `outputs/predict` | Prediction result directory |
+| `--batch-size` | `1` | Prediction batch size |
+| `--model-size` | `7b` | Model specification; available values are determined by NeMo `HYENA_MODEL_OPTIONS` |
+| `--output-log-prob-seqs` | Disabled | Output sequence log probability |
+
+`data/data_mini/genome_data/chr20.fa`, `chr21.fa`, and `chr22.fa` are relatively large chromosome-level FASTA files. Direct prediction may consume substantial GPU memory. It is recommended to split them into shorter fragments first, or use a multi-GPU parallel configuration.
+
+## 7. Training
+
+The training entry point requires one of two options: pass `-d/--dataset-config`, or use `--mock-data`. For the built-in example data, `config/genome_data_config.yaml` and `data/data_mini/genome_data` are recommended.
+
+Example for training the 1B architecture from scratch or validating the training workflow:
+
+```bash
+python scripts/train.py \
+  -d config/genome_data_config.yaml \
+  --dataset-dir data/data_mini/genome_data \
+  --model-size 1b \
+  --result-dir results_1b \
+  --devices 8 \
+  --num-nodes 1 \
+  --seq-length 8192 \
+  --micro-batch-size 2 \
+  --lr 0.0001 \
+  --warmup-steps 5 \
+  --max-steps 1000 \
+  --clip-grad 1 \
+  --wd 0.01 \
+  --activation-checkpoint-recompute-num-layers 1 \
+  --val-check-interval 50 \
+  --limit-val-batches 2
+```
+
+This example does not load a checkpoint and is suitable for validating the training workflow when 1B weights are unavailable. To fine-tune from a 1B NeMo checkpoint, additionally pass `--ckpt-dir /path/to/evo2_nemo_1b`.
+
+Example for training the 7B long-context architecture from scratch or validating the training workflow:
+
+```bash
+python scripts/train.py \
+  -d config/genome_data_config.yaml \
+  --dataset-dir data/data_mini/genome_data \
+  --model-size 7b_arc_longcontext \
+  --result-dir results_7b \
+  --devices 8 \
+  --num-nodes 1 \
+  --seq-length 1024 \
+  --micro-batch-size 1 \
+  --lr 0.0001 \
+  --warmup-steps 5 \
+  --max-steps 1000 \
+  --clip-grad 1 \
+  --wd 0.01 \
+  --activation-checkpoint-recompute-num-layers 1 \
+  --val-check-interval 50 \
+  --limit-val-batches 2
+```
+
+This example does not load a checkpoint. If you need to fine-tune from an existing 7B NeMo checkpoint or resume training, additionally pass `--ckpt-dir checkpoints/evo2_nemo_7b` or another checkpoint path.
+
+In a Slurm/cluster environment, replace the entry point with:
+
+```bash
+python scripts/train_slurm.py ...
+```
+
+Common training parameters:
+
+The table below covers the main parameters used in the training examples above and in `scripts/train_evo2_1b.sh` and `scripts/train_evo2_7b.sh`. For more advanced parameters, run `python scripts/train.py --help`.
+
+| Parameter | Default | Description |
+| --- | --- | --- |
+| `-d, --dataset-config` | Required, or use `--mock-data` | Training data configuration YAML |
+| `--mock-data` | Disabled | Do not read real data; use mock data for connectivity testing. Mutually exclusive with `-d/--dataset-config` |
+| `--dataset-dir` | `EVO2_DATASET_DIR` or `data/data_mini/genome_data` | Data root directory |
+| `--ckpt-dir` | Empty | Initial checkpoint directory; pass explicitly when fine-tuning from existing weights or resuming training |
+| `--model-size` | `7b` | Model specification. Common values include `1b`, `7b`, and `7b_arc_longcontext`; use `test` for testing |
+| `--devices` | `1` | Number of devices on a single node |
+| `--num-nodes` | `1` | Number of nodes |
+| `--tensor-parallel-size` | `1` | Tensor parallel size |
+| `--pipeline-model-parallel-size` | `1` | Pipeline model parallel size |
+| `--context-parallel-size` | `1` | Context parallel size |
+| `--sequence-parallel` | Disabled | Enable sequence parallel, usually used together with tensor parallelism |
+| `--seq-length` | `8192` | Training sequence length |
+| `--micro-batch-size` | `1` | Micro batch size |
+| `--global-batch-size` | Automatically inferred | Global batch size |
+| `--grad-acc-batches` | `1` | Number of gradient accumulation batches, used to infer the global batch size |
+| `--lr` | `3e-4` | Learning rate, explicitly set to `0.0001` in the examples |
+| `--min-lr` | `3e-5` | Minimum learning rate of the cosine scheduler |
+| `--warmup-steps` | `2500` | Number of warmup steps, explicitly set to `5` in the examples |
+| `--constant-steps` | `80000` | Number of steps for which the learning rate stays constant |
+| `--max-steps` | `500000` | Number of training steps |
+| `--wd` | `0.01` | Optimizer weight decay |
+| `--clip-grad` | `1.0` | Gradient clipping threshold |
+| `--workers` | `8` | Number of DataLoader workers |
+| `--activation-checkpoint-recompute-num-layers` | Empty | Override the number of activation recomputation layers; explicitly set to `1` in the examples |
+| `--val-check-interval` | Empty | Validation and checkpoint check interval; explicitly set to `50` in the examples |
+| `--limit-val-batches` | `20` | Maximum number of batches to run per validation; explicitly set to `2` in the examples |
+| `--result-dir` | `./results` | Log and result directory |
+| `--experiment-name` | `evo2` | Experiment name, which affects the log directory |
+| `--disable-checkpointing` | Not passed by default; checkpoint callback enabled | Pass this parameter during connectivity tests to disable the checkpoint callback |
+| `--no-save-last-checkpoint` | Save the last checkpoint by default | Disable saving the last checkpoint; often used together with `--disable-checkpointing` for quick tests |
+| `--save-top-k` | `5` | Number of best checkpoints to save |
+| `--ckpt-async-save` | Disabled | Enable asynchronous checkpoint saving |
+
+## 8. Data Preprocessing
+
+The current example training data has already been preprocessed. To process new FASTA or JSON data, use:
+
+```bash
+bash scripts/tools/data_process/preprocess_data_fasta.sh
+bash scripts/tools/data_process/preprocess_data_json.sh
+```
+
+Related configurations:
+
+```text
+config/genome_preprocess_config.yaml
+config/genome_data_config.yaml
+```
+
+# Official OneScience Information
+
+| Platform | OneScience Main Repository | Skills Repository |
+| --- | --- | --- |
+| Gitee | https://gitee.com/onescience-ai/onescience | https://gitee.com/onescience-ai/oneskills |
+| GitHub | https://github.com/onescience-ai/OneScience | https://github.com/onescience-ai/oneskills |
+
+# Citations and License
+
+- Original Evo2 paper: [Genome modelling and design across all domains of life with Evo 2](https://doi.org/10.1038/s41586-026-10176-5).
+- The original Evo2 code uses the Apache License 2.0. See `LICENSE` in this repository. Original license source: [ArcInstitute/evo2 LICENSE](https://github.com/ArcInstitute/evo2/blob/main/LICENSE).
+- The Evo2 7B model weights are sourced from Hugging Face [`arcinstitute/evo2_7b`](https://huggingface.co/arcinstitute/evo2_7b). In this repository, `checkpoints/evo2_nemo_7b` is the converted NeMo checkpoint format. The original weight license is Apache-2.0.
+- The example dataset `data/data_mini/genome_data/` was downloaded and preprocessed from the hg38 `chr20`, `chr21`, and `chr22` chromosome FASTA files provided by the UCSC Genome Browser. It is used only to validate the training and inference workflows. See the data download directory: [UCSC hg38 chromosomes](https://hgdownload.soe.ucsc.edu/goldenpath/hg38/chromosomes/).
+- Use of UCSC hg38 data must comply with the UCSC Genome Browser data usage terms. See: [UCSC Terms of Use](https://genome.ucsc.edu/license/).
+- If you use this repository, the model weights, or generated results in research, it is recommended to cite the original Evo2 paper, the model weight source, the UCSC hg38 data source, and relevant OneScience project information, and to add citations for downstream analysis tools or datasets according to the actual task.

