nicholaswaltz commited on
Commit
8622b7d
·
verified ·
1 Parent(s): 568b00f

Jeeves-9B: fused weights, pointer head, drafters

Browse files
.gitattributes CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
LICENSE ADDED
@@ -0,0 +1,202 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+
2
+ Apache License
3
+ Version 2.0, January 2004
4
+ http://www.apache.org/licenses/
5
+
6
+ TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
7
+
8
+ 1. Definitions.
9
+
10
+ "License" shall mean the terms and conditions for use, reproduction,
11
+ and distribution as defined by Sections 1 through 9 of this document.
12
+
13
+ "Licensor" shall mean the copyright owner or entity authorized by
14
+ the copyright owner that is granting the License.
15
+
16
+ "Legal Entity" shall mean the union of the acting entity and all
17
+ other entities that control, are controlled by, or are under common
18
+ control with that entity. For the purposes of this definition,
19
+ "control" means (i) the power, direct or indirect, to cause the
20
+ direction or management of such entity, whether by contract or
21
+ otherwise, or (ii) ownership of fifty percent (50%) or more of the
22
+ outstanding shares, or (iii) beneficial ownership of such entity.
23
+
24
+ "You" (or "Your") shall mean an individual or Legal Entity
25
+ exercising permissions granted by this License.
26
+
27
+ "Source" form shall mean the preferred form for making modifications,
28
+ including but not limited to software source code, documentation
29
+ source, and configuration files.
30
+
31
+ "Object" form shall mean any form resulting from mechanical
32
+ transformation or translation of a Source form, including but
33
+ not limited to compiled object code, generated documentation,
34
+ and conversions to other media types.
35
+
36
+ "Work" shall mean the work of authorship, whether in Source or
37
+ Object form, made available under the License, as indicated by a
38
+ copyright notice that is included in or attached to the work
39
+ (an example is provided in the Appendix below).
40
+
41
+ "Derivative Works" shall mean any work, whether in Source or Object
42
+ form, that is based on (or derived from) the Work and for which the
43
+ editorial revisions, annotations, elaborations, or other modifications
44
+ represent, as a whole, an original work of authorship. For the purposes
45
+ of this License, Derivative Works shall not include works that remain
46
+ separable from, or merely link (or bind by name) to the interfaces of,
47
+ the Work and Derivative Works thereof.
48
+
49
+ "Contribution" shall mean any work of authorship, including
50
+ the original version of the Work and any modifications or additions
51
+ to that Work or Derivative Works thereof, that is intentionally
52
+ submitted to Licensor for inclusion in the Work by the copyright owner
53
+ or by an individual or Legal Entity authorized to submit on behalf of
54
+ the copyright owner. For the purposes of this definition, "submitted"
55
+ means any form of electronic, verbal, or written communication sent
56
+ to the Licensor or its representatives, including but not limited to
57
+ communication on electronic mailing lists, source code control systems,
58
+ and issue tracking systems that are managed by, or on behalf of, the
59
+ Licensor for the purpose of discussing and improving the Work, but
60
+ excluding communication that is conspicuously marked or otherwise
61
+ designated in writing by the copyright owner as "Not a Contribution."
62
+
63
+ "Contributor" shall mean Licensor and any individual or Legal Entity
64
+ on behalf of whom a Contribution has been received by Licensor and
65
+ subsequently incorporated within the Work.
66
+
67
+ 2. Grant of Copyright License. Subject to the terms and conditions of
68
+ this License, each Contributor hereby grants to You a perpetual,
69
+ worldwide, non-exclusive, no-charge, royalty-free, irrevocable
70
+ copyright license to reproduce, prepare Derivative Works of,
71
+ publicly display, publicly perform, sublicense, and distribute the
72
+ Work and such Derivative Works in Source or Object form.
73
+
74
+ 3. Grant of Patent License. Subject to the terms and conditions of
75
+ this License, each Contributor hereby grants to You a perpetual,
76
+ worldwide, non-exclusive, no-charge, royalty-free, irrevocable
77
+ (except as stated in this section) patent license to make, have made,
78
+ use, offer to sell, sell, import, and otherwise transfer the Work,
79
+ where such license applies only to those patent claims licensable
80
+ by such Contributor that are necessarily infringed by their
81
+ Contribution(s) alone or by combination of their Contribution(s)
82
+ with the Work to which such Contribution(s) was submitted. If You
83
+ institute patent litigation against any entity (including a
84
+ cross-claim or counterclaim in a lawsuit) alleging that the Work
85
+ or a Contribution incorporated within the Work constitutes direct
86
+ or contributory patent infringement, then any patent licenses
87
+ granted to You under this License for that Work shall terminate
88
+ as of the date such litigation is filed.
89
+
90
+ 4. Redistribution. You may reproduce and distribute copies of the
91
+ Work or Derivative Works thereof in any medium, with or without
92
+ modifications, and in Source or Object form, provided that You
93
+ meet the following conditions:
94
+
95
+ (a) You must give any other recipients of the Work or
96
+ Derivative Works a copy of this License; and
97
+
98
+ (b) You must cause any modified files to carry prominent notices
99
+ stating that You changed the files; and
100
+
101
+ (c) You must retain, in the Source form of any Derivative Works
102
+ that You distribute, all copyright, patent, trademark, and
103
+ attribution notices from the Source form of the Work,
104
+ excluding those notices that do not pertain to any part of
105
+ the Derivative Works; and
106
+
107
+ (d) If the Work includes a "NOTICE" text file as part of its
108
+ distribution, then any Derivative Works that You distribute must
109
+ include a readable copy of the attribution notices contained
110
+ within such NOTICE file, excluding those notices that do not
111
+ pertain to any part of the Derivative Works, in at least one
112
+ of the following places: within a NOTICE text file distributed
113
+ as part of the Derivative Works; within the Source form or
114
+ documentation, if provided along with the Derivative Works; or,
115
+ within a display generated by the Derivative Works, if and
116
+ wherever such third-party notices normally appear. The contents
117
+ of the NOTICE file are for informational purposes only and
118
+ do not modify the License. You may add Your own attribution
119
+ notices within Derivative Works that You distribute, alongside
120
+ or as an addendum to the NOTICE text from the Work, provided
121
+ that such additional attribution notices cannot be construed
122
+ as modifying the License.
123
+
124
+ You may add Your own copyright statement to Your modifications and
125
+ may provide additional or different license terms and conditions
126
+ for use, reproduction, or distribution of Your modifications, or
127
+ for any such Derivative Works as a whole, provided Your use,
128
+ reproduction, and distribution of the Work otherwise complies with
129
+ the conditions stated in this License.
130
+
131
+ 5. Submission of Contributions. Unless You explicitly state otherwise,
132
+ any Contribution intentionally submitted for inclusion in the Work
133
+ by You to the Licensor shall be under the terms and conditions of
134
+ this License, without any additional terms or conditions.
135
+ Notwithstanding the above, nothing herein shall supersede or modify
136
+ the terms of any separate license agreement you may have executed
137
+ with Licensor regarding such Contributions.
138
+
139
+ 6. Trademarks. This License does not grant permission to use the trade
140
+ names, trademarks, service marks, or product names of the Licensor,
141
+ except as required for reasonable and customary use in describing the
142
+ origin of the Work and reproducing the content of the NOTICE file.
143
+
144
+ 7. Disclaimer of Warranty. Unless required by applicable law or
145
+ agreed to in writing, Licensor provides the Work (and each
146
+ Contributor provides its Contributions) on an "AS IS" BASIS,
147
+ WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
148
+ implied, including, without limitation, any warranties or conditions
149
+ of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
150
+ PARTICULAR PURPOSE. You are solely responsible for determining the
151
+ appropriateness of using or redistributing the Work and assume any
152
+ risks associated with Your exercise of permissions under this License.
153
+
154
+ 8. Limitation of Liability. In no event and under no legal theory,
155
+ whether in tort (including negligence), contract, or otherwise,
156
+ unless required by applicable law (such as deliberate and grossly
157
+ negligent acts) or agreed to in writing, shall any Contributor be
158
+ liable to You for damages, including any direct, indirect, special,
159
+ incidental, or consequential damages of any character arising as a
160
+ result of this License or out of the use or inability to use the
161
+ Work (including but not limited to damages for loss of goodwill,
162
+ work stoppage, computer failure or malfunction, or any and all
163
+ other commercial damages or losses), even if such Contributor
164
+ has been advised of the possibility of such damages.
165
+
166
+ 9. Accepting Warranty or Additional Liability. While redistributing
167
+ the Work or Derivative Works thereof, You may choose to offer,
168
+ and charge a fee for, acceptance of support, warranty, indemnity,
169
+ or other liability obligations and/or rights consistent with this
170
+ License. However, in accepting such obligations, You may act only
171
+ on Your own behalf and on Your sole responsibility, not on behalf
172
+ of any other Contributor, and only if You agree to indemnify,
173
+ defend, and hold each Contributor harmless for any liability
174
+ incurred by, or claims asserted against, such Contributor by reason
175
+ of your accepting any such warranty or additional liability.
176
+
177
+ END OF TERMS AND CONDITIONS
178
+
179
+ APPENDIX: How to apply the Apache License to your work.