checkpoints/evo2_nemo_7b/context/io.json

@@ -0,0 +1 @@
+{"root": {"type": "ref", "key": "trainer_context_1"}, "objects": {"tuple_1": {"type": {"type": "pyref", "module": "builtins", "name": "tuple"}, "items": [["Index(index=0)", "tensor_model_parallel_size"], ["Index(index=1)", "pipeline_model_parallel_comm_backend"], ["Index(index=2)", "pipeline_model_parallel_size"], ["Index(index=3)", "virtual_pipeline_model_parallel_size"], ["Index(index=4)", "sequence_parallel"], ["Index(index=5)", "context_parallel_size"], ["Index(index=6)", "expert_model_parallel_size"], ["Index(index=7)", "expert_tensor_parallel_size"], ["Index(index=8)", "moe_extended_tp"], ["Index(index=9)", "use_te_rng_tracker"], ["Index(index=10)", "pipeline_dtype"], ["Index(index=11)", "microbatch_group_size_per_vp_stage"], ["Index(index=12)", "num_layers_in_first_pipeline_stage"], ["Index(index=13)", "num_layers_in_last_pipeline_stage"], ["Index(index=14)", "pipeline_model_parallel_layout"], ["Index(index=15)", "account_for_embedding_in_pipeline_split"], ["Index(index=16)", "account_for_loss_in_pipeline_split"]], "metadata": null}, "dict_1": {"type": {"type": "pyref", "module": "builtins", "name": "dict"}, "items": [], "metadata": {"type": {"type": "pyref", "module": "builtins", "name": "tuple"}, "items": [], "metadata": null}}, "dict_2": {"type": {"type": "pyref", "module": "builtins", "name": "dict"}, "items": [], "metadata": {"type": {"type": "pyref", "module": "builtins", "name": "tuple"}, "items": [], "metadata": null}}, "buildable_traverser_metadata_1": {"type": {"type": "pyref", "module": "fiddle._src.config", "name": "BuildableTraverserMetadata"}, "items": [["Attr(name='fn_or_cls')", {"type": "pyref", "module": "nemo.collections.llm.gpt.model.hyena", "name": "Hyena7bConfig"}], ["Attr(name='argument_names')", {"type": "ref", "key": "tuple_1"}], ["Attr(name='argument_tags')", {"type": "ref", "key": "dict_1"}], ["Attr(name='argument_history')", {"type": "ref", "key": "dict_2"}]], "metadata": {"type": "pyref", "module": "fiddle._src.config", "name": "BuildableTraverserMetadata"}}, "hyena7b_config_1": {"type": {"type": "pyref", "module": "fiddle._src.config", "name": "Config"}, "items": [["Attr(name='tensor_model_parallel_size')", {"type": "leaf", "value": 1, "paths": ["<root>.model.config.tensor_model_parallel_size"]}], ["Attr(name='pipeline_model_parallel_comm_backend')", {"type": "leaf", "value": null, "paths": ["<root>.model.config.pipeline_model_parallel_comm_backend"]}], ["Attr(name='pipeline_model_parallel_size')", {"type": "leaf", "value": 1, "paths": ["<root>.model.config.pipeline_model_parallel_size"]}], ["Attr(name='virtual_pipeline_model_parallel_size')", {"type": "leaf", "value": null, "paths": ["<root>.model.config.virtual_pipeline_model_parallel_size"]}], ["Attr(name='sequence_parallel')", {"type": "leaf", "value": false, "paths": ["<root>.model.config.sequence_parallel"]}], ["Attr(name='context_parallel_size')", {"type": "leaf", "value": 1, "paths": ["<root>.model.config.context_parallel_size"]}], ["Attr(name='expert_model_parallel_size')", {"type": "leaf", "value": 1, "paths": ["<root>.model.config.expert_model_parallel_size"]}], ["Attr(name='expert_tensor_parallel_size')", {"type": "leaf", "value": null, "paths": ["<root>.model.config.expert_tensor_parallel_size"]}], ["Attr(name='moe_extended_tp')", {"type": "leaf", "value": false, "paths": ["<root>.model.config.moe_extended_tp"]}], ["Attr(name='use_te_rng_tracker')", {"type": "leaf", "value": false, "paths": ["<root>.model.config.use_te_rng_tracker"]}], ["Attr(name='pipeline_dtype')", {"type": "leaf", "value": null, "paths": ["<root>.model.config.pipeline_dtype"]}], ["Attr(name='microbatch_group_size_per_vp_stage')", {"type": "leaf", "value": 1, "paths": ["<root>.model.config.microbatch_group_size_per_vp_stage"]}], ["Attr(name='num_layers_in_first_pipeline_stage')", {"type": "leaf", "value": null, "paths": ["<root>.model.config.num_layers_in_first_pipeline_stage"]}], ["Attr(name='num_layers_in_last_pipeline_stage')", {"type": "leaf", "value": null, "paths": ["<root>.model.config.num_layers_in_last_pipeline_stage"]}], ["Attr(name='pipeline_model_parallel_layout')", {"type": "leaf", "value": null, "paths": ["<root>.model.config.pipeline_model_parallel_layout"]}], ["Attr(name='account_for_embedding_in_pipeline_split')", {"type": "leaf", "value": false, "paths": ["<root>.model.config.account_for_embedding_in_pipeline_split"]}], ["Attr(name='account_for_loss_in_pipeline_split')", {"type": "leaf", "value": false, "paths": ["<root>.model.config.account_for_loss_in_pipeline_split"]}]], "metadata": {"type": "ref", "key": "buildable_traverser_metadata_1"}, "paths": ["<root>.model.config"]}, "tuple_2": {"type": {"type": "pyref", "module": "builtins", "name": "tuple"}, "items": [["Index(index=0)", "optimizer"], ["Index(index=1)", "lr"], ["Index(index=2)", "min_lr"], ["Index(index=3)", "decoupled_lr"], ["Index(index=4)", "decoupled_min_lr"], ["Index(index=5)", "weight_decay"], ["Index(index=6)", "fp8_recipe"], ["Index(index=7)", "fp16"], ["Index(index=8)", "bf16"], ["Index(index=9)", "reuse_grad_buf_for_mxfp8_param_ag"], ["Index(index=10)", "params_dtype"], ["Index(index=11)", "use_precision_aware_optimizer"], ["Index(index=12)", "store_param_remainders"], ["Index(index=13)", "main_grads_dtype"], ["Index(index=14)", "main_params_dtype"], ["Index(index=15)", "exp_avg_dtype"], ["Index(index=16)", "exp_avg_sq_dtype"], ["Index(index=17)", "loss_scale"], ["Index(index=18)", "initial_loss_scale"], ["Index(index=19)", "min_loss_scale"], ["Index(index=20)", "loss_scale_window"], ["Index(index=21)", "hysteresis"], ["Index(index=22)", "adam_beta1"], ["Index(index=23)", "adam_beta2"], ["Index(index=24)", "adam_eps"], ["Index(index=25)", "sgd_momentum"], ["Index(index=26)", "use_distributed_optimizer"], ["Index(index=27)", "overlap_param_gather_with_optimizer_step"], ["Index(index=28)", "optimizer_cpu_offload"], ["Index(index=29)", "optimizer_offload_fraction"], ["Index(index=30)", "use_torch_optimizer_for_cpu_offload"], ["Index(index=31)", "overlap_cpu_optimizer_d2h_h2d"], ["Index(index=32)", "pin_cpu_grads"], ["Index(index=33)", "pin_cpu_params"], ["Index(index=34)", "clip_grad"], ["Index(index=35)", "log_num_zeros_in_grad"], ["Index(index=36)", "barrier_with_L1_time"], ["Index(index=37)", "timers"], ["Index(index=38)", "config_logger_dir"]], "metadata": null}, "dict_3": {"type": {"type": "pyref", "module": "builtins", "name": "dict"}, "items": [], "metadata": {"type": {"type": "pyref", "module": "builtins", "name": "tuple"}, "items": [], "metadata": null}}, "dict_4": {"type": {"type": "pyref", "module": "builtins", "name": "dict"}, "items": [], "metadata": {"type": {"type": "pyref", "module": "builtins", "name": "tuple"}, "items": [], "metadata": null}}, "buildable_traverser_metadata_2": {"type": {"type": "pyref", "module": "fiddle._src.config", "name": "BuildableTraverserMetadata"}, "items": [["Attr(name='fn_or_cls')", {"type": "pyref", "module": "megatron.core.optimizer.optimizer_config", "name": "OptimizerConfig"}], ["Attr(name='argument_names')", {"type": "ref", "key": "tuple_2"}], ["Attr(name='argument_tags')", {"type": "ref", "key": "dict_3"}], ["Attr(name='argument_history')", {"type": "ref", "key": "dict_4"}]], "metadata": {"type": "pyref", "module": "fiddle._src.config", "name": "BuildableTraverserMetadata"}}, "optimizer_config_1": {"type": {"type": "pyref", "module": "fiddle._src.config", "name": "Config"}, "items": [["Attr(name='optimizer')", {"type": "leaf", "value": "adam", "paths": ["<root>.model.optim.config.optimizer"]}], ["Attr(name='lr')", {"type": "leaf", "value": 0.0001, "paths": ["<root>.model.optim.config.lr"]}], ["Attr(name='min_lr')", {"type": "leaf", "value": null, "paths": ["<root>.model.optim.config.min_lr"]}], ["Attr(name='decoupled_lr')", {"type": "leaf", "value": null, "paths": ["<root>.model.optim.config.decoupled_lr"]}], ["Attr(name='decoupled_min_lr')", {"type": "leaf", "value": null, "paths": ["<root>.model.optim.config.decoupled_min_lr"]}], ["Attr(name='weight_decay')", {"type": "leaf", "value": 0.01, "paths": ["<root>.model.optim.config.weight_decay"]}], ["Attr(name='fp8_recipe')", {"type": "leaf", "value": null, "paths": ["<root>.model.optim.config.fp8_recipe"]}], ["Attr(name='fp16')", {"type": "leaf", "value": false, "paths": ["<root>.model.optim.config.fp16"]}], ["Attr(name='bf16')", {"type": "leaf", "value": false, "paths": ["<root>.model.optim.config.bf16"]}], ["Attr(name='reuse_grad_buf_for_mxfp8_param_ag')", {"type": "leaf", "value": false, "paths": ["<root>.model.optim.config.reuse_grad_buf_for_mxfp8_param_ag"]}], ["Attr(name='params_dtype')", {"type": "pyref", "module": "torch", "name": "float32", "paths": ["<root>.model.optim.config.params_dtype", "<root>.model.optim.config.main_grads_dtype", "<root>.model.optim.config.main_params_dtype", "<root>.model.optim.config.exp_avg_dtype", "<root>.model.optim.config.exp_avg_sq_dtype"]}], ["Attr(name='use_precision_aware_optimizer')", {"type": "leaf", "value": false, "paths": ["<root>.model.optim.config.use_precision_aware_optimizer"]}], ["Attr(name='store_param_remainders')", {"type": "leaf", "value": true, "paths": ["<root>.model.optim.config.store_param_remainders"]}], ["Attr(name='main_grads_dtype')", {"type": "pyref", "module": "torch", "name": "float32", "paths": ["<root>.model.optim.config.params_dtype", "<root>.model.optim.config.main_grads_dtype", "<root>.model.optim.config.main_params_dtype", "<root>.model.optim.config.exp_avg_dtype", "<root>.model.optim.config.exp_avg_sq_dtype"]}], ["Attr(name='main_params_dtype')", {"type": "pyref", "module": "torch", "name": "float32", "paths": ["<root>.model.optim.config.params_dtype", "<root>.model.optim.config.main_grads_dtype", "<root>.model.optim.config.main_params_dtype", "<root>.model.optim.config.exp_avg_dtype", "<root>.model.optim.config.exp_avg_sq_dtype"]}], ["Attr(name='exp_avg_dtype')", {"type": "pyref", "module": "torch", "name": "float32", "paths": ["<root>.model.optim.config.params_dtype", "<root>.model.optim.config.main_grads_dtype", "<root>.model.optim.config.main_params_dtype", "<root>.model.optim.config.exp_avg_dtype", "<root>.model.optim.config.exp_avg_sq_dtype"]}], ["Attr(name='exp_avg_sq_dtype')", {"type": "pyref", "module": "torch", "name": "float32", "paths": ["<root>.model.optim.config.params_dtype", "<root>.model.optim.config.main_grads_dtype", "<root>.model.optim.config.main_params_dtype", "<root>.model.optim.config.exp_avg_dtype", "<root>.model.optim.config.exp_avg_sq_dtype"]}], ["Attr(name='loss_scale')", {"type": "leaf", "value": null, "paths": ["<root>.model.optim.config.loss_scale"]}], ["Attr(name='initial_loss_scale')", {"type": "leaf", "value": 4294967296, "paths": ["<root>.model.optim.config.initial_loss_scale"]}], ["Attr(name='min_loss_scale')", {"type": "leaf", "value": 1.0, "paths": ["<root>.model.optim.config.min_loss_scale"]}], ["Attr(name='loss_scale_window')", {"type": "leaf", "value": 1000, "paths": ["<root>.model.optim.config.loss_scale_window"]}], ["Attr(name='hysteresis')", {"type": "leaf", "value": 2, "paths": ["<root>.model.optim.config.hysteresis"]}], ["Attr(name='adam_beta1')", {"type": "leaf", "value": 0.9, "paths": ["<root>.model.optim.config.adam_beta1"]}], ["Attr(name='adam_beta2')", {"type": "leaf", "value": 0.999, "paths": ["<root>.model.optim.config.adam_beta2"]}], ["Attr(name='adam_eps')", {"type": "leaf", "value": 1e-08, "paths": ["<root>.model.optim.config.adam_eps"]}], ["Attr(name='sgd_momentum')", {"type": "leaf", "value": 0.9, "paths": ["<root>.model.optim.config.sgd_momentum"]}], ["Attr(name='use_distributed_optimizer')", {"type": "leaf", "value": true, "paths": ["<root>.model.optim.config.use_distributed_optimizer"]}], ["Attr(name='overlap_param_gather_with_optimizer_step')", {"type": "leaf", "value": false, "paths": ["<root>.model.optim.config.overlap_param_gather_with_optimizer_step"]}], ["Attr(name='optimizer_cpu_offload')", {"type": "leaf", "value": false, "paths": ["<root>.model.optim.config.optimizer_cpu_offload"]}], ["Attr(name='optimizer_offload_fraction')", {"type": "leaf", "value": 