180
+
181
+ To apply the Apache License to your work, attach the following
182
+ boilerplate notice, with the fields enclosed by brackets "[]"
183
+ replaced with your own identifying information. (Don't include
184
+ the brackets!) The text should be enclosed in the appropriate
185
+ comment syntax for the file format. We also recommend that a
186
+ file or class name and description of purpose be included on the
187
+ same "printed page" as the copyright notice for easier
188
+ identification within third-party archives.
189
+
190
+ Copyright 2026 Alibaba Cloud
191
+
192
+ Licensed under the Apache License, Version 2.0 (the "License");
193
+ you may not use this file except in compliance with the License.
194
+ You may obtain a copy of the License at
195
+
196
+ http://www.apache.org/licenses/LICENSE-2.0
197
+
198
+ Unless required by applicable law or agreed to in writing, software
199
+ distributed under the License is distributed on an "AS IS" BASIS,
200
+ WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
201
+ See the License for the specific language governing permissions and
202
+ limitations under the License.
README.md ADDED
@@ -0,0 +1,106 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ base_model: Qwen/Qwen3.5-9B
4
+ language:
5
+ - en
6
+ pipeline_tag: text-classification
7
+ tags:
8
+ - decision
9
+ - calibration
10
+ - reasoning
11
+ - speculative-decoding
12
+ - qwen3.5
13
+ ---
14
+
15
+ # Jeeves-9B
16
+
17
+ A Jev-like decision model that reasons before it decides. Give it a state (text or JSON) and yes/no, multiple-choice or rating questions; it writes a reasoning chain per question and returns a calibrated probability for every option.
18
+
19
+ This repository holds the fused weights (Qwen3.5-9B with the LoRA merged), the pointer head, the fitted temperature, and two speculative-decoding drafters. It loads with the Jeeves code, not with `transformers`: the pointer head and the prompt format are part of the model.
20
+
21
+ ## Files
22
+
23
+ | file | contents |
24
+ |---|---|
25
+ | `model-*.safetensors`, `config.json` | fused Qwen3.5-9B weights, bf16 |
26
+ | `head.pt` | pointer head (query and key projections, 256-dim) |
27
+ | `export.json` | temperature (1.859), prompt format, training step and config |
28
+ | `tokenizer.json`, `vocab.json`, `merges.txt`, `tokenizer_config.json`, `chat_template.jinja` | Qwen3.5 tokenizer |
29
+ | `drafter_k4.safetensors` | block-4 drafter, the serving default, bf16 |
30
+ | `drafter_k8.safetensors` | block-8 drafter, faster for single-question requests, bf16 |
31
+ | `drafter_k4.config.json`, `drafter_k8.config.json` | drafter training settings |
32
+ | `LICENSE` | Apache-2.0, inherited from Qwen3.5-9B |
33
+
34
+ ## Usage
35
+
36
+ ```bash
37
+ hf download PostHog/jeeves --local-dir jeeves-weights
38
+ git clone https://github.com/PostHog/jeeves && cd jeeves
39
+ python -m inference.serve --model ../jeeves-weights --drafter ../jeeves-weights/drafter_k4.safetensors --port 8009
40
+ ```
41
+
42
+ ```bash
43
+ curl -s localhost:8009/v1/systemone -H 'content-type: application/json' -d '{
44
+ "state": "I was charged twice for one order.",
45
+ "questions": {
46
+ "billing": {"type": "noul", "instructions": "Is this about billing?"},
47
+ "tone": {"type": "choice", "instructions": "What is the customer'"'"'s tone?", "criteria": {"calm": null, "frustrated": null, "angry": null}}
48
+ }}'
49
+ ```
50
+
51
+ The request and response follow Jev's `/v1/systemone` format. An optional `options` object sets `think`, `max_think` (truncate chains), `nothink_threshold` (skip thinking when the no-think answer is already confident) and `return_reasoning`. Serving needs a CUDA GPU; the FP8 kernel needs Hopper, and `--no-fp8` serves in bf16.
52
+
53
+ ## Results
54
+
55
+ Accuracy with thinking, greedy, 2,560-token cap. Kev-9B and Jev numbers are the ones Kev publishes. JevBench uses the same 231 public items for every model (the sealed judge tier is not included); the other rows use the same sources with different items.
56
+
57
+ | | Kev-9B | Jev | Jeeves-9B |
58
+ |---|---|---|---|
59
+ | Test overall (out-of-domain and held-out) | 0.822 | 0.857 | **0.889** |
60
+ | MMLU-Pro and buried state | 0.579 | **0.800** | 0.746 |
61
+ | JevBench, public tiers | 0.715* | 0.866 | **0.935** |
62
+ | JevBench hard | 0.451* | 0.730 | **0.865** |
63
+
64
+ \* Kev-8B (Qwen3); no Kev-9B JevBench result is published.
65
+
66
+ Without thinking the model scores 0.804 on the Jeeves test split, against 0.840 with it. With the fitted temperature the no-think path has a top-label calibration error of 0.021 and 1.3% confident errors (wrong at p ≥ 0.9).
67
+
68
+ Serving on one H100, 325 dev questions:
69
+
70
+ | setting | accuracy | median / p90 latency |
71
+ |---|---|---|
72
+ | full thinking | 0.825 | 3.3 s / 17.1 s |
73
+ | `max_think` 768, `nothink_threshold` 0.9 | 0.806 | 2.0 s / 5.6 s |
74
+ | no thinking | 0.775 | about 0.3 s |
75
+
76
+ ## Training
77
+
78
+ - **SFT.** LoRA r=16 on every projection plus the pointer head, 2 epochs on 19,126 questions from 12 public datasets and synthetic policy data; half the questions carry a reasoning chain sampled from the base model.
79
+ - **CISPO.** 9,992 RL questions, 8 rollouts each, up to 2,560 thinking tokens. Reward is the probability of the correct option, discounted by up to 10% for long chains. The released checkpoint is step 402 of a 624-step schedule.
80
+ - **Calibration.** One softmax temperature fitted on the dev set.
81
+ - **Drafters.** Diffusion views of the frozen model, inspired by Orthrus, distilled by KL divergence on chains sampled from this model. At one question the block-4 drafter decodes 1.6× faster than graphed greedy decoding and the block-8 drafter 1.76×.
82
+
83
+ A from-scratch reproduction with the released code matched this checkpoint within noise. The training code, dataset build scripts and pinned dataset revisions are in the GitHub repository.
84
+
85
+ ## Limitations
86
+
87
+ - Knowledge questions trail Jev (MMLU 0.793 vs 0.900, MMLU-Pro 0.739 vs 0.840).
88
+ - Thinking is slow at the tail (17 s at p90 with full chains); use `max_think` and `nothink_threshold` when latency matters.
89
+ - About a third of full-length chains hit the token cap without closing; accuracy on those items is lower.
90
+ - Evaluated on English inputs only.
91
+
92
+ ## License
93
+
94
+ The weights are derived from Qwen3.5-9B and are released under its Apache-2.0 license (`LICENSE`). The Jeeves code is MIT licensed.
95
+
96
+ ## Citation
97
+
98
+ ```bibtex
99
+ @software{waltz2026jeeves,
100
+ author = {Waltz, Nicholas P.},
101
+ title = {Jeeves: Reasoning Improves Jev-like Decisions},
102
+ year = {2026},
103
+ url = {https://github.com/PostHog/jeeves},
104
+ note = {Qwen3.5-9B decision model trained with SFT and CISPO, with a block-4 diffusion drafter}
105
+ }
106
+ ```
chat_template.jinja ADDED
@@ -0,0 +1,154 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {%- set image_count = namespace(value=0) %}
2
+ {%- set video_count = namespace(value=0) %}
3
+ {%- macro render_content(content, do_vision_count, is_system_content=false) %}
4
+ {%- if content is string %}
5
+ {{- content }}
6
+ {%- elif content is iterable and content is not mapping %}
7
+ {%- for item in content %}
8
+ {%- if 'image' in item or 'image_url' in item or item.type == 'image' %}
9
+ {%- if is_system_content %}
10
+ {{- raise_exception('System message cannot contain images.') }}
11
+ {%- endif %}
12
+ {%- if do_vision_count %}
13
+ {%- set image_count.value = image_count.value + 1 %}
14
+ {%- endif %}
15
+ {%- if add_vision_id %}
16
+ {{- 'Picture ' ~ image_count.value ~ ': ' }}
17
+ {%- endif %}
18
+ {{- '<|vision_start|><|image_pad|><|vision_end|>' }}
19
+ {%- elif 'video' in item or item.type == 'video' %}
20
+ {%- if is_system_content %}
21
+ {{- raise_exception('System message cannot contain videos.') }}
22
+ {%- endif %}
23
+ {%- if do_vision_count %}
24
+ {%- set video_count.value = video_count.value + 1 %}
25
+ {%- endif %}
26
+ {%- if add_vision_id %}
27
+ {{- 'Video ' ~ video_count.value ~ ': ' }}
28
+ {%- endif %}
29
+ {{- '<|vision_start|><|video_pad|><|vision_end|>' }}
30
+ {%- elif 'text' in item %}
31
+ {{- item.text }}
32
+ {%- else %}
33
+ {{- raise_exception('Unexpected item type in content.') }}
34
+ {%- endif %}
35
+ {%- endfor %}
36
+ {%- elif content is none or content is undefined %}
37
+ {{- '' }}
38
+ {%- else %}
39
+ {{- raise_exception('Unexpected content type.') }}
40
+ {%- endif %}
41
+ {%- endmacro %}
42
+ {%- if not messages %}
43
+ {{- raise_exception('No messages provided.') }}
44
+ {%- endif %}
45
+ {%- if tools and tools is iterable and tools is not mapping %}
46
+ {{- '<|im_start|>system\n' }}
47
+ {{- "# Tools\n\nYou have access to the following functions:\n\n<tools>" }}
48
+ {%- for tool in tools %}
49
+ {{- "\n" }}
50
+ {{- tool | tojson }}
51
+ {%- endfor %}
52
+ {{- "\n</tools>" }}
53
+ {{- '\n\nIf you choose to call a function ONLY reply in the following format with NO suffix:\n\n<tool_call>\n<function=example_function_name>\n<parameter=example_parameter_1>\nvalue_1\n</parameter>\n<parameter=example_parameter_2>\nThis is the value for the second parameter\nthat can span\nmultiple lines\n</parameter>\n</function>\n</tool_call>\n\n<IMPORTANT>\nReminder:\n- Function calls MUST follow the specified format: an inner <function=...></function> block must be nested within <tool_call></tool_call> XML tags\n- Required parameters MUST be specified\n- You may provide optional reasoning for your function call in natural language BEFORE the function call, but NOT after\n- If there is no function call available, answer the question like normal with your current knowledge and do not tell the user about function calls\n</IMPORTANT>' }}
54
+ {%- if messages[0].role == 'system' %}
55
+ {%- set content = render_content(messages[0].content, false, true)|trim %}
56
+ {%- if content %}
57
+ {{- '\n\n' + content }}
58
+ {%- endif %}
59
+ {%- endif %}
60
+ {{- '<|im_end|>\n' }}
61
+ {%- else %}
62
+ {%- if messages[0].role == 'system' %}
63
+ {%- set content = render_content(messages[0].content, false, true)|trim %}
64
+ {{- '<|im_start|>system\n' + content + '<|im_end|>\n' }}
65
+ {%- endif %}
66
+ {%- endif %}
67
+ {%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
68
+ {%- for message in messages[::-1] %}
69
+ {%- set index = (messages|length - 1) - loop.index0 %}
70
+ {%- if ns.multi_step_tool and message.role == "user" %}
71
+ {%- set content = render_content(message.content, false)|trim %}
72
+ {%- if not(content.startswith('<tool_response>') and content.endswith('</tool_response>')) %}
73
+ {%- set ns.multi_step_tool = false %}
74
+ {%- set ns.last_query_index = index %}
75
+ {%- endif %}
76
+ {%- endif %}
77
+ {%- endfor %}
78
+ {%- if ns.multi_step_tool %}
79
+ {{- raise_exception('No user query found in messages.') }}
80
+ {%- endif %}
81
+ {%- for message in messages %}
82
+ {%- set content = render_content(message.content, true)|trim %}
83
+ {%- if message.role == "system" %}
84
+ {%- if not loop.first %}
85
+ {{- raise_exception('System message must be at the beginning.') }}
86
+ {%- endif %}
87
+ {%- elif message.role == "user" %}
88
+ {{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
89
+ {%- elif message.role == "assistant" %}
90
+ {%- set reasoning_content = '' %}
91
+ {%- if message.reasoning_content is string %}
92
+ {%- set reasoning_content = message.reasoning_content %}
93
+ {%- else %}
94
+ {%- if '</think>' in content %}
95
+ {%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
96
+ {%- set content = content.split('</think>')[-1].lstrip('\n') %}
97
+ {%- endif %}
98
+ {%- endif %}
99
+ {%- set reasoning_content = reasoning_content|trim %}
100
+ {%- if loop.index0 > ns.last_query_index %}
101
+ {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content + '\n</think>\n\n' + content }}
102
+ {%- else %}
103
+ {{- '<|im_start|>' + message.role + '\n' + content }}
104
+ {%- endif %}
105
+ {%- if message.tool_calls and message.tool_calls is iterable and message.tool_calls is not mapping %}
106
+ {%- for tool_call in message.tool_calls %}
107
+ {%- if tool_call.function is defined %}
108
+ {%- set tool_call = tool_call.function %}
109
+ {%- endif %}
110
+ {%- if loop.first %}
111
+ {%- if content|trim %}
112
+ {{- '\n\n<tool_call>\n<function=' + tool_call.name + '>\n' }}
113
+ {%- else %}
114
+ {{- '<tool_call>\n<function=' + tool_call.name + '>\n' }}
115
+ {%- endif %}
116
+ {%- else %}
117
+ {{- '\n<tool_call>\n<function=' + tool_call.name + '>\n' }}
118
+ {%- endif %}
119
+ {%- if tool_call.arguments is defined %}
120
+ {%- for args_name, args_value in tool_call.arguments|items %}
121
+ {{- '<parameter=' + args_name + '>\n' }}
122
+ {%- set args_value = args_value | tojson | safe if args_value is mapping or (args_value is sequence and args_value is not string) else args_value | string %}
123
+ {{- args_value }}
124
+ {{- '\n</parameter>\n' }}
125
+ {%- endfor %}
126
+ {%- endif %}
127
+ {{- '</function>\n</tool_call>' }}
128
+ {%- endfor %}
129
+ {%- endif %}
130
+ {{- '<|im_end|>\n' }}
131
+ {%- elif message.role == "tool" %}
132
+ {%- if loop.previtem and loop.previtem.role != "tool" %}
133
+ {{- '<|im_start|>user' }}
134
+ {%- endif %}
135
+ {{- '\n<tool_response>\n' }}
136
+ {{- content }}
137
+ {{- '\n</tool_response>' }}
138
+ {%- if not loop.last and loop.nextitem.role != "tool" %}
139
+ {{- '<|im_end|>\n' }}
140
+ {%- elif loop.last %}
141
+ {{- '<|im_end|>\n' }}
142
+ {%- endif %}
143
+ {%- else %}
144
+ {{- raise_exception('Unexpected message role.') }}
145
+ {%- endif %}
146
+ {%- endfor %}
147
+ {%- if add_generation_prompt %}
148
+ {{- '<|im_start|>assistant\n' }}
149
+ {%- if enable_thinking is defined and enable_thinking is false %}
150
+ {{- '<think>\n\n</think>\n\n' }}
151
+ {%- else %}
152
+ {{- '<think>\n' }}
153
+ {%- endif %}
154
+ {%- endif %}
config.json ADDED
@@ -0,0 +1,61 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "vocab_size": 248320,
3
+ "hidden_size": 4096,
4
+ "intermediate_size": 12288,
5
+ "num_hidden_layers": 32,
6
+ "layer_types": [
7
+ "linear_attention",
8
+ "linear_attention",
9
+ "linear_attention",
10
+ "full_attention",
11
+ "linear_attention",
12
+ "linear_attention",
13
+ "linear_attention",
14
+ "full_attention",
15
+ "linear_attention",
16
+ "linear_attention",
17
+ "linear_attention",
18
+ "full_attention",
19
+ "linear_attention",
20
+ "linear_attention",
21
+ "linear_attention",
22
+ "full_attention",
23
+ "linear_attention",
24
+ "linear_attention",
25
+ "linear_attention",
26
+ "full_attention",
27
+ "linear_attention",
28
+ "linear_attention",
29
+ "linear_attention",
30
+ "full_attention",
31
+ "linear_attention",
32
+ "linear_attention",
33
+ "linear_attention",
34
+ "full_attention",
35
+ "linear_attention",
36
+ "linear_attention",
37
+ "linear_attention",
38
+ "full_attention"
39
+ ],
40
+ "tie_word_embeddings": false,
41
+ "num_attention_heads": 16,
42
+ "num_key_value_heads": 4,
43
+ "head_dim": 256,
44
+ "attention_bias": false,
45
+ "attention_dropout": 0.0,
46
+ "linear_num_key_heads": 16,
47
+ "linear_num_value_heads": 32,
48
+ "linear_key_head_dim": 128,
49
+ "linear_value_head_dim": 128,
50
+ "linear_conv_kernel_dim": 4,
51
+ "rms_norm_eps": 1e-06,
52
+ "hidden_act": "silu",
53
+ "rope_theta": 10000000,
54
+ "partial_rotary_factor": 0.25,
55
+ "max_position_embeddings": 262144,
56
+ "pad_token_id": null,
57
+ "eos_token_id": 248044,
58
+ "bos_token_id": null,
59
+ "dtype": "bfloat16",
60