0.0, "paths": ["<root>.model.optim.config.optimizer_offload_fraction"]}], ["Attr(name='use_torch_optimizer_for_cpu_offload')", {"type": "leaf", "value": false, "paths": ["<root>.model.optim.config.use_torch_optimizer_for_cpu_offload"]}], ["Attr(name='overlap_cpu_optimizer_d2h_h2d')", {"type": "leaf", "value": false, "paths": ["<root>.model.optim.config.overlap_cpu_optimizer_d2h_h2d"]}], ["Attr(name='pin_cpu_grads')", {"type": "leaf", "value": true, "paths": ["<root>.model.optim.config.pin_cpu_grads"]}], ["Attr(name='pin_cpu_params')", {"type": "leaf", "value": true, "paths": ["<root>.model.optim.config.pin_cpu_params"]}], ["Attr(name='clip_grad')", {"type": "leaf", "value": 1.0, "paths": ["<root>.model.optim.config.clip_grad"]}], ["Attr(name='log_num_zeros_in_grad')", {"type": "leaf", "value": false, "paths": ["<root>.model.optim.config.log_num_zeros_in_grad"]}], ["Attr(name='barrier_with_L1_time')", {"type": "leaf", "value": false, "paths": ["<root>.model.optim.config.barrier_with_L1_time"]}], ["Attr(name='timers')", {"type": "leaf", "value": null, "paths": ["<root>.model.optim.config.timers"]}], ["Attr(name='config_logger_dir')", {"type": "leaf", "value": "", "paths": ["<root>.model.optim.config.config_logger_dir"]}]], "metadata": {"type": "ref", "key": "buildable_traverser_metadata_2"}, "paths": ["<root>.model.optim.config"]}, "tuple_3": {"type": {"type": "pyref", "module": "builtins", "name": "tuple"}, "items": [["Index(index=0)", "config"]], "metadata": null}, "dict_5": {"type": {"type": "pyref", "module": "builtins", "name": "dict"}, "items": [], "metadata": {"type": {"type": "pyref", "module": "builtins", "name": "tuple"}, "items": [], "metadata": null}}, "dict_6": {"type": {"type": "pyref", "module": "builtins", "name": "dict"}, "items": [], "metadata": {"type": {"type": "pyref", "module": "builtins", "name": "tuple"}, "items": [], "metadata": null}}, "buildable_traverser_metadata_3": {"type": {"type": "pyref", "module": "fiddle._src.config", "name": "BuildableTraverserMetadata"}, "items": [["Attr(name='fn_or_cls')", {"type": "pyref", "module": "nemo.lightning.pytorch.optim.megatron", "name": "MegatronOptimizerModule"}], ["Attr(name='argument_names')", {"type": "ref", "key": "tuple_3"}], ["Attr(name='argument_tags')", {"type": "ref", "key": "dict_5"}], ["Attr(name='argument_history')", {"type": "ref", "key": "dict_6"}]], "metadata": {"type": "pyref", "module": "fiddle._src.config", "name": "BuildableTraverserMetadata"}}, "megatron_optimizer_module_1": {"type": {"type": "pyref", "module": "fiddle._src.config", "name": "Config"}, "items": [["Attr(name='config')", {"type": "ref", "key": "optimizer_config_1"}]], "metadata": {"type": "ref", "key": "buildable_traverser_metadata_3"}, "paths": ["<root>.model.optim"]}, "dict_7": {"type": {"type": "pyref", "module": "builtins", "name": "dict"}, "items": [], "metadata": {"type": {"type": "pyref", "module": "builtins", "name": "tuple"}, "items": [], "metadata": null}, "paths": ["<root>.model.tokenizer.special_tokens"]}, "tuple_4": {"type": {"type": "pyref", "module": "builtins", "name": "tuple"}, "items": [["Index(index=0)", "special_tokens"]], "metadata": null}, "dict_8": {"type": {"type": "pyref", "module": "builtins", "name": "dict"}, "items": [], "metadata": {"type": {"type": "pyref", "module": "builtins", "name": "tuple"}, "items": [], "metadata": null}}, "dict_9": {"type": {"type": "pyref", "module": "builtins", "name": "dict"}, "items": [], "metadata": {"type": {"type": "pyref", "module": "builtins", "name": "tuple"}, "items": [], "metadata": null}}, "buildable_traverser_metadata_4": {"type": {"type": "pyref", "module": "fiddle._src.config", "name": "BuildableTraverserMetadata"}, "items": [["Attr(name='fn_or_cls')", {"type": "pyref", "module": "nemo.collections.common.tokenizers.bytelevel_tokenizers", "name": "ByteLevelTokenizer"}], ["Attr(name='argument_names')", {"type": "ref", "key": "tuple_4"}], ["Attr(name='argument_tags')", {"type": "ref", "key": "dict_8"}], ["Attr(name='argument_history')", {"type": "ref", "key": "dict_9"}]], "metadata": {"type": "pyref", "module": "fiddle._src.config", "name": "BuildableTraverserMetadata"}}, "byte_level_tokenizer_1": {"type": {"type": "pyref", "module": "fiddle._src.config", "name": "Config"}, "items": [["Attr(name='special_tokens')", {"type": "ref", "key": "dict_7"}]], "metadata": {"type": "ref", "key": "buildable_traverser_metadata_4"}, "paths": ["<root>.model.tokenizer"]}, "tuple_5": {"type": {"type": "pyref", "module": "builtins", "name": "tuple"}, "items": [["Index(index=0)", "config"], ["Index(index=1)", "optim"], ["Index(index=2)", "tokenizer"]], "metadata": null}, "dict_10": {"type": {"type": "pyref", "module": "builtins", "name": "dict"}, "items": [], "metadata": {"type": {"type": "pyref", "module": "builtins", "name": "tuple"}, "items": [], "metadata": null}}, "dict_11": {"type": {"type": "pyref", "module": "builtins", "name": "dict"}, "items": [], "metadata": {"type": {"type": "pyref", "module": "builtins", "name": "tuple"}, "items": [], "metadata": null}}, "buildable_traverser_metadata_5": {"type": {"type": "pyref", "module": "fiddle._src.config", "name": "BuildableTraverserMetadata"}, "items": [["Attr(name='fn_or_cls')", {"type": "pyref", "module": "nemo.collections.llm.gpt.model.hyena", "name": "HyenaModel"}], ["Attr(name='argument_names')", {"type": "ref", "key": "tuple_5"}], ["Attr(name='argument_tags')", {"type": "ref", "key": "dict_10"}], ["Attr(name='argument_history')", {"type": "ref", "key": "dict_11"}]], "metadata": {"type": "pyref", "module": "fiddle._src.config", "name": "BuildableTraverserMetadata"}}, "hyena_model_1": {"type": {"type": "pyref", "module": "fiddle._src.config", "name": "Config"}, "items": [["Attr(name='config')", {"type": "ref", "key": "hyena7b_config_1"}], ["Attr(name='optim')", {"type": "ref", "key": "megatron_optimizer_module_1"}], ["Attr(name='tokenizer')", {"type": "ref", "key": "byte_level_tokenizer_1"}]], "metadata": {"type": "ref", "key": "buildable_traverser_metadata_5"}, "paths": ["<root>.model"]}, "tuple_6": {"type": {"type": "pyref", "module": "builtins", "name": "tuple"}, "items": [["Index(index=0)", "always_save_context"]], "metadata": null}, "dict_12": {"type": {"type": "pyref", "module": "builtins", "name": "dict"}, "items": [["Key(key='always_save_context')", {"type": "leaf", "value": true, "paths": ["<root>.trainer.strategy.kwargs['always_save_context']"]}]], "metadata": {"type": "ref", "key": "tuple_6"}, "paths": ["<root>.trainer.strategy.kwargs"]}, "tuple_7": {"type": {"type": "pyref", "module": "builtins", "name": "tuple"}, "items": [["Index(index=0)", "ckpt_save_optimizer"], ["Index(index=1)", "save_ckpt_format"], ["Index(index=2)", "ckpt_async_save"], ["Index(index=3)", "kwargs"]], "metadata": null}, "dict_13": {"type": {"type": "pyref", "module": "builtins", "name": "dict"}, "items": [], "metadata": {"type": {"type": "pyref", "module": "builtins", "name": "tuple"}, "items": [], "metadata": null}}, "dict_14": {"type": {"type": "pyref", "module": "builtins", "name": "dict"}, "items": [], "metadata": {"type": {"type": "pyref", "module": "builtins", "name": "tuple"}, "items": [], "metadata": null}}, "buildable_traverser_metadata_6": {"type": {"type": "pyref", "module": "fiddle._src.config", "name": "BuildableTraverserMetadata"}, "items": [["Attr(name='fn_or_cls')", {"type": "pyref", "module": "nemo.lightning.pytorch.strategies.megatron_strategy", "name": "MegatronStrategy"}], ["Attr(name='argument_names')", {"type": "ref", "key": "tuple_7"}], ["Attr(name='argument_tags')", {"type": "ref", "key": "dict_13"}], ["Attr(name='argument_history')", {"type": "ref", "key": "dict_14"}]], "metadata": {"type": "pyref", "module": "fiddle._src.config", "name": "BuildableTraverserMetadata"}}, "megatron_strategy_1": {"type": {"type": "pyref", "module": "fiddle._src.config", "name": "Config"}, "items": [["Attr(name='ckpt_save_optimizer')", {"type": "leaf", "value": false, "paths": ["<root>.trainer.strategy.ckpt_save_optimizer"]}], ["Attr(name='save_ckpt_format')", {"type": "leaf", "value": "torch_dist", "paths": ["<root>.trainer.strategy.save_ckpt_format"]}], ["Attr(name='ckpt_async_save')", {"type": "leaf", "value": false, "paths": ["<root>.trainer.strategy.ckpt_async_save"]}], ["Attr(name='kwargs')", {"type": "ref", "key": "dict_12"}]], "metadata": {"type": "ref", "key": "buildable_traverser_metadata_6"}, "paths": ["<root>.trainer.strategy"]}, "tuple_8": {"type": {"type": "pyref", "module": "builtins", "name": "tuple"}, "items": [["Index(index=0)", "accelerator"], ["Index(index=1)", "strategy"], ["Index(index=2)", "devices"]], "metadata": null}, "dict_15": {"type": {"type": "pyref", "module": "builtins", "name": "dict"}, "items": [], "metadata": {"type": {"type": "pyref", "module": "builtins", "name": "tuple"}, "items": [], "metadata": null}}, "dict_16": {"type": {"type": "pyref", "module": "builtins", "name": "dict"}, "items": [], "metadata": {"type": {"type": "pyref", "module": "builtins", "name": "tuple"}, "items": [], "metadata": null}}, "buildable_traverser_metadata_7": {"type": {"type": "pyref", "module": "fiddle._src.config", "name": "BuildableTraverserMetadata"}, "items": [["Attr(name='fn_or_cls')", {"type": "pyref", "module": "nemo.lightning.pytorch.trainer", "name": "Trainer"}], ["Attr(name='argument_names')", {"type": "ref", "key": "tuple_8"}], ["Attr(name='argument_tags')", {"type": "ref", "key": "dict_15"}], ["Attr(name='argument_history')", {"type": "ref", "key": "dict_16"}]], "metadata": {"type": "pyref", "module": "fiddle._src.config", "name": "BuildableTraverserMetadata"}}, "trainer_1": {"type": {"type": "pyref", "module": "fiddle._src.config", "name": "Config"}, "items": [["Attr(name='accelerator')", {"type": "leaf", "value": "cpu", "paths": ["<root>.trainer.accelerator"]}], ["Attr(name='strategy')", {"type": "ref", "key": "megatron_strategy_1"}], ["Attr(name='devices')", {"type": "leaf", "value": 1, "paths": ["<root>.trainer.devices"]}]], "metadata": {"type": "ref", "key": "buildable_traverser_metadata_7"}, "paths": ["<root>.trainer"]}, "dict_17": {"type": {"type": "pyref", "module": "builtins", "name": "dict"}, "items": [], "metadata": {"type": {"type": "pyref", "module": "builtins", "name": "tuple"}, "items": [], "metadata": null}, "paths": ["<root>.extra"]}, "tuple_9": {"type": {"type": "pyref", "module": "builtins", "name": "tuple"}, "items": [["Index(index=0)", "model"], ["Index(index=1)", "trainer"], ["Index(index=2)", "extra"]], "metadata": null}, "dict_18": {"type": {"type": "pyref", "module": "builtins", "name": "dict"}, "items": [], "metadata": {"type": {"type": "pyref", "module": "builtins", "name": "tuple"}, "items": [], "metadata": null}}, "dict_19": {"type": {"type": "pyref", "module": "builtins", "name": "dict"}, "items": [], "metadata": {"type": {"type": "pyref", "module": "builtins", "name": "tuple"}, "items": [], "metadata": null}}, "buildable_traverser_metadata_8": {"type": {"type": "pyref", "module": "fiddle._src.config", "name": "BuildableTraverserMetadata"}, "items": [["Attr(name='fn_or_cls')", {"type": "pyref", "module": "nemo.lightning.io.pl", "name": "TrainerContext"}], ["Attr(name='argument_names')", {"type": "ref", "key": "tuple_9"}], ["Attr(name='argument_tags')", {"type": "ref", "key": "dict_18"}], ["Attr(name='argument_history')", {"type": "ref", "key": "dict_19"}]], "metadata": {"type": "pyref", "module": "fiddle._src.config", "name": "BuildableTraverserMetadata"}}, "trainer_context_1": {"type": {"type": "pyref", "module": "fiddle._src.config", "name": "Config"}, "items": [["Attr(name='model')", {"type": "ref", "key": "hyena_model_1"}], ["Attr(name='trainer')", {"type": "ref", "key": "trainer_1"}], ["Attr(name='extra')", {"type": "ref", "key": "dict_17"}]], "metadata": {"type": "ref", "key": "buildable_traverser_metadata_8"}, "paths": ["<root>"]}}, "refcounts": {"tuple_1": 1, "dict_1": 1, "dict_2": 1, "buildable_traverser_metadata_1": 1, "hyena7b_config_1": 1, "tuple_2": 1, "dict_3": 1, "dict_4": 1, "buildable_traverser_metadata_2": 1, "optimizer_config_1": 1, "tuple_3": 1, "dict_5": 1, "dict_6": 1, "buildable_traverser_metadata_3": 1, "megatron_optimizer_module_1": 1, "dict_7": 1, "tuple_4": 1, "dict_8": 1, "dict_9": 1, "buildable_traverser_metadata_4": 1, "byte_level_tokenizer_1": 1, "tuple_5": 1, "dict_10": 1, "dict_11": 1, "buildable_traverser_metadata_5": 1, "hyena_model_1": 1, "tuple_6": 1, "dict_12": 1, "tuple_7": 1, "dict_13": 1, "dict_14": 1, "buildable_traverser_metadata_6": 1, "megatron_strategy_1": 1, "tuple_8": 1, "dict_15": 1, "dict_16": 1, "buildable_traverser_metadata_7": 1, "trainer_1": 1, "dict_17": 1, "tuple_9": 1, "dict_18": 1, "dict_19": 1, "buildable_traverser_metadata_8": 1, "trainer_context_1": 1}, "version": "0.0.1"}

checkpoints/evo2_nemo_7b/context/model.yaml

@@ -0,0 +1,302 @@
+_target_: nemo.collections.llm.gpt.model.hyena.HyenaModel
+config:
+  _cpu_offloading_context: null
+  _target_: nemo.collections.llm.gpt.model.hyena.Hyena7bConfig
+  account_for_embedding_in_pipeline_split: false
+  account_for_loss_in_pipeline_split: false
+  activation_func:
+    _call_: false
+    _target_: torch._C._nn.gelu
+  activation_func_fp8_input_store: false
+  add_attn_proj_bias: true
+  add_bias_linear: false
+  add_bias_output: false
+  add_qkv_bias: false
+  apply_query_key_layer_scaling: false
+  apply_residual_connection_post_layernorm: false
+  apply_rope_fusion: true
+  async_tensor_model_parallel_allreduce: false
+  attention_backend:
+    _call_: true
+    _target_: megatron.core.transformer.enums.AttnBackend
+  attention_dropout: 0.0
+  attention_softmax_in_fp32: true
+  autocast_dtype: null
+  barrier_with_L1_time: true
+  batch_p2p_comm: true
+  batch_p2p_sync: true
+  bf16: true
+  bias_activation_fusion: true
+  bias_dropout_add_fusion: true
+  bias_dropout_fusion: false
+  calculate_per_token_loss: false
+  clone_scatter_output_in_embedding: true
+  config_logger_dir: ''
+  context_parallel_size: 1
+  cp_comm_type: null
+  cpu_offloading: false
+  cpu_offloading_activations: true
+  cpu_offloading_num_layers: 0
+  cpu_offloading_weights: true
+  cross_entropy_fusion_impl: native
+  cross_entropy_loss_fusion: false
+  cuda_graph_retain_backward_graph: false
+  cuda_graph_scope: full
+  cuda_graph_use_single_mempool: false
+  cuda_graph_warmup_steps: 3
+  data_step_fn:
+    _call_: false
+    _target_: nemo.collections.llm.gpt.model.base.gpt_data_step
+  deallocate_pipeline_outputs: false
+  defer_embedding_wgrad_compute: false
+  delay_wgrad_compute: false
+  deterministic_mode: false
+  disable_bf16_reduced_precision_matmul: false
+  disable_parameter_transpose_cache: false
+  distribute_saved_activations: null
+  embedding_init_method: null
+  embedding_init_method_std: null
+  enable_autocast: false
+  enable_cuda_graph: false
+  expert_model_parallel_size: 1
+  expert_tensor_parallel_size: null
+  external_cuda_graph: false
+  ffn_hidden_size: 11008
+  finalize_model_grads_func: null
+  first_last_layers_bf16: false
+  flash_decode: false
+  forward_step_fn:
+    _call_: false
+    _target_: nemo.collections.llm.gpt.model.hyena.hyena_forward_step
+  fp16: false
+  fp16_lm_cross_entropy: false
+  fp32_residual_connection: true
+  fp8: null
+  fp8_amax_compute_algo: most_recent
+  fp8_amax_history_len: 1
+  fp8_dot_product_attention: false
+  fp8_interval: 1
+  fp8_margin: 0
+  fp8_multi_head_attention: false
+  fp8_param: false
+  fp8_recipe: delayed
+  fp8_wgrad: true
+  gated_linear_unit: true
+  get_attention_mask_from_fusion: false
+  grad_scale_func: null
+  grad_sync_func: null
+  gradient_accumulation_fusion: false
+  hetereogenous_dist_checkpoint: false
+  heterogeneous_block_specs: false
+  hidden_dropout: 0.0
+  hidden_size: 4096
+  hierarchical_context_parallel_sizes: null
+  hybrid_attention_ratio: 0.0
+  hybrid_mlp_ratio: 0.0
+  hybrid_override_pattern: SDH*SDHSDH*SDHSDH*SDHSDH*SDHSDH*
+  hyena_filter_no_wd: true
+  hyena_init_method: small_init
+  hyena_output_layer_init_method: wang_init
+  inference_rng_tracker: false
+  init_method: null
+  init_method_std: 0.02
+  init_model_with_meta_device: false
+  is_hybrid_model: false
+  kv_channels: null
+  layernorm_epsilon: 1.0e-06
+  layernorm_zero_centered_gamma: false
+  make_vocab_size_divisible_by: 8
+  mamba_head_dim: 64
+  mamba_num_groups: 8
+  mamba_num_heads: null
+  mamba_state_dim: 128
+  mapping_type: base
+  masked_softmax_fusion: false
+  memory_efficient_layer_norm: false
+  microbatch_group_size_per_vp_stage: 1
+  mlp_chunks_for_prefill: 1
+  moe_apply_probs_on_input: false
+  moe_aux_loss_coeff: 0
+  moe_deepep_num_sms: 20
+  moe_enable_deepep: false
+  moe_expert_capacity_factor: null
+  moe_extended_tp: false
+  moe_ffn_hidden_size: null
+  moe_grouped_gemm: false
+  moe_input_jitter_eps: null
+  moe_layer_freq: 1
+  moe_layer_recompute: false
+  moe_pad_expert_input_to_capacity: false
+  moe_per_layer_logging: false
+  moe_permute_fusion: false
+  moe_router_bias_update_rate: 0.001
+  moe_router_dtype: null
+  moe_router_enable_expert_bias: false
+  moe_router_force_load_balancing: false
+  moe_router_group_topk: null
+  moe_router_load_balancing_type: aux_loss
+  moe_router_num_groups: null
+  moe_router_padding_for_fp8: false
+  moe_router_pre_softmax: false
+  moe_router_score_function: softmax
+  moe_router_topk: 2
+  moe_router_topk_limited_devices: null
+  moe_router_topk_scaling_factor: null
+  moe_shared_expert_intermediate_size: null
+  moe_shared_expert_overlap: false
+  moe_token_dispatcher_type: allgather
+  moe_token_drop_policy: probs
+  moe_token_dropping: false
+  moe_use_legacy_grouped_gemm: false
+  moe_z_loss_coeff: null
+  mrope_section: null
+  mtp_loss_scaling_factor: null
+  mtp_num_layers: null
+  multi_latent_attention: false
+  no_rope_freq: null
+  no_sync_func: null
+  normalization: RMSNorm
+  num_attention_heads: 32
+  num_groups_hyena: 4096
+  num_groups_hyena_medium: 256
+  num_groups_hyena_short: 256
+  num_layers: 32
+  num_layers_at_end_in_bf16: 1
+  num_layers_at_start_in_bf16: 1
+  num_layers_in_first_pipeline_stage: null
+  num_layers_in_last_pipeline_stage: null
+  num_microbatches_with_partial_activation_checkpoints: null
+  num_moe_experts: null
+  num_query_groups: null
+  output_layer_init_method: null
+  overlap_p2p_comm: false
+  overlap_p2p_comm_warmup_flush: false
+  parallel_output: true
+  param_sync_func: null
+  params_dtype:
+    _call_: false
+    _target_: torch.bfloat16
+  perform_initialization: true
+  persist_layer_norm: false
+  pipeline_dtype: null
+  pipeline_model_parallel_comm_backend: null
+  pipeline_model_parallel_layout: null
+  pipeline_model_parallel_size: 1
+  pipeline_model_parallel_split_rank: null
+  position_embedding_type: rope
+  post_process: true
+  pre_process: true
+  qk_layernorm: false
+  quant_recipe: null
+  recompute_granularity: full
+  recompute_method: uniform
+  recompute_modules: null
+  recompute_num_layers: 4
+  remove_activation_post_first_layer: true
+  rotary_base: 10000
+  rotary_interleaved: false
+  rotary_percent: 1.0
+  seq_len_interpolation_factor: null
+  seq_length: 8192
+  sequence_parallel: false
+  softmax_scale: null
+  symmetric_ar_type: null
+  tensor_model_parallel_size: 1
+  test_mode: false
+  timers: null
+  to_upper: normalized_weighted
+  tokenizer_library: byte-level
+  tokenizer_model_path: null
+  tp_comm_atomic_ag: false
+  tp_comm_atomic_rs: false
+  tp_comm_bootstrap_backend: nccl
+  tp_comm_bulk_dgrad: true
+  tp_comm_bulk_wgrad: true
+  tp_comm_overlap: false
+  tp_comm_overlap_ag: true
+  tp_comm_overlap_disable_fc1: false
+  tp_comm_overlap_disable_qkv: false
+  tp_comm_overlap_rs: true
+  tp_comm_overlap_rs_dgrad: false
+  tp_comm_split_ag: true
+  tp_comm_split_rs: true
+  tp_only_amax_red: false
+  use_b2b_causal_conv1d: false
+  use_cpu_initialization: false
+  use_kitchen: false
+  use_mamba_mem_eff_path: true
+  use_ring_exchange_p2p: false
+  use_short_conv_bias: false
+  use_te: true
+  use_te_rng_tracker: false
+  variable_seq_lengths: false
+  virtual_pipeline_model_parallel_size: null
+  vortex_style_fp8: false
+  wgrad_deferral_limit: 0
+  window_size: null
+model_context_managers: []
+model_transform: null
+optim:
+  _target_: nemo.lightning.pytorch.optim.megatron.MegatronOptimizerModule
+  config:
+    _target_: megatron.core.optimizer.optimizer_config.OptimizerConfig
+    adam_beta1: 0.9
+    adam_beta2: 0.999
+    adam_eps: 1.0e-08
+    barrier_with_L1_time: false
+    bf16: false
+    clip_grad: 1.0
+    config_logger_dir: ''
+    decoupled_lr: null
+    decoupled_min_lr: null
+    exp_avg_dtype:
+      _call_: false
+      _target_: torch.float32
+    exp_avg_sq_dtype:
+      _call_: false
+      _target_: torch.float32
+    fp16: false
+    fp8_recipe: null
+    hysteresis: 2
+    initial_loss_scale: 4294967296
+    log_num_zeros_in_grad: false
+    loss_scale: null
+    loss_scale_window: 1000
+    lr: 0.0001
+    main_grads_dtype:
+      _call_: false
+      _target_: torch.float32
+    main_params_dtype:
+      _call_: false
+      _target_: torch.float32
+    min_loss_scale: 1.0
+    min_lr: null
+    optimizer: adam
+    optimizer_cpu_offload: false
+    optimizer_offload_fraction: 0.0
+    overlap_cpu_optimizer_d2h_h2d: false
+    overlap_param_gather_with_optimizer_step: false
+    params_dtype:
+      _call_: false
+      _target_: torch.float32
+    pin_cpu_grads: true
+    pin_cpu_params: true
+    reuse_grad_buf_for_mxfp8_param_ag: false
+    sgd_momentum: 0.9
+    store_param_remainders: true
+    timers: null
+    use_distributed_optimizer: true
+    use_precision_aware_optimizer: false
+    use_torch_optimizer_for_cpu_offload: false
+    weight_decay: 0.01
+  lr_mult: 1.0
+  lr_scheduler: null
+  no_weight_decay_cond: null
+  scale_lr_cond: null
+tokenizer:
+  _bos_id: null
+  _eos_id: 0
+  _pad_id: 1
+  _target_: nemo.collections.common.tokenizers.bytelevel_tokenizers.ByteLevelTokenizer
+  special_tokens: {}
+  vocab_size: 512