+ "initializer_range": 0.02
61
+ }
drafter_k4.config.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "model": "runs/rep_fused",
3
+ "tokenizer": "Qwen/Qwen3.5-9B",
4
+ "chains": "data/chains_rep/rep.rank*.jsonl,data/chains_402b/chains.rank*.jsonl",
5
+ "data_dir": "data",
6
+ "out": "runs/orthrus_k4_402_deep",
7
+ "length": 2048,
8
+ "block": 4,
9
+ "delta_mode": "kvattn",
10
+ "blocks": 512,
11
+ "dense": true,
12
+ "batch_size": 2,
13
+ "lr": 0.0003,
14
+ "warmup": 200,
15
+ "steps": 20000,
16
+ "log_every": 100,
17
+ "limit": 0,
18
+ "seed": 0,
19
+ "compile": false,
20
+ "grad_checkpoint": true,
21
+ "profile_steps": 0,
22
+ "init": ""
23
+ }
drafter_k4.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d98c34af8b067f6eb2dec6367f65d451e38178cbd57bb963934c2df3bf72ed7e
3
+ size 3087025136
drafter_k8.config.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "model": "runs/rep_fused",
3
+ "tokenizer": "Qwen/Qwen3.5-9B",
4
+ "chains": "data/chains_rep/rep.rank*.jsonl",
5
+ "data_dir": "data",
6
+ "out": "runs/orthrus_9b_kvattn_k8_402",
7
+ "length": 2048,
8
+ "block": 8,
9
+ "delta_mode": "kvattn",
10
+ "blocks": 512,
11
+ "dense": true,
12
+ "batch_size": 2,
13
+ "lr": 0.00015,
14
+ "warmup": 100,
15
+ "steps": 2500,
16
+ "log_every": 100,
17
+ "limit": 0,
18
+ "seed": 0,
19
+ "compile": false,
20
+ "grad_checkpoint": true,
21
+ "profile_steps": 0,
22
+ "init": "runs/orthrus_9b_kvattn_k8/orthrus.safetensors"
23
+ }
drafter_k8.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:46ab9b9ae99be8dd924af9dba25c2095756d0348b00764db2eb97f85f5e33c82
3
+ size 3087025136
export.json ADDED
@@ -0,0 +1,111 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "source_checkpoint": "runs/best_step402",
3
+ "base_model": "Qwen/Qwen3.5-9B",
4
+ "dtype": "bfloat16",
5
+ "format": "markers-v3-plainchains",
6
+ "head_dim": 256,
7
+ "temperature": 1.8589280843734741,
8
+ "stage": "cispo",
9
+ "step": 402,
10
+ "sources": {
11
+ "banking77": 0,
12
+ "boolq": 1,
13
+ "agnews": 2,
14
+ "mnli": 3,
15
+ "sst5": 4,
16
+ "yelp": 5,
17
+ "trec": 6,
18
+ "dbpedia14": 7,
19
+ "amazon": 8,
20
+ "imdb": 9,
21
+ "mmlu": 10,
22
+ "emotion": 11,
23
+ "tweet_offensive": 12,
24
+ "qnli": 13,
25
+ "paws": 14,
26
+ "sciq": 15,
27
+ "contrastive": 16,
28
+ "compositional": 17,
29
+ "composition_holdout": 18,
30
+ "semif": 19,
31
+ "wanli": 20,
32
+ "mmlu_pro": 21,
33
+ "buried": 22,
34
+ "unknowable": 23,
35
+ "unknowable_control": 24,
36
+ "night2_assertion": 25,
37
+ "night2_dates": 26,
38
+ "night2_unknowable": 27,
39
+ "night2_unknowable_control": 28
40
+ },
41
+ "metrics": null,
42
+ "training_config": {
43
+ "stage": "cispo",
44
+ "run_dir": "runs/cispo_rep",
45
+ "data_dir": "data",
46
+ "model": "Qwen/Qwen3.5-9B",
47
+ "init": "runs/sft_v4/final",
48
+ "resume": null,
49
+ "lora_r": 16,
50
+ "lora_alpha": 32.0,
51
+ "lora_dropout": 0.0,
52
+ "head_dim": 256,
53
+ "lr": 5e-05,
54
+ "head_lr": 0.0001,
55
+ "weight_decay": 0.0,
56
+ "warmup": 20,
57
+ "epochs": 4,
58
+ "max_steps": 0,
59
+ "batch_size": 8,
60
+ "grad_clip": 1.0,
61
+ "max_len": 4096,
62
+ "max_seq_len": 8192,
63
+ "train_limit": 0,
64
+ "dev_limit": 0,
65
+ "eval_every": 50,
66
+ "eval_batch_size": 16,
67
+ "eval_think": true,
68
+ "eval_think_limit": 256,
69
+ "log_every": 10,
70
+ "seed": 0,
71
+ "gradient_checkpointing": true,
72
+ "prompts_per_step": 8,
73
+ "group": 8,
74
+ "nothink_per_group": 0,
75
+ "nothink_start_epoch": 1,
76
+ "max_think": 2560,
77
+ "temperature": 1.0,
78
+ "top_p": 1.0,
79
+ "eps_high": 0.2,
80
+ "updates": 1,
81
+ "train_mix_frac": 0.0,
82
+ "rollout_ce_weight": 0.5,
83
+ "anchor_ce_weight": 0.5,
84
+ "anchor_batch": 8,
85
+ "gen_batch_size": 64,
86
+ "logprob_chunk": 128,
87
+ "micro_groups": 2,
88
+ "length_hinge": 2048,
89
+ "length_hinge_end": 1024,
90
+ "length_ramp": 0,
91
+ "length_penalty_weight": 1.0,
92
+ "length_penalty_cap": 0.1,
93
+ "length_penalty_correct_only": true,
94
+ "length_hinge2": 0,
95
+ "length_hinge2_end": 1792,
96
+ "length_penalty2_weight": 0.0,
97
+ "closure_reward": 0.0,
98
+ "pad_multiple": 128,
99
+ "num_workers": 2,
100
+ "compile": true,
101
+ "graph_decode": true,
102
+ "async_rollouts": true,
103
+ "ckpt_minutes": 45.0,
104
+ "log_rollouts": 3,
105
+ "log_chain_chars": 1200,
106
+ "sft_think_frac": 0.5,
107
+ "chain_cache": "data/chains",
108
+ "filter_active": false,
109
+ "filter_min_spread": 0.02
110
+ }
111
+ }
head.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2ab935dea9eecf263086d9ed6dfe97fd5558193663ecae102fd3c50ae6878d60
3
+ size 8392767
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
model-00001-of-00005.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c8d38178b51c845d6befca9e2c8a579889055cecf510fdbc85dbdf7bb867a0d6
3
+ size 4268059288
model-00002-of-00005.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a25e1a608a5be9cadef95e3f40fdca5c17b6c21e86481186adfd7a8a1f5b8f40
3
+ size 4266315424
model-00003-of-00005.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ab693e0b5940052ad04450fccfd12c87a49ce9ad23984bdfc07ee20d3ab654fe
3
+ size 4215378072
model-00004-of-00005.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9942b7369222a4403809a05f1da21f53b006f2d5cf72651483dda48c4931ed9a
3
+ size 3123665648
model-00005-of-00005.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dd63614f1dc80dce2d83be3f3e69af1f8a0ebc8add9b8e0abf3910f563e44344
3
+ size 2034237568
model.safetensors.index.json ADDED
@@ -0,0 +1,434 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 17907606528
4
+ },
5
+ "weight_map": {
6
+ "model.embed_tokens.weight": "model-00001-of-00005.safetensors",
7
+ "model.layers.0.linear_attn.dt_bias": "model-00001-of-00005.safetensors",
8
+ "model.layers.0.linear_attn.A_log": "model-00001-of-00005.safetensors",
9
+ "model.layers.0.linear_attn.in_proj_qkv.weight": "model-00001-of-00005.safetensors",
10
+ "model.layers.0.linear_attn.in_proj_z.weight": "model-00001-of-00005.safetensors",
11
+ "model.layers.0.linear_attn.in_proj_b.weight": "model-00001-of-00005.safetensors",
12
+ "model.layers.0.linear_attn.in_proj_a.weight": "model-00001-of-00005.safetensors",
13
+ "model.layers.0.linear_attn.conv1d.weight": "model-00001-of-00005.safetensors",
14
+ "model.layers.0.linear_attn.norm.weight": "model-00001-of-00005.safetensors",
15
+ "model.layers.0.linear_attn.out_proj.weight": "model-00001-of-00005.safetensors",
16
+ "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
17
+ "model.layers.0.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
18
+ "model.layers.0.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
19
+ "model.layers.0.input_layernorm.weight": "model-00001-of-00005.safetensors",
20
+ "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
21
+ "model.layers.1.linear_attn.dt_bias": "model-00001-of-00005.safetensors",
22
+ "model.layers.1.linear_attn.A_log": "model-00001-of-00005.safetensors",
23
+ "model.layers.1.linear_attn.in_proj_qkv.weight": "model-00001-of-00005.safetensors",
24
+ "model.layers.1.linear_attn.in_proj_z.weight": "model-00001-of-00005.safetensors",
25
+ "model.layers.1.linear_attn.in_proj_b.weight": "model-00001-of-00005.safetensors",
26
+ "model.layers.1.linear_attn.in_proj_a.weight": "model-00001-of-00005.safetensors",
27
+ "model.layers.1.linear_attn.conv1d.weight": "model-00001-of-00005.safetensors",
28
+ "model.layers.1.linear_attn.norm.weight": "model-00001-of-00005.safetensors",
29
+ "model.layers.1.linear_attn.out_proj.weight": "model-00001-of-00005.safetensors",
30
+ "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
31
+ "model.layers.1.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
32
+ "model.layers.1.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
33
+ "model.layers.1.input_layernorm.weight": "model-00001-of-00005.safetensors",
34
+ "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
35
+ "model.layers.2.linear_attn.dt_bias": "model-00001-of-00005.safetensors",
36
+ "model.layers.2.linear_attn.A_log": "model-00001-of-00005.safetensors",
37
+ "model.layers.2.linear_attn.in_proj_qkv.weight": "model-00001-of-00005.safetensors",
38
+ "model.layers.2.linear_attn.in_proj_z.weight": "model-00001-of-00005.safetensors",
39
+ "model.layers.2.linear_attn.in_proj_b.weight": "model-00001-of-00005.safetensors",
40
+ "model.layers.2.linear_attn.in_proj_a.weight": "model-00001-of-00005.safetensors",
41
+ "model.layers.2.linear_attn.conv1d.weight": "model-00001-of-00005.safetensors",
42
+ "model.layers.2.linear_attn.norm.weight": "model-00001-of-00005.safetensors",
43
+ "model.layers.2.linear_attn.out_proj.weight": "model-00001-of-00005.safetensors",
44
+ "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
45
+ "model.layers.2.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
46
+ "model.layers.2.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
47
+ "model.layers.2.input_layernorm.weight": "model-00001-of-00005.safetensors",
48
+ "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
49
+ "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
50
+ "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