checkpoints/evo2_nemo_7b/weights/.metadata

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9136c78b4ec769bcbcaae649bbb9fd2b8f9d563b1547279a77c5eb09fd27bd36
+size 180057

checkpoints/evo2_nemo_7b/weights/__0_0.distcp

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d0adb229a170471e48f3526b7c52e31d01f41b617f7deeabc06bfbf37d15928d
+size 6482259480

checkpoints/evo2_nemo_7b/weights/__0_1.distcp

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:35c492de6332f4e423f26186c76115ee43ecdc45eb1289b006d40226c520c60c
+size 6482293876

checkpoints/evo2_nemo_7b/weights/common.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:74760670a728a4aed7567efcb15c1572ce7388cf389dbf5102c55569ea31498a
+size 2839

checkpoints/evo2_nemo_7b/weights/metadata.json

@@ -0,0 +1 @@
+{"sharded_backend": "torch_dist", "sharded_backend_version": 1, "common_backend": "torch", "common_backend_version": 1}

config/config.yaml

@@ -0,0 +1,13 @@
+model:
+  name: Evo2
+  package_path: ../model/evo2
+  base_dependency: OneScience
+runtime:
+  pythonpath: ../model
+  onescience_root_env: ONESCIENCE_ROOT
+train:
+  entry: ../scripts/train.py
+  config: ./opengenome2.yml
+inference:
+  entry: ../scripts/infer.py
+  checkpoint_dir: ../checkpoints

config/genome_data_config.yaml

@@ -0,0 +1,9 @@
+- dataset_prefix: ./preprocessed_data/chr20_21_22_uint8_distinct_byte-level_train
+  dataset_split: train
+  dataset_weight: 1.0
+- dataset_prefix: ./preprocessed_data/chr20_21_22_uint8_distinct_byte-level_val
+  dataset_split: validation
+  dataset_weight: 1.0
+- dataset_prefix: ./preprocessed_data/chr20_21_22_uint8_distinct_byte-level_test
+  dataset_split: test
+  dataset_weight: 1.0

config/genome_preprocess_config.yaml

@@ -0,0 +1,31 @@
+
+- datapaths: ["chr20_21_22.fa"]
+  output_dir: "./preprocessed_data"
+  output_prefix: chr20_21_22_uint8_distinct
+  train_split: 0.9
+  valid_split: 0.05
+  test_split: 0.05
+  overwrite: True
+  embed_reverse_complement: true
+  random_reverse_complement: 0.0
+  random_lineage_dropout: 0.0
+  include_sequence_id: false
+  transcribe: "back_transcribe"
+  force_uppercase: false
+  indexed_dataset_dtype: "uint8"
+  tokenizer_type: "Byte-Level"
+  vocab_file: null
+  vocab_size: null
+  merges_file: null
+  pretrained_tokenizer_model: null
+  special_tokens: null
+  fast_hf_tokenizer: true
+  append_eod: true
+  enforce_sample_length: null
+  ftfy: false
+  workers: 1
+  preproc_concurrency: 100000
+  chunksize: 25
+  drop_empty_sequences: true
+  nnn_filter: false  # If you split your fasta on NNN (in human these are contigs), then you should set this to true.
+  seed: 12342  # Not relevant because we are not using random reverse complement or lineage dropout.

config/opengenome2.yml

@@ -0,0 +1,177 @@
+{
+  "train-data-paths": [
+    "/datasets/evo2/metagenomics/pretraining_data_metagenomics/data_metagenomics_train_text_CharLevelTokenizer_document",
+    "/datasets/evo2/gtdb_imgpr/pretraining_data_gtdb_imgpr/data_gtdb_imgpr_train_text_CharLevelTokenizer_document",
+    "/datasets/evo2/imgvr/pretraining_data_imgvr/data_imgvr_train_text_CharLevelTokenizer_document",
+    "/datasets/evo2/hg38/pretraining_data_hg38/data_hg38_all_text_CharLevelTokenizer_document",
+    "/datasets/evo2/ncrna/pretraining_data_ncrna/data_ncrna_train_text_CharLevelTokenizer_document",
+    "/datasets/evo2/mrna_splice/pretraining_data_mrna_splice/data_mrna_splice_train_text_CharLevelTokenizer_document",
+    "/datasets/evo2/promoters/pretraining_data_promoters/data_promoters_train_text_CharLevelTokenizer_document",
+    "/datasets/evo2/eukaryote_ncbi/pretraining_data/data_train_batch1_animalia_text_CharLevelTokenizer_document",
+    "/datasets/evo2/eukaryote_ncbi/pretraining_data/data_train_batch2_animalia_text_CharLevelTokenizer_document",
+    "/datasets/evo2/eukaryote_ncbi/pretraining_data/data_train_batch3_animalia_text_CharLevelTokenizer_document",
+    "/datasets/evo2/eukaryote_ncbi/pretraining_data/data_train_batch4_animalia_text_CharLevelTokenizer_document",
+    "/datasets/evo2/eukaryote_ncbi/pretraining_data/data_train_batch5_animalia_text_CharLevelTokenizer_document",
+    "/datasets/evo2/eukaryote_ncbi/pretraining_data/data_train_batch6_animalia_text_CharLevelTokenizer_document",
+    "/datasets/evo2/eukaryote_ncbi/pretraining_data/data_train_batch7_animalia_text_CharLevelTokenizer_document",
+    "/datasets/evo2/eukaryote_ncbi/pretraining_data/data_train_batch8_animalia_text_CharLevelTokenizer_document",
+    "/datasets/evo2/eukaryote_ncbi/pretraining_data/data_train_batch1_fungi_text_CharLevelTokenizer_document",
+    "/datasets/evo2/eukaryote_ncbi/pretraining_data/data_train_batch2_fungi_text_CharLevelTokenizer_document",
+    "/datasets/evo2/eukaryote_ncbi/pretraining_data/data_train_batch3_fungi_text_CharLevelTokenizer_document",
+    "/datasets/evo2/eukaryote_ncbi/pretraining_data/data_train_batch4_fungi_text_CharLevelTokenizer_document",
+    "/datasets/evo2/eukaryote_ncbi/pretraining_data/data_train_batch5_fungi_text_CharLevelTokenizer_document",
+    "/datasets/evo2/eukaryote_ncbi/pretraining_data/data_train_batch6_fungi_text_CharLevelTokenizer_document",
+    "/datasets/evo2/eukaryote_ncbi/pretraining_data/data_train_batch7_fungi_text_CharLevelTokenizer_document",
+    "/datasets/evo2/eukaryote_ncbi/pretraining_data/data_train_batch8_fungi_text_CharLevelTokenizer_document",
+    "/datasets/evo2/eukaryote_ncbi/pretraining_data/data_train_batch1_plantae_text_CharLevelTokenizer_document",
+    "/datasets/evo2/eukaryote_ncbi/pretraining_data/data_train_batch2_plantae_text_CharLevelTokenizer_document",
+    "/datasets/evo2/eukaryote_ncbi/pretraining_data/data_train_batch3_plantae_text_CharLevelTokenizer_document",
+    "/datasets/evo2/eukaryote_ncbi/pretraining_data/data_train_batch4_plantae_text_CharLevelTokenizer_document",
+    "/datasets/evo2/eukaryote_ncbi/pretraining_data/data_train_batch5_plantae_text_CharLevelTokenizer_document",
+    "/datasets/evo2/eukaryote_ncbi/pretraining_data/data_train_batch6_plantae_text_CharLevelTokenizer_document",
+    "/datasets/evo2/eukaryote_ncbi/pretraining_data/data_train_batch7_plantae_text_CharLevelTokenizer_document",
+    "/datasets/evo2/eukaryote_ncbi/pretraining_data/data_train_batch8_plantae_text_CharLevelTokenizer_document",
+    "/datasets/evo2/eukaryote_ncbi/pretraining_data/data_train_batch1_chromista_text_CharLevelTokenizer_document",
+    "/datasets/evo2/eukaryote_ncbi/pretraining_data/data_train_batch2_chromista_text_CharLevelTokenizer_document",
+    "/datasets/evo2/eukaryote_ncbi/pretraining_data/data_train_batch3_chromista_text_CharLevelTokenizer_document",
+    "/datasets/evo2/eukaryote_ncbi/pretraining_data/data_train_batch4_chromista_text_CharLevelTokenizer_document",
+    "/datasets/evo2/eukaryote_ncbi/pretraining_data/data_train_batch5_chromista_text_CharLevelTokenizer_document",
+    "/datasets/evo2/eukaryote_ncbi/pretraining_data/data_train_batch6_chromista_text_CharLevelTokenizer_document",
+    "/datasets/evo2/eukaryote_ncbi/pretraining_data/data_train_batch7_chromista_text_CharLevelTokenizer_document",
+    "/datasets/evo2/eukaryote_ncbi/pretraining_data/data_train_batch8_chromista_text_CharLevelTokenizer_document",
+    "/datasets/evo2/eukaryote_ncbi/pretraining_data/data_train_batch1_protista_text_CharLevelTokenizer_document",
+    "/datasets/evo2/eukaryote_ncbi/pretraining_data/data_train_batch2_protista_text_CharLevelTokenizer_document",
+    "/datasets/evo2/eukaryote_ncbi/pretraining_data/data_train_batch3_protista_text_CharLevelTokenizer_document",
+    "/datasets/evo2/eukaryote_ncbi/pretraining_data/data_train_batch4_protista_text_CharLevelTokenizer_document",
+    "/datasets/evo2/eukaryote_ncbi/pretraining_data/data_train_batch5_protista_text_CharLevelTokenizer_document",
+    "/datasets/evo2/eukaryote_ncbi/pretraining_data/data_train_batch6_protista_text_CharLevelTokenizer_document",
+    "/datasets/evo2/eukaryote_ncbi/pretraining_data/data_train_batch7_protista_text_CharLevelTokenizer_document",
+    "/datasets/evo2/eukaryote_ncbi/pretraining_data/data_train_batch8_protista_text_CharLevelTokenizer_document",
+
+    ],
+
+  # note no hg38
+  "valid-data-paths": [
+    "/datasets/evo2/metagenomics/pretraining_data_metagenomics/data_metagenomics_valid_text_CharLevelTokenizer_document",
+    "/datasets/evo2/gtdb_imgpr/pretraining_data_gtdb_imgpr/data_gtdb_imgpr_valid_text_CharLevelTokenizer_document",
+    "/datasets/evo2/imgvr/pretraining_data_imgvr/data_imgvr_valid_text_CharLevelTokenizer_document",
+    "/datasets/evo2/ncrna/pretraining_data_ncrna/data_ncrna_valid_text_CharLevelTokenizer_document",
+    "/datasets/evo2/mrna_splice/pretraining_data_mrna_splice/data_mrna_splice_valid_text_CharLevelTokenizer_document",
+    "/datasets/evo2/promoters/pretraining_data_promoters/data_promoters_valid_text_CharLevelTokenizer_document",
+    "/datasets/evo2/eukaryote_ncbi/pretraining_data/data_valid_batch1_animalia_text_CharLevelTokenizer_document",
+    "/datasets/evo2/eukaryote_ncbi/pretraining_data/data_valid_batch2_animalia_text_CharLevelTokenizer_document",
+    "/datasets/evo2/eukaryote_ncbi/pretraining_data/data_valid_batch3_animalia_text_CharLevelTokenizer_document",
+    "/datasets/evo2/eukaryote_ncbi/pretraining_data/data_valid_batch4_animalia_text_CharLevelTokenizer_document",
+    "/datasets/evo2/eukaryote_ncbi/pretraining_data/data_valid_batch5_animalia_text_CharLevelTokenizer_document",
+    "/datasets/evo2/eukaryote_ncbi/pretraining_data/data_valid_batch6_animalia_text_CharLevelTokenizer_document",
+    "/datasets/evo2/eukaryote_ncbi/pretraining_data/data_valid_batch7_animalia_text_CharLevelTokenizer_document",
+    "/datasets/evo2/eukaryote_ncbi/pretraining_data/data_valid_batch8_animalia_text_CharLevelTokenizer_document",
+    "/datasets/evo2/eukaryote_ncbi/pretraining_data/data_valid_batch1_fungi_text_CharLevelTokenizer_document",
+    "/datasets/evo2/eukaryote_ncbi/pretraining_data/data_valid_batch2_fungi_text_CharLevelTokenizer_document",
+    "/datasets/evo2/eukaryote_ncbi/pretraining_data/data_valid_batch3_fungi_text_CharLevelTokenizer_document",
+    "/datasets/evo2/eukaryote_ncbi/pretraining_data/data_valid_batch4_fungi_text_CharLevelTokenizer_document",
+    "/datasets/evo2/eukaryote_ncbi/pretraining_data/data_valid_batch5_fungi_text_CharLevelTokenizer_document",
+    "/datasets/evo2/eukaryote_ncbi/pretraining_data/data_valid_batch6_fungi_text_CharLevelTokenizer_document",
+    "/datasets/evo2/eukaryote_ncbi/pretraining_data/data_valid_batch7_fungi_text_CharLevelTokenizer_document",
+    "/datasets/evo2/eukaryote_ncbi/pretraining_data/data_valid_batch8_fungi_text_CharLevelTokenizer_document",
+    "/datasets/evo2/eukaryote_ncbi/pretraining_data/data_valid_batch1_plantae_text_CharLevelTokenizer_document",
+    "/datasets/evo2/eukaryote_ncbi/pretraining_data/data_valid_batch2_plantae_text_CharLevelTokenizer_document",
+    "/datasets/evo2/eukaryote_ncbi/pretraining_data/data_valid_batch3_plantae_text_CharLevelTokenizer_document",
+    "/datasets/evo2/eukaryote_ncbi/pretraining_data/data_valid_batch4_plantae_text_CharLevelTokenizer_document",
+    "/datasets/evo2/eukaryote_ncbi/pretraining_data/data_valid_batch5_plantae_text_CharLevelTokenizer_document",
+    "/datasets/evo2/eukaryote_ncbi/pretraining_data/data_valid_batch6_plantae_text_CharLevelTokenizer_document",
+    "/datasets/evo2/eukaryote_ncbi/pretraining_data/data_valid_batch7_plantae_text_CharLevelTokenizer_document",
+    "/datasets/evo2/eukaryote_ncbi/pretraining_data/data_valid_batch8_plantae_text_CharLevelTokenizer_document",
+    "/datasets/evo2/eukaryote_ncbi/pretraining_data/data_valid_batch1_chromista_text_CharLevelTokenizer_document",
+    "/datasets/evo2/eukaryote_ncbi/pretraining_data/data_valid_batch2_chromista_text_CharLevelTokenizer_document",
+    "/datasets/evo2/eukaryote_ncbi/pretraining_data/data_valid_batch3_chromista_text_CharLevelTokenizer_document",
+    "/datasets/evo2/eukaryote_ncbi/pretraining_data/data_valid_batch4_chromista_text_CharLevelTokenizer_document",
+    "/datasets/evo2/eukaryote_ncbi/pretraining_data/data_valid_batch5_chromista_text_CharLevelTokenizer_document",
+    "/datasets/evo2/eukaryote_ncbi/pretraining_data/data_valid_batch6_chromista_text_CharLevelTokenizer_document",
+    "/datasets/evo2/eukaryote_ncbi/pretraining_data/data_valid_batch7_chromista_text_CharLevelTokenizer_document",
+    "/datasets/evo2/eukaryote_ncbi/pretraining_data/data_valid_batch8_chromista_text_CharLevelTokenizer_document",
+    "/datasets/evo2/eukaryote_ncbi/pretraining_data/data_valid_batch1_protista_text_CharLevelTokenizer_document",
+    "/datasets/evo2/eukaryote_ncbi/pretraining_data/data_valid_batch2_protista_text_CharLevelTokenizer_document",
+    "/datasets/evo2/eukaryote_ncbi/pretraining_data/data_valid_batch3_protista_text_CharLevelTokenizer_document",
+    "/datasets/evo2/eukaryote_ncbi/pretraining_data/data_valid_batch4_protista_text_CharLevelTokenizer_document",
+    "/datasets/evo2/eukaryote_ncbi/pretraining_data/data_valid_batch5_protista_text_CharLevelTokenizer_document",
+    "/datasets/evo2/eukaryote_ncbi/pretraining_data/data_valid_batch6_protista_text_CharLevelTokenizer_document",
+    "/datasets/evo2/eukaryote_ncbi/pretraining_data/data_valid_batch7_protista_text_CharLevelTokenizer_document",
+    "/datasets/evo2/eukaryote_ncbi/pretraining_data/data_valid_batch8_protista_text_CharLevelTokenizer_document",
+    ],
+
+  # note no hg38
+  "test-data-paths": [
+    "/datasets/evo2/metagenomics/pretraining_data_metagenomics/data_metagenomics_test_text_CharLevelTokenizer_document",
+    "/datasets/evo2/gtdb_imgpr/pretraining_data_gtdb_imgpr/data_gtdb_imgpr_test_text_CharLevelTokenizer_document",
+    "/datasets/evo2/imgvr/pretraining_data_imgvr/data_imgvr_test_text_CharLevelTokenizer_document",
+    "/datasets/evo2/ncrna/pretraining_data_ncrna/data_ncrna_test_text_CharLevelTokenizer_document",
+    "/datasets/evo2/mrna_splice/pretraining_data_mrna_splice/data_mrna_splice_test_text_CharLevelTokenizer_document",
+    "/datasets/evo2/promoters/pretraining_data_promoters/data_promoters_test_text_CharLevelTokenizer_document",
+    "/datasets/evo2/eukaryote_ncbi/pretraining_data/data_test_batch1_animalia_text_CharLevelTokenizer_document",
+    "/datasets/evo2/eukaryote_ncbi/pretraining_data/data_test_batch2_animalia_text_CharLevelTokenizer_document",
+    "/datasets/evo2/eukaryote_ncbi/pretraining_data/data_test_batch3_animalia_text_CharLevelTokenizer_document",
+    "/datasets/evo2/eukaryote_ncbi/pretraining_data/data_test_batch4_animalia_text_CharLevelTokenizer_document",
+    "/datasets/evo2/eukaryote_ncbi/pretraining_data/data_test_batch5_animalia_text_CharLevelTokenizer_document",
+    "/datasets/evo2/eukaryote_ncbi/pretraining_data/data_test_batch6_animalia_text_CharLevelTokenizer_document",
+    "/datasets/evo2/eukaryote_ncbi/pretraining_data/data_test_batch7_animalia_text_CharLevelTokenizer_document",
+    "/datasets/evo2/eukaryote_ncbi/pretraining_data/data_test_batch8_animalia_text_CharLevelTokenizer_document",
+    "/datasets/evo2/eukaryote_ncbi/pretraining_data/data_test_batch1_fungi_text_CharLevelTokenizer_document",
+    "/datasets/evo2/eukaryote_ncbi/pretraining_data/data_test_batch2_fungi_text_CharLevelTokenizer_document",
+    "/datasets/evo2/eukaryote_ncbi/pretraining_data/data_test_batch3_fungi_text_CharLevelTokenizer_document",
+    "/datasets/evo2/eukaryote_ncbi/pretraining_data/data_test_batch4_fungi_text_CharLevelTokenizer_document",
+    "/datasets/evo2/eukaryote_ncbi/pretraining_data/data_test_batch5_fungi_text_CharLevelTokenizer_document",
+    "/datasets/evo2/eukaryote_ncbi/pretraining_data/data_test_batch6_fungi_text_CharLevelTokenizer_document",
+    "/datasets/evo2/eukaryote_ncbi/pretraining_data/data_test_batch7_fungi_text_CharLevelTokenizer_document",
+    "/datasets/evo2/eukaryote_ncbi/pretraining_data/data_test_batch8_fungi_text_CharLevelTokenizer_document",
+    "/datasets/evo2/eukaryote_ncbi/pretraining_data/data_test_batch1_plantae_text_CharLevelTokenizer_document",
+    "/datasets/evo2/eukaryote_ncbi/pretraining_data/data_test_batch2_plantae_text_CharLevelTokenizer_document",
+    "/datasets/evo2/eukaryote_ncbi/pretraining_data/data_test_batch3_plantae_text_CharLevelTokenizer_document",
+    "/datasets/evo2/eukaryote_ncbi/pretraining_data/data_test_batch4_plantae_text_CharLevelTokenizer_document",
+    "/datasets/evo2/eukaryote_ncbi/pretraining_data/data_test_batch5_plantae_text_CharLevelTokenizer_document",
+    "/datasets/evo2/eukaryote_ncbi/pretraining_data/data_test_batch6_plantae_text_CharLevelTokenizer_document",
+    "/datasets/evo2/eukaryote_ncbi/pretraining_data/data_test_batch7_plantae_text_CharLevelTokenizer_document",
+    "/datasets/evo2/eukaryote_ncbi/pretraining_data/data_test_batch8_plantae_text_CharLevelTokenizer_document",
+    "/datasets/evo2/eukaryote_ncbi/pretraining_data/data_test_batch1_chromista_text_CharLevelTokenizer_document",
+    "/datasets/evo2/eukaryote_ncbi/pretraining_data/data_test_batch2_chromista_text_CharLevelTokenizer_document",
+    "/datasets/evo2/eukaryote_ncbi/pretraining_data/data_test_batch3_chromista_text_CharLevelTokenizer_document",
+    "/datasets/evo2/eukaryote_ncbi/pretraining_data/data_test_batch4_chromista_text_CharLevelTokenizer_document",
+    "/datasets/evo2/eukaryote_ncbi/pretraining_data/data_test_batch5_chromista_text_CharLevelTokenizer_document",
+    "/datasets/evo2/eukaryote_ncbi/pretraining_data/data_test_batch6_chromista_text_CharLevelTokenizer_document",
+    "/datasets/evo2/eukaryote_ncbi/pretraining_data/data_test_batch7_chromista_text_CharLevelTokenizer_document",
+    "/datasets/evo2/eukaryote_ncbi/pretraining_data/data_test_batch8_chromista_text_CharLevelTokenizer_document",
+    "/datasets/evo2/eukaryote_ncbi/pretraining_data/data_test_batch1_protista_text_CharLevelTokenizer_document",
+    "/datasets/evo2/eukaryote_ncbi/pretraining_data/data_test_batch2_protista_text_CharLevelTokenizer_document",
+    "/datasets/evo2/eukaryote_ncbi/pretraining_data/data_test_batch3_protista_text_CharLevelTokenizer_document",
+    "/datasets/evo2/eukaryote_ncbi/pretraining_data/data_test_batch4_protista_text_CharLevelTokenizer_document",
+    "/datasets/evo2/eukaryote_ncbi/pretraining_data/data_test_batch5_protista_text_CharLevelTokenizer_document",
+    "/datasets/evo2/eukaryote_ncbi/pretraining_data/data_test_batch6_protista_text_CharLevelTokenizer_document",
+    "/datasets/evo2/eukaryote_ncbi/pretraining_data/data_test_batch7_protista_text_CharLevelTokenizer_document",
+    "/datasets/evo2/eukaryote_ncbi/pretraining_data/data_test_batch8_protista_text_CharLevelTokenizer_document",
+    ],
+"train-data-weights": [
+  0.09, 0.15, 0.017, 0.003, 0.02, 0.09, 0.0002, 0.05625, 0.05625,
+  0.05625, 0.05625, 0.05625, 0.05625, 0.05625, 0.05625, 0.01, 0.01, 0.01, 0.01,
+  0.01, 0.01, 0.01, 0.01, 0.010725, 0.010725, 0.010725, 0.010725, 0.010725, 0.010725,
+  0.010725, 0.010725, 0.00075, 0.00075, 0.00075, 0.00075, 0.00075, 0.00075, 0.00075, 0.00075,
+  0.001, 0.001, 0.001, 0.001, 0.001, 0.001, 0.001, 0.001
+  ],
+  "test-data-weights": [
+  0.09, 0.15, 0.017, 0.02, 0.09, 0.0002, 0.05625, 0.05625, 0.05625, 0.05625,
+  0.05625, 0.05625, 0.05625, 0.05625, 0.01, 0.01, 0.01, 0.01, 0.01, 0.01,
+  0.01, 0.01, 0.010725, 0.010725, 0.010725, 0.010725, 0.010725, 0.010725, 0.010725,
+  0.010725, 0.00075, 0.00075, 0.00075, 0.00075, 0.00075, 0.00075, 0.00075, 0.00075,
+  0.001, 0.001, 0.001, 0.001, 0.001, 0.001, 0.001, 0.001
+  ],
+  "valid-data-weights": [
+  0.09, 0.15, 0.017, 0.02, 0.09, 0.0002, 0.05625, 0.05625, 0.05625,
+  0.05625, 0.05625, 0.05625, 0.05625, 0.05625, 0.01, 0.01, 0.01, 0.01, 0.01,
+  0.01, 0.01, 0.01, 0.010725, 0.010725, 0.010725, 0.010725, 0.010725, 0.010725, 0.010725,
+  0.010725, 0.00075, 0.00075, 0.00075, 0.00075, 0.00075, 0.00075, 0.00075, 0.00075,
+  0.001, 0.001, 0.001, 0.001, 0.001, 0.001, 0.001, 0.001
+  ],
+  "checkpoint_validation_with_forward_pass": False,
+  # "use_wandb": false,
+  "wandb_host": "https://api.wandb.ai",
+  "wandb_project": "evo2"
+}