51
+ "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
52
+ "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
53
+ "model.layers.3.self_attn.q_norm.weight": "model-00001-of-00005.safetensors",
54
+ "model.layers.3.self_attn.k_norm.weight": "model-00001-of-00005.safetensors",
55
+ "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
56
+ "model.layers.3.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
57
+ "model.layers.3.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
58
+ "model.layers.3.input_layernorm.weight": "model-00001-of-00005.safetensors",
59
+ "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
60
+ "model.layers.4.linear_attn.dt_bias": "model-00001-of-00005.safetensors",
61
+ "model.layers.4.linear_attn.A_log": "model-00001-of-00005.safetensors",
62
+ "model.layers.4.linear_attn.in_proj_qkv.weight": "model-00001-of-00005.safetensors",
63
+ "model.layers.4.linear_attn.in_proj_z.weight": "model-00001-of-00005.safetensors",
64
+ "model.layers.4.linear_attn.in_proj_b.weight": "model-00001-of-00005.safetensors",
65
+ "model.layers.4.linear_attn.in_proj_a.weight": "model-00001-of-00005.safetensors",
66
+ "model.layers.4.linear_attn.conv1d.weight": "model-00001-of-00005.safetensors",
67
+ "model.layers.4.linear_attn.norm.weight": "model-00001-of-00005.safetensors",
68
+ "model.layers.4.linear_attn.out_proj.weight": "model-00001-of-00005.safetensors",
69
+ "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
70
+ "model.layers.4.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
71
+ "model.layers.4.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
72
+ "model.layers.4.input_layernorm.weight": "model-00001-of-00005.safetensors",
73
+ "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
74
+ "model.layers.5.linear_attn.dt_bias": "model-00001-of-00005.safetensors",
75
+ "model.layers.5.linear_attn.A_log": "model-00001-of-00005.safetensors",
76
+ "model.layers.5.linear_attn.in_proj_qkv.weight": "model-00001-of-00005.safetensors",
77
+ "model.layers.5.linear_attn.in_proj_z.weight": "model-00002-of-00005.safetensors",
78
+ "model.layers.5.linear_attn.in_proj_b.weight": "model-00002-of-00005.safetensors",
79
+ "model.layers.5.linear_attn.in_proj_a.weight": "model-00002-of-00005.safetensors",
80
+ "model.layers.5.linear_attn.conv1d.weight": "model-00002-of-00005.safetensors",
81
+ "model.layers.5.linear_attn.norm.weight": "model-00002-of-00005.safetensors",
82
+ "model.layers.5.linear_attn.out_proj.weight": "model-00002-of-00005.safetensors",
83
+ "model.layers.5.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
84
+ "model.layers.5.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
85
+ "model.layers.5.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
86
+ "model.layers.5.input_layernorm.weight": "model-00002-of-00005.safetensors",
87
+ "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
88
+ "model.layers.6.linear_attn.dt_bias": "model-00002-of-00005.safetensors",
89
+ "model.layers.6.linear_attn.A_log": "model-00002-of-00005.safetensors",
90
+ "model.layers.6.linear_attn.in_proj_qkv.weight": "model-00002-of-00005.safetensors",
91
+ "model.layers.6.linear_attn.in_proj_z.weight": "model-00002-of-00005.safetensors",
92
+ "model.layers.6.linear_attn.in_proj_b.weight": "model-00002-of-00005.safetensors",
93
+ "model.layers.6.linear_attn.in_proj_a.weight": "model-00002-of-00005.safetensors",
94
+ "model.layers.6.linear_attn.conv1d.weight": "model-00002-of-00005.safetensors",
95
+ "model.layers.6.linear_attn.norm.weight": "model-00002-of-00005.safetensors",
96
+ "model.layers.6.linear_attn.out_proj.weight": "model-00002-of-00005.safetensors",
97
+ "model.layers.6.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
98
+ "model.layers.6.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
99
+ "model.layers.6.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
100
+ "model.layers.6.input_layernorm.weight": "model-00002-of-00005.safetensors",
101
+ "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
102
+ "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
103
+ "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
104
+ "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
105
+ "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
106
+ "model.layers.7.self_attn.q_norm.weight": "model-00002-of-00005.safetensors",
107
+ "model.layers.7.self_attn.k_norm.weight": "model-00002-of-00005.safetensors",
108
+ "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
109
+ "model.layers.7.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
110
+ "model.layers.7.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
111
+ "model.layers.7.input_layernorm.weight": "model-00002-of-00005.safetensors",
112
+ "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
113
+ "model.layers.8.linear_attn.dt_bias": "model-00002-of-00005.safetensors",
114
+ "model.layers.8.linear_attn.A_log": "model-00002-of-00005.safetensors",
115
+ "model.layers.8.linear_attn.in_proj_qkv.weight": "model-00002-of-00005.safetensors",
116
+ "model.layers.8.linear_attn.in_proj_z.weight": "model-00002-of-00005.safetensors",
117
+ "model.layers.8.linear_attn.in_proj_b.weight": "model-00002-of-00005.safetensors",
118
+ "model.layers.8.linear_attn.in_proj_a.weight": "model-00002-of-00005.safetensors",
119
+ "model.layers.8.linear_attn.conv1d.weight": "model-00002-of-00005.safetensors",
120
+ "model.layers.8.linear_attn.norm.weight": "model-00002-of-00005.safetensors",
121
+ "model.layers.8.linear_attn.out_proj.weight": "model-00002-of-00005.safetensors",
122
+ "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
123
+ "model.layers.8.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
124
+ "model.layers.8.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
125
+ "model.layers.8.input_layernorm.weight": "model-00002-of-00005.safetensors",
126
+ "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
127
+ "model.layers.9.linear_attn.dt_bias": "model-00002-of-00005.safetensors",
128
+ "model.layers.9.linear_attn.A_log": "model-00002-of-00005.safetensors",
129
+ "model.layers.9.linear_attn.in_proj_qkv.weight": "model-00002-of-00005.safetensors",
130
+ "model.layers.9.linear_attn.in_proj_z.weight": "model-00002-of-00005.safetensors",
131
+ "model.layers.9.linear_attn.in_proj_b.weight": "model-00002-of-00005.safetensors",
132
+ "model.layers.9.linear_attn.in_proj_a.weight": "model-00002-of-00005.safetensors",
133
+ "model.layers.9.linear_attn.conv1d.weight": "model-00002-of-00005.safetensors",
134
+ "model.layers.9.linear_attn.norm.weight": "model-00002-of-00005.safetensors",
135
+ "model.layers.9.linear_attn.out_proj.weight": "model-00002-of-00005.safetensors",
136
+ "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
137
+ "model.layers.9.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
138
+ "model.layers.9.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
139
+ "model.layers.9.input_layernorm.weight": "model-00002-of-00005.safetensors",
140
+ "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
141
+ "model.layers.10.linear_attn.dt_bias": "model-00002-of-00005.safetensors",
142
+ "model.layers.10.linear_attn.A_log": "model-00002-of-00005.safetensors",
143
+ "model.layers.10.linear_attn.in_proj_qkv.weight": "model-00002-of-00005.safetensors",
144
+ "model.layers.10.linear_attn.in_proj_z.weight": "model-00002-of-00005.safetensors",
145
+ "model.layers.10.linear_attn.in_proj_b.weight": "model-00002-of-00005.safetensors",
146
+ "model.layers.10.linear_attn.in_proj_a.weight": "model-00002-of-00005.safetensors",
147
+ "model.layers.10.linear_attn.conv1d.weight": "model-00002-of-00005.safetensors",
148
+ "model.layers.10.linear_attn.norm.weight": "model-00002-of-00005.safetensors",
149
+ "model.layers.10.linear_attn.out_proj.weight": "model-00002-of-00005.safetensors",
150
+ "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
151
+ "model.layers.10.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
152
+ "model.layers.10.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
153
+ "model.layers.10.input_layernorm.weight": "model-00002-of-00005.safetensors",
154
+ "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
155
+ "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
156
+ "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
157
+ "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
158
+ "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
159
+ "model.layers.11.self_attn.q_norm.weight": "model-00002-of-00005.safetensors",
160
+ "model.layers.11.self_attn.k_norm.weight": "model-00002-of-00005.safetensors",
161
+ "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
162
+ "model.layers.11.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
163
+ "model.layers.11.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
164
+ "model.layers.11.input_layernorm.weight": "model-00002-of-00005.safetensors",
165
+ "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
166
+ "model.layers.12.linear_attn.dt_bias": "model-00002-of-00005.safetensors",
167
+ "model.layers.12.linear_attn.A_log": "model-00002-of-00005.safetensors",
168
+ "model.layers.12.linear_attn.in_proj_qkv.weight": "model-00002-of-00005.safetensors",
169
+ "model.layers.12.linear_attn.in_proj_z.weight": "model-00002-of-00005.safetensors",
170
+ "model.layers.12.linear_attn.in_proj_b.weight": "model-00002-of-00005.safetensors",
171
+ "model.layers.12.linear_attn.in_proj_a.weight": "model-00002-of-00005.safetensors",
172
+ "model.layers.12.linear_attn.conv1d.weight": "model-00002-of-00005.safetensors",
173
+ "model.layers.12.linear_attn.norm.weight": "model-00002-of-00005.safetensors",
174
+ "model.layers.12.linear_attn.out_proj.weight": "model-00002-of-00005.safetensors",
175
+ "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
176
+ "model.layers.12.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
177
+ "model.layers.12.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
178
+ "model.layers.12.input_layernorm.weight": "model-00002-of-00005.safetensors",
179
+ "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
180
+ "model.layers.13.linear_attn.dt_bias": "model-00002-of-00005.safetensors",
181
+ "model.layers.13.linear_attn.A_log": "model-00002-of-00005.safetensors",
182
+ "model.layers.13.linear_attn.in_proj_qkv.weight": "model-00002-of-00005.safetensors",
183
+ "model.layers.13.linear_attn.in_proj_z.weight": "model-00002-of-00005.safetensors",
184
+ "model.layers.13.linear_attn.in_proj_b.weight": "model-00002-of-00005.safetensors",
185
+ "model.layers.13.linear_attn.in_proj_a.weight": "model-00002-of-00005.safetensors",
186
+ "model.layers.13.linear_attn.conv1d.weight": "model-00002-of-00005.safetensors",
187
+ "model.layers.13.linear_attn.norm.weight": "model-00002-of-00005.safetensors",
188
+ "model.layers.13.linear_attn.out_proj.weight": "model-00002-of-00005.safetensors",
189
+ "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
190
+ "model.layers.13.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
191
+ "model.layers.13.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
192
+ "model.layers.13.input_layernorm.weight": "model-00002-of-00005.safetensors",
193
+ "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
194
+ "model.layers.14.linear_attn.dt_bias": "model-00002-of-00005.safetensors",
195
+ "model.layers.14.linear_attn.A_log": "model-00002-of-00005.safetensors",
196
+ "model.layers.14.linear_attn.in_proj_qkv.weight": "model-00002-of-00005.safetensors",
197
+ "model.layers.14.linear_attn.in_proj_z.weight": "model-00002-of-00005.safetensors",
198
+ "model.layers.14.linear_attn.in_proj_b.weight": "model-00002-of-00005.safetensors",
199
+ "model.layers.14.linear_attn.in_proj_a.weight": "model-00002-of-00005.safetensors",
200
+ "model.layers.14.linear_attn.conv1d.weight": "model-00002-of-00005.safetensors",
201
+ "model.layers.14.linear_attn.norm.weight": "model-00002-of-00005.safetensors",
202
+ "model.layers.14.linear_attn.out_proj.weight": "model-00002-of-00005.safetensors",
203
+ "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
204
+ "model.layers.14.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
205
+ "model.layers.14.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
206
+ "model.layers.14.input_layernorm.weight": "model-00002-of-00005.safetensors",
207
+ "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
208
+ "model.layers.15.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
209
+ "model.layers.15.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
210
+ "model.layers.15.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
211
+ "model.layers.15.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
212
+ "model.layers.15.self_attn.q_norm.weight": "model-00003-of-00005.safetensors",
213
+ "model.layers.15.self_attn.k_norm.weight": "model-00003-of-00005.safetensors",
214
+ "model.layers.15.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
215
+ "model.layers.15.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
216
+ "model.layers.15.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
217
+ "model.layers.15.input_layernorm.weight": "model-00003-of-00005.safetensors",
218
+ "model.layers.15.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
219
+ "model.layers.16.linear_attn.dt_bias": "model-00003-of-00005.safetensors",
220
+ "model.layers.16.linear_attn.A_log": "model-00003-of-00005.safetensors",
221
+ "model.layers.16.linear_attn.in_proj_qkv.weight": "model-00003-of-00005.safetensors",
222
+ "model.layers.16.linear_attn.in_proj_z.weight": "model-00003-of-00005.safetensors",
223
+ "model.layers.16.linear_attn.in_proj_b.weight": "model-00003-of-00005.safetensors",
224
+ "model.layers.16.linear_attn.in_proj_a.weight": "model-00003-of-00005.safetensors",
225
+ "model.layers.16.linear_attn.conv1d.weight": "model-00003-of-00005.safetensors",
226
+ "model.layers.16.linear_attn.norm.weight": "model-00003-of-00005.safetensors",
227
+ "model.layers.16.linear_attn.out_proj.weight": "model-00003-of-00005.safetensors",
228
+ "model.layers.16.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
229
+ "model.layers.16.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
230
+ "model.layers.16.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
231
+ "model.layers.16.input_layernorm.weight": "model-00003-of-00005.safetensors",
232
+ "model.layers.16.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
233
+ "model.layers.17.linear_attn.dt_bias": "model-00003-of-00005.safetensors",
234
+ "model.layers.17.linear_attn.A_log": "model-00003-of-00005.safetensors",
235
+ "model.layers.17.linear_attn.in_proj_qkv.weight": "model-00003-of-00005.safetensors",
236
+ "model.layers.17.linear_attn.in_proj_z.weight": "model-00003-of-00005.safetensors",
237
+ "model.layers.17.linear_attn.in_proj_b.weight": "model-00003-of-00005.safetensors",
238
+ "model.layers.17.linear_attn.in_proj_a.weight": "model-00003-of-00005.safetensors",
239
+ "model.layers.17.linear_attn.conv1d.weight": "model-00003-of-00005.safetensors",
240
+ "model.layers.17.linear_attn.norm.weight": "model-00003-of-00005.safetensors",
241
+ "model.layers.17.linear_attn.out_proj.weight": "model-00003-of-00005.safetensors",
242
+ "model.layers.17.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
243
+ "model.layers.17.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
244
+ "model.layers.17.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
245
+ "model.layers.17.input_layernorm.weight": "model-00003-of-00005.safetensors",
246
+ "model.layers.17.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
247
+ "model.layers.18.linear_attn.dt_bias": "model-00003-of-00005.safetensors",
248
+ "model.layers.18.linear_attn.A_log": "model-00003-of-00005.safetensors",
249
+ "model.layers.18.linear_attn.in_proj_qkv.weight": "model-00003-of-00005.safetensors",
250
+ "model.layers.18.linear_attn.in_proj_z.weight": "model-00003-of-00005.safetensors",
251
+ "model.layers.18.linear_attn.in_proj_b.weight": "model-00003-of-00005.safetensors",
252
+ "model.layers.18.linear_attn.in_proj_a.weight": "model-00003-of-00005.safetensors",
253
+ "model.layers.18.linear_attn.conv1d.weight": "model-00003-of-00005.safetensors",
254
+ "model.layers.18.linear_attn.norm.weight": "model-00003-of-00005.safetensors",
255
+ "model.layers.18.linear_attn.out_proj.weight": "model-00003-of-00005.safetensors",
256
+ "model.layers.18.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
257
+ "model.layers.18.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
258
+ "model.layers.18.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
259
+ "model.layers.18.input_layernorm.weight": "model-00003-of-00005.safetensors",
260
+ "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
261
+ "model.layers.19.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
262
+ "model.layers.19.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
263
+ "model.layers.19.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
264
+ "model.layers.19.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
265
+ "model.layers.19.self_attn.q_norm.weight": "model-00003-of-00005.safetensors",
266
+ "model.layers.19.self_attn.k_norm.weight": "model-00003-of-00005.safetensors",
267
+ "model.layers.19.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
268
+ "model.layers.19.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
269
+ "model.layers.19.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
270
+ "model.layers.19.input_layernorm.weight": "model-00003-of-00005.safetensors",
271
+ "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
272
+ "model.layers.20.linear_attn.dt_bias": "model-00003-of-00005.safetensors",
273
+ "model.layers.20.linear_attn.A_log": "model-00003-of-00005.safetensors",
274
+ "model.layers.20.linear_attn.in_proj_qkv.weight": "model-00003-of-00005.safetensors",
275
+ "model.layers.20.linear_attn.in_proj_z.weight": "model-00003-of-00005.safetensors",
276
+ "model.layers.20.linear_attn.in_proj_b.weight": "model-00003-of-00005.safetensors",
277