configuration.json

@@ -0,0 +1,15 @@
+{
+  "model_name": "Evo2",
+  "framework": "PyTorch/NeMo",
+  "task": "genomic-sequence-modeling",
+  "entry_points": {
+    "train": "scripts/train.py",
+    "inference": "scripts/infer.py",
+    "predict": "scripts/predict.py"
+  },
+  "source_package": "model/evo2",
+  "base_dependency": "onescience",
+  "config": "config/config.yaml",
+  "weight_dir": "checkpoints",
+  "license": "Apache-2.0"
+}

data/data_mini/genome_data/chr20.fa

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a704b3a25c698bb5219b750d0ba6a333ddb0043904b4921992d5f709771c2666
+size 65733058

data/data_mini/genome_data/chr20.fa.gz

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:271ca0ee4247c2fa30c8491764ad8acd4bdde8eb3cf314f0720235010ae85c9f
+size 20350590

data/data_mini/genome_data/chr20_21_22.fa

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5c65fe1f46bb7949ab4e670a004e01f4815501f5f949c5b75cd06cd6df229059
+size 165212093

data/data_mini/genome_data/chr21.fa

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:35c71b68436d1a278ecb6a1e875af3ba4020738a028a7feac769a6d62790ae1f
+size 47644190

data/data_mini/genome_data/chr21.fa.gz

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c979ca1e5065c2521a50773473e0d0cc018fd6f3e9bb3aa90493fe7b45d57d1b
+size 12709705

data/data_mini/genome_data/chr22.fa

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ce3ee1ca39356238f7aee438a40a88b4f1b9d80b316b263e16fb12402212d10f
+size 51834845

data/data_mini/genome_data/chr22.fa.gz

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:05f9d97d6fbfd08a44ca45b50837ca2ae9c471f35ba79dffec04d2cb5eaaf695
+size 12255678

data/data_mini/genome_data/preprocessed_data/chr20_21_22_uint8_distinct_byte-level_test.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c03f70b9b67e85e9dd37277ec7d18ec69ff8bf18e822dfb8300d944c18c2e5a2
+size 101636938

data/data_mini/genome_data/preprocessed_data/chr20_21_22_uint8_distinct_byte-level_test/cache/GPTDataset_indices/342ca946fce706bd1bebace29d20c889-GPTDataset-test-description.txt