+ "model.layers.20.linear_attn.in_proj_a.weight": "model-00003-of-00005.safetensors",
278
+ "model.layers.20.linear_attn.conv1d.weight": "model-00003-of-00005.safetensors",
279
+ "model.layers.20.linear_attn.norm.weight": "model-00003-of-00005.safetensors",
280
+ "model.layers.20.linear_attn.out_proj.weight": "model-00003-of-00005.safetensors",
281
+ "model.layers.20.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
282
+ "model.layers.20.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
283
+ "model.layers.20.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
284
+ "model.layers.20.input_layernorm.weight": "model-00003-of-00005.safetensors",
285
+ "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
286
+ "model.layers.21.linear_attn.dt_bias": "model-00003-of-00005.safetensors",
287
+ "model.layers.21.linear_attn.A_log": "model-00003-of-00005.safetensors",
288
+ "model.layers.21.linear_attn.in_proj_qkv.weight": "model-00003-of-00005.safetensors",
289
+ "model.layers.21.linear_attn.in_proj_z.weight": "model-00003-of-00005.safetensors",
290
+ "model.layers.21.linear_attn.in_proj_b.weight": "model-00003-of-00005.safetensors",
291
+ "model.layers.21.linear_attn.in_proj_a.weight": "model-00003-of-00005.safetensors",
292
+ "model.layers.21.linear_attn.conv1d.weight": "model-00003-of-00005.safetensors",
293
+ "model.layers.21.linear_attn.norm.weight": "model-00003-of-00005.safetensors",
294
+ "model.layers.21.linear_attn.out_proj.weight": "model-00003-of-00005.safetensors",
295
+ "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
296
+ "model.layers.21.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
297
+ "model.layers.21.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
298
+ "model.layers.21.input_layernorm.weight": "model-00003-of-00005.safetensors",
299
+ "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
300
+ "model.layers.22.linear_attn.dt_bias": "model-00003-of-00005.safetensors",
301
+ "model.layers.22.linear_attn.A_log": "model-00003-of-00005.safetensors",
302
+ "model.layers.22.linear_attn.in_proj_qkv.weight": "model-00003-of-00005.safetensors",
303
+ "model.layers.22.linear_attn.in_proj_z.weight": "model-00003-of-00005.safetensors",
304
+ "model.layers.22.linear_attn.in_proj_b.weight": "model-00003-of-00005.safetensors",
305
+ "model.layers.22.linear_attn.in_proj_a.weight": "model-00003-of-00005.safetensors",
306
+ "model.layers.22.linear_attn.conv1d.weight": "model-00003-of-00005.safetensors",
307
+ "model.layers.22.linear_attn.norm.weight": "model-00003-of-00005.safetensors",
308
+ "model.layers.22.linear_attn.out_proj.weight": "model-00003-of-00005.safetensors",
309
+ "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
310
+ "model.layers.22.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
311
+ "model.layers.22.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
312
+ "model.layers.22.input_layernorm.weight": "model-00003-of-00005.safetensors",
313
+ "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
314
+ "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
315
+ "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
316
+ "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
317
+ "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
318
+ "model.layers.23.self_attn.q_norm.weight": "model-00003-of-00005.safetensors",
319
+ "model.layers.23.self_attn.k_norm.weight": "model-00003-of-00005.safetensors",
320
+ "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
321
+ "model.layers.23.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
322
+ "model.layers.23.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
323
+ "model.layers.23.input_layernorm.weight": "model-00003-of-00005.safetensors",
324
+ "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
325
+ "model.layers.24.linear_attn.dt_bias": "model-00003-of-00005.safetensors",
326
+ "model.layers.24.linear_attn.A_log": "model-00003-of-00005.safetensors",
327
+ "model.layers.24.linear_attn.in_proj_qkv.weight": "model-00003-of-00005.safetensors",
328
+ "model.layers.24.linear_attn.in_proj_z.weight": "model-00003-of-00005.safetensors",
329
+ "model.layers.24.linear_attn.in_proj_b.weight": "model-00003-of-00005.safetensors",
330
+ "model.layers.24.linear_attn.in_proj_a.weight": "model-00003-of-00005.safetensors",
331
+ "model.layers.24.linear_attn.conv1d.weight": "model-00003-of-00005.safetensors",
332
+ "model.layers.24.linear_attn.norm.weight": "model-00003-of-00005.safetensors",
333
+ "model.layers.24.linear_attn.out_proj.weight": "model-00003-of-00005.safetensors",
334
+ "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
335
+ "model.layers.24.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
336
+ "model.layers.24.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
337
+ "model.layers.24.input_layernorm.weight": "model-00004-of-00005.safetensors",
338
+ "model.layers.24.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
339
+ "model.layers.25.linear_attn.dt_bias": "model-00004-of-00005.safetensors",
340
+ "model.layers.25.linear_attn.A_log": "model-00004-of-00005.safetensors",
341
+ "model.layers.25.linear_attn.in_proj_qkv.weight": "model-00004-of-00005.safetensors",
342
+ "model.layers.25.linear_attn.in_proj_z.weight": "model-00004-of-00005.safetensors",
343
+ "model.layers.25.linear_attn.in_proj_b.weight": "model-00004-of-00005.safetensors",
344
+ "model.layers.25.linear_attn.in_proj_a.weight": "model-00004-of-00005.safetensors",
345
+ "model.layers.25.linear_attn.conv1d.weight": "model-00004-of-00005.safetensors",
346
+ "model.layers.25.linear_attn.norm.weight": "model-00004-of-00005.safetensors",
347
+ "model.layers.25.linear_attn.out_proj.weight": "model-00004-of-00005.safetensors",
348
+ "model.layers.25.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
349
+ "model.layers.25.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
350
+ "model.layers.25.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
351
+ "model.layers.25.input_layernorm.weight": "model-00004-of-00005.safetensors",
352
+ "model.layers.25.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
353
+ "model.layers.26.linear_attn.dt_bias": "model-00004-of-00005.safetensors",
354
+ "model.layers.26.linear_attn.A_log": "model-00004-of-00005.safetensors",
355
+ "model.layers.26.linear_attn.in_proj_qkv.weight": "model-00004-of-00005.safetensors",
356
+ "model.layers.26.linear_attn.in_proj_z.weight": "model-00004-of-00005.safetensors",
357
+ "model.layers.26.linear_attn.in_proj_b.weight": "model-00004-of-00005.safetensors",
358
+ "model.layers.26.linear_attn.in_proj_a.weight": "model-00004-of-00005.safetensors",
359
+ "model.layers.26.linear_attn.conv1d.weight": "model-00004-of-00005.safetensors",
360
+ "model.layers.26.linear_attn.norm.weight": "model-00004-of-00005.safetensors",
361
+ "model.layers.26.linear_attn.out_proj.weight": "model-00004-of-00005.safetensors",
362
+ "model.layers.26.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
363
+ "model.layers.26.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
364
+ "model.layers.26.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
365
+ "model.layers.26.input_layernorm.weight": "model-00004-of-00005.safetensors",
366
+ "model.layers.26.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
367
+ "model.layers.27.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
368
+ "model.layers.27.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
369
+ "model.layers.27.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
370
+ "model.layers.27.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
371
+ "model.layers.27.self_attn.q_norm.weight": "model-00004-of-00005.safetensors",
372
+ "model.layers.27.self_attn.k_norm.weight": "model-00004-of-00005.safetensors",
373
+ "model.layers.27.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
374
+ "model.layers.27.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
375
+ "model.layers.27.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
376
+ "model.layers.27.input_layernorm.weight": "model-00004-of-00005.safetensors",
377
+ "model.layers.27.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
378
+ "model.layers.28.linear_attn.dt_bias": "model-00004-of-00005.safetensors",
379
+ "model.layers.28.linear_attn.A_log": "model-00004-of-00005.safetensors",
380
+ "model.layers.28.linear_attn.in_proj_qkv.weight": "model-00004-of-00005.safetensors",
381
+ "model.layers.28.linear_attn.in_proj_z.weight": "model-00004-of-00005.safetensors",
382
+ "model.layers.28.linear_attn.in_proj_b.weight": "model-00004-of-00005.safetensors",
383
+ "model.layers.28.linear_attn.in_proj_a.weight": "model-00004-of-00005.safetensors",
384
+ "model.layers.28.linear_attn.conv1d.weight": "model-00004-of-00005.safetensors",
385
+ "model.layers.28.linear_attn.norm.weight": "model-00004-of-00005.safetensors",
386
+ "model.layers.28.linear_attn.out_proj.weight": "model-00004-of-00005.safetensors",
387
+ "model.layers.28.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
388
+ "model.layers.28.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
389
+ "model.layers.28.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
390
+ "model.layers.28.input_layernorm.weight": "model-00004-of-00005.safetensors",
391
+ "model.layers.28.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
392
+ "model.layers.29.linear_attn.dt_bias": "model-00004-of-00005.safetensors",
393
+ "model.layers.29.linear_attn.A_log": "model-00004-of-00005.safetensors",
394
+ "model.layers.29.linear_attn.in_proj_qkv.weight": "model-00004-of-00005.safetensors",
395
+ "model.layers.29.linear_attn.in_proj_z.weight": "model-00004-of-00005.safetensors",
396
+ "model.layers.29.linear_attn.in_proj_b.weight": "model-00004-of-00005.safetensors",
397
+ "model.layers.29.linear_attn.in_proj_a.weight": "model-00004-of-00005.safetensors",
398
+ "model.layers.29.linear_attn.conv1d.weight": "model-00004-of-00005.safetensors",
399
+ "model.layers.29.linear_attn.norm.weight": "model-00004-of-00005.safetensors",
400
+ "model.layers.29.linear_attn.out_proj.weight": "model-00004-of-00005.safetensors",
401
+ "model.layers.29.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
402
+ "model.layers.29.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
403
+ "model.layers.29.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
404
+ "model.layers.29.input_layernorm.weight": "model-00004-of-00005.safetensors",
405
+ "model.layers.29.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
406
+ "model.layers.30.linear_attn.dt_bias": "model-00004-of-00005.safetensors",
407
+ "model.layers.30.linear_attn.A_log": "model-00004-of-00005.safetensors",
408
+ "model.layers.30.linear_attn.in_proj_qkv.weight": "model-00004-of-00005.safetensors",
409
+ "model.layers.30.linear_attn.in_proj_z.weight": "model-00004-of-00005.safetensors",
410
+ "model.layers.30.linear_attn.in_proj_b.weight": "model-00004-of-00005.safetensors",
411
+ "model.layers.30.linear_attn.in_proj_a.weight": "model-00004-of-00005.safetensors",
412
+ "model.layers.30.linear_attn.conv1d.weight": "model-00004-of-00005.safetensors",
413
+ "model.layers.30.linear_attn.norm.weight": "model-00004-of-00005.safetensors",
414
+ "model.layers.30.linear_attn.out_proj.weight": "model-00004-of-00005.safetensors",
415
+ "model.layers.30.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
416
+ "model.layers.30.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
417
+ "model.layers.30.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
418
+ "model.layers.30.input_layernorm.weight": "model-00004-of-00005.safetensors",
419
+ "model.layers.30.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
420
+ "model.layers.31.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
421
+ "model.layers.31.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
422
+ "model.layers.31.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
423
+ "model.layers.31.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
424
+ "model.layers.31.self_attn.q_norm.weight": "model-00004-of-00005.safetensors",
425
+ "model.layers.31.self_attn.k_norm.weight": "model-00004-of-00005.safetensors",
426
+ "model.layers.31.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
427
+ "model.layers.31.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
428
+ "model.layers.31.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
429
+ "model.layers.31.input_layernorm.weight": "model-00004-of-00005.safetensors",
430
+ "model.layers.31.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
431
+ "model.norm.weight": "model-00004-of-00005.safetensors",
432
+ "lm_head.weight": "model-00005-of-00005.safetensors"
433
+ }
434
+ }
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5f9e4d4901a92b997e463c1f46055088b6cca5ca61a6522d1b9f64c4bb81cb42
3
+ size 12807982
tokenizer_config.json ADDED
@@ -0,0 +1,305 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "248044": {
5
+ "content": "<|endoftext|>",
6
+ "lstrip": false,
7
+ "normalized": false,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "248045": {
13
+ "content": "<|im_start|>",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "248046": {
21
+ "content": "<|im_end|>",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ },
28
+ "248047": {
29
+ "content": "<|object_ref_start|>",
30
+ "lstrip": false,
31
+ "normalized": false,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": true
35
+ },
36
+ "248048": {
37
+ "content": "<|object_ref_end|>",
38
+ "lstrip": false,
39
+ "normalized": false,
40
+ "rstrip": false,
41
+ "single_word": false,
42
+ "special": true
43
+ },
44
+ "248049": {
45
+ "content": "<|box_start|>",
46
+ "lstrip": false,
47
+ "normalized": false,
48
+ "rstrip": false,
49
+ "single_word": false,
50
+ "special": true
51
+ },
52
+ "248050": {
53
+ "content": "<|box_end|>",
54
+ "lstrip": false,
55
+ "normalized": false,
56
+ "rstrip": false,
57
+ "single_word": false,
58
+ "special": true
59
+ },
60
+ "248051": {
61
+ "content": "<|quad_start|>",
62
+ "lstrip": false,
63
+ "normalized": false,
64
+ "rstrip": false,
65
+ "single_word": false,
66
+ "special": true
67
+ },
68
+ "248052": {
69
+ "content": "<|quad_end|>",
70
+ "lstrip": false,
71
+ "normalized": false,
72
+ "rstrip": false,
73
+ "single_word": false,
74
+ "special": true
75
+ },
76
+ "248053": {
77
+ "content": "<|vision_start|>",
78
+ "lstrip": false,
79
+ "normalized": false,
80
+ "rstrip": false,
81
+ "single_word": false,
82
+ "special": true
83
+ },
84
+ "248054": {
85
+ "content": "<|vision_end|>",
86
+ "lstrip": false,
87
+ "normalized": false,
88
+ "rstrip": false,
89
+ "single_word": false,
90
+ "special": true
91
+ },
92
+ "248055": {
93
+ "content": "<|vision_pad|>",
94
+ "lstrip": false,
95
+ "normalized": false,
96
+ "rstrip": false,
97
+ "single_word": false,
98
+ "special": true
99
+ },
100
+ "248056": {
101
+ "content": "<|image_pad|>",
102
+ "lstrip": false,
103
+ "normalized": false,
104
+ "rstrip": false,
105
+ "single_word": false,
106
+ "special": true
107
+ },
108
+ "248057": {
109
+ "content": "<|video_pad|>",
110
+ "lstrip": false,
111
+ "normalized": false,
112
+ "rstrip": false,
113
+ "single_word": false,
114
+ "special": true
115
+ },
116
+ "248058": {
117
+ "content": "<tool_call>",
118
+ "lstrip": false,
119
+ "normalized": false,
120
+ "rstrip": false,
121
+ "single_word": false,
122
+ "special": false
123
+ },
124
+ "248059": {
125
+ "content": "</tool_call>",
126
+ "lstrip": false,
127
+ "normalized": false,
128
+ "rstrip": false,
129
+ "single_word": false,
130
+ "special": false
131
+ },
132
+ "248060": {
133
+ "content": "<|fim_prefix|>",
134
+ "lstrip": false,
135
+ "normalized": false,
136
+ "rstrip": false,
137
+ "single_word": false,
138
+ "special": false
139
+ },
140
+ "248061": {
141
+ "content": "<|fim_middle|>",
142
+ "lstrip": false,
143
+ "normalized": false,
144
+ "rstrip": false,
145
+ "single_word": false,
146
+ "special": false
147
+ },
148
+ "248062": {
149
+ "content": "<|fim_suffix|>",
150
+ "lstrip": false,
151
+ "normalized": false,
152
+ "rstrip": false,
153
+ "single_word": false,
154
+ "special": false
155
+ },
156
+ "248063": {
157
+ "content": "<|fim_pad|>",
158
+ "lstrip": false,
159
+ "normalized": false,
160
+ "rstrip": false,
161
+ "single_word": false,
162
+ "special": false
163
+ },
164
+ "248064": {
165
+ "content": "<|repo_name|>",
166
+ "lstrip": false,
167
+ "normalized": false,
168
+ "rstrip": false,
169
+ "single_word": false,
170
+ "special": false
171
+ },
172
+ "248065": {
173
+ "content": "<|file_sep|>",
174
+ "lstrip": false,
175
+ "normalized": false,
176
+ "rstrip": false,
177
+ "single_word": false,
178
+ "special": false
179
+ },
180
+ "248066": {
181
+ "content": "<tool_response>",
182
+ "lstrip": false,
183
+ "normalized": false,
184
+ "rstrip": false,
185
+ "single_word": false,
186
+ "special": false
187
+ },
188
+ "248067": {
189
+ "content": "</tool_response>",
190
+ "lstrip": false,
191
+ "normalized": false,
192
+ "rstrip": false,
193
+ "single_word": false,
194
+ "special": false
195
+ },
196
+ "248068": {
197
+ "content": "<think>",
198
+ "lstrip": false,
199
+ "normalized": false,
200
+ "rstrip": false,
201
+ "single_word": false,
202
+ "special": false
203
+ },
204
+ "248069": {
205
+ "content": "</think>",
206
+ "lstrip": false,
207
+ "normalized": false,
208
+ "rstrip": false,
209
+ "single_word": false,
210
+ "special": false
211
+ },
212
+ "248070": {
213
+ "content": "<|audio_start|>",
214
+ "lstrip": false,
215
+ "normalized": false,
216
+ "rstrip": false,
217
+ "single_word": false,
218
+ "special": true
219
+ },
220
+ "248071": {
221
+ "content": "<|audio_end|>",
222
+ "lstrip": false,
223
+ "normalized": false,
224
+ "rstrip": false,
225
+ "single_word": false,
226
+ "special": true
227
+ },
228
+ "248072": {
229
+ "content": "<tts_pad>",
230
+ "lstrip": false,
231
+ "normalized": false,
232
+ "rstrip": false,
233
+ "single_word": false,
234
+ "special": true
235
+ },
236
+ "248073": {
237
+ "content": "<tts_text_bos>",
238
+ "lstrip": false,
239
+ "normalized": false,
240
+ "rstrip": false,