@@ -0,0 +1,13 @@
+{
+    "class": "GPTDataset",
+    "dataset_path": "data/data_mini/genome_data/preprocessed_data/chr20_21_22_uint8_distinct_byte-level_test",
+    "num_samples": 16,
+    "index_split": "test",
+    "random_seed": 1234,
+    "sequence_length": 8192,
+    "split": null,
+    "split_matrix": null,
+    "tokenizer": {
+        "class": "nemo.collections.common.tokenizers.bytelevel_tokenizers.ByteLevelTokenizer"
+    }
+}

data/data_mini/genome_data/preprocessed_data/chr20_21_22_uint8_distinct_byte-level_test/cache/GPTDataset_indices/342ca946fce706bd1bebace29d20c889-GPTDataset-test-document_index.npy

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:28d4b63fdadd72ed19f8fad1638746569959d59ee50d3e10d67810fced9dc78f
+size 136

data/data_mini/genome_data/preprocessed_data/chr20_21_22_uint8_distinct_byte-level_test/cache/GPTDataset_indices/342ca946fce706bd1bebace29d20c889-GPTDataset-test-sample_index.npy

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b4b37f6c8f8a94fd66ed63489802ee9b633c786b3a3c94ac900fb0e5ef4f617d
+size 99384

data/data_mini/genome_data/preprocessed_data/chr20_21_22_uint8_distinct_byte-level_test/cache/GPTDataset_indices/342ca946fce706bd1bebace29d20c889-GPTDataset-test-shuffle_index.npy

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a68f8b87962dfc3d24757b2869592ab15741d2326a29cdb30b4df150912cfe7a
+size 49752

data/data_mini/genome_data/preprocessed_data/chr20_21_22_uint8_distinct_byte-level_test/cache/GPTDataset_indices/bdd3bfe88a1201b3e8f83953f7072ca6-GPTDataset-test-description.txt

@@ -0,0 +1,13 @@
+{
+    "class": "GPTDataset",
+    "dataset_path": "data/data_mini/genome_data/preprocessed_data/chr20_21_22_uint8_distinct_byte-level_test",
+    "num_samples": 8,
+    "index_split": "test",
+    "random_seed": 1234,
+    "sequence_length": 1024,
+    "split": null,
+    "split_matrix": null,
+    "tokenizer": {
+        "class": "nemo.collections.common.tokenizers.bytelevel_tokenizers.ByteLevelTokenizer"
+    }
+}

data/data_mini/genome_data/preprocessed_data/chr20_21_22_uint8_distinct_byte-level_test/cache/GPTDataset_indices/bdd3bfe88a1201b3e8f83953f7072ca6-GPTDataset-test-document_index.npy

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:28d4b63fdadd72ed19f8fad1638746569959d59ee50d3e10d67810fced9dc78f
+size 136

data/data_mini/genome_data/preprocessed_data/chr20_21_22_uint8_distinct_byte-level_test/cache/GPTDataset_indices/bdd3bfe88a1201b3e8f83953f7072ca6-GPTDataset-test-sample_index.npy

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:53f2655dac75ebf3e3bb0454ffe82e61bcda93a47b3c8df90401d123e0be8bb5
+size 794168

data/data_mini/genome_data/preprocessed_data/chr20_21_22_uint8_distinct_byte-level_test/cache/GPTDataset_indices/bdd3bfe88a1201b3e8f83953f7072ca6-GPTDataset-test-shuffle_index.npy

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c33ad031b614ec8043d296f2ecc4ebd4a21d1cf636f40ebfa0af56bc7fa0eb8c
+size 397144

data/data_mini/genome_data/preprocessed_data/chr20_21_22_uint8_distinct_byte-level_train.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3f3d2d68af61f62bd11cbc0c13648029637baaf6a3a0d2ce228db6724ac60b7e
+size 128888336

data/data_mini/genome_data/preprocessed_data/chr20_21_22_uint8_distinct_byte-level_train/cache/GPTDataset_indices/746855b0ca028bf7efd5622b8169f84e-GPTDataset-train-description.txt

@@ -0,0 +1,13 @@
+{
+    "class": "GPTDataset",
+    "dataset_path": "data/data_mini/genome_data/preprocessed_data/chr20_21_22_uint8_distinct_byte-level_train",
+    "num_samples": 8000,
+    "index_split": "train",
+    "random_seed": 1234,
+    "sequence_length": 1024,
+    "split": null,
+    "split_matrix": null,
+    "tokenizer": {
+        "class": "nemo.collections.common.tokenizers.bytelevel_tokenizers.ByteLevelTokenizer"
+    }
+}

data/data_mini/genome_data/preprocessed_data/chr20_21_22_uint8_distinct_byte-level_train/cache/GPTDataset_indices/746855b0ca028bf7efd5622b8169f84e-GPTDataset-train-document_index.npy

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:28d4b63fdadd72ed19f8fad1638746569959d59ee50d3e10d67810fced9dc78f
+size 136

data/data_mini/genome_data/preprocessed_data/chr20_21_22_uint8_distinct_byte-level_train/cache/GPTDataset_indices/746855b0ca028bf7efd5622b8169f84e-GPTDataset-train-sample_index.npy

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:34f9e9c57b454b1b4888a5492aed2014952633e9b6c93639bca9c4217532d2d9
+size 1007072

data/data_mini/genome_data/preprocessed_data/chr20_21_22_uint8_distinct_byte-level_train/cache/GPTDataset_indices/746855b0ca028bf7efd5622b8169f84e-GPTDataset-train-shuffle_index.npy

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1d0e161e823144594d9eef6ffd50ca778f8e1ae1f0831cf1d040c02a9f056771
+size 503596

data/data_mini/genome_data/preprocessed_data/chr20_21_22_uint8_distinct_byte-level_train/cache/GPTDataset_indices/9f44c7ed4a3ebd5a2cfaed3f9be3b954-GPTDataset-train-description.txt

@@ -0,0 +1,13 @@
+{
+    "class": "GPTDataset",
+    "dataset_path": "data/data_mini/genome_data/preprocessed_data/chr20_21_22_uint8_distinct_byte-level_train",
+    "num_samples": 16000,
+    "index_split": "train",
+    "random_seed": 1234,
+    "sequence_length": 8192,
+    "split": null,
+    "split_matrix": null,
+    "tokenizer": {
+        "class": "nemo.collections.common.tokenizers.bytelevel_tokenizers.ByteLevelTokenizer"
+    }
+}

data/data_mini/genome_data/preprocessed_data/chr20_21_22_uint8_distinct_byte-level_train/cache/GPTDataset_indices/9f44c7ed4a3ebd5a2cfaed3f9be3b954-GPTDataset-train-document_index.npy

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bc6782cd85e561058197445aef6cf1e89bb2897b69dacb26af801ba986f2322e
+size 144

data/data_mini/genome_data/preprocessed_data/chr20_21_22_uint8_distinct_byte-level_train/cache/GPTDataset_indices/9f44c7ed4a3ebd5a2cfaed3f9be3b954-GPTDataset-train-sample_index.npy

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ee4ef251a29baa3cdcbbefbd7a4876eccf2b69d1e1d326513a342b29382e167f
+size 251864

data/data_mini/genome_data/preprocessed_data/chr20_21_22_uint8_distinct_byte-level_train/cache/GPTDataset_indices/9f44c7ed4a3ebd5a2cfaed3f9be3b954-GPTDataset-train-shuffle_index.npy

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cdfdd5f02d57271a14de63780596ea8db0044311e6990ba05cdeaf5c0181255a
+size 125992

data/data_mini/genome_data/preprocessed_data/chr20_21_22_uint8_distinct_byte-level_val.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:596393be374e2a0aa08e7f4f8ba3c42a21c76f825c1b3f49c76c0f5dd44e7cd5
+size 93419968

data/data_mini/genome_data/preprocessed_data/chr20_21_22_uint8_distinct_byte-level_val/cache/GPTDataset_indices/a8235fab7adf408b89a5c5806a781046-GPTDataset-valid-description.txt

@@ -0,0 +1,13 @@
+{
+    "class": "GPTDataset",
+    "dataset_path": "data/data_mini/genome_data/preprocessed_data/chr20_21_22_uint8_distinct_byte-level_val",
+    "num_samples": 672,
+    "index_split": "valid",
+    "random_seed": 1234,
+    "sequence_length": 8192,
+    "split": null,
+    "split_matrix": null,
+    "tokenizer": {
+        "class": "nemo.collections.common.tokenizers.bytelevel_tokenizers.ByteLevelTokenizer"
+    }
+}

data/data_mini/genome_data/preprocessed_data/chr20_21_22_uint8_distinct_byte-level_val/cache/GPTDataset_indices/a8235fab7adf408b89a5c5806a781046-GPTDataset-valid-document_index.npy

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:28d4b63fdadd72ed19f8fad1638746569959d59ee50d3e10d67810fced9dc78f
+size 136

data/data_mini/genome_data/preprocessed_data/chr20_21_22_uint8_distinct_byte-level_val/cache/GPTDataset_indices/a8235fab7adf408b89a5c5806a781046-GPTDataset-valid-sample_index.npy

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a8ab709b3b7a8600968430e26d46a77c8d7924914d52ec076847841aa73edd81
+size 91360

data/data_mini/genome_data/preprocessed_data/chr20_21_22_uint8_distinct_byte-level_val/cache/GPTDataset_indices/a8235fab7adf408b89a5c5806a781046-GPTDataset-valid-shuffle_index.npy

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2e7754043b6dd3baae0db20e3d0b8a7f04743c973a5f856f78f720c144ba8763
+size 45740

data/data_mini/genome_data/preprocessed_data/chr20_21_22_uint8_distinct_byte-level_val/cache/GPTDataset_indices/cccf4722f9a5df3869a82454d596a5e6-GPTDataset-valid-description.txt

@@ -0,0 +1,13 @@
+{
+    "class": "GPTDataset",
+    "dataset_path": "data/data_mini/genome_data/preprocessed_data/chr20_21_22_uint8_distinct_byte-level_val",
+    "num_samples": 336,
+    "index_split": "valid",
+    "random_seed": 1234,
+    "sequence_length": 1024,
+    "split": null,
+    "split_matrix": null,
+    "tokenizer": {
+        "class": "nemo.collections.common.tokenizers.bytelevel_tokenizers.ByteLevelTokenizer"
+    }
+}

data/data_mini/genome_data/preprocessed_data/chr20_21_22_uint8_distinct_byte-level_val/cache/GPTDataset_indices/cccf4722f9a5df3869a82454d596a5e6-GPTDataset-valid-document_index.npy

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:28d4b63fdadd72ed19f8fad1638746569959d59ee50d3e10d67810fced9dc78f
+size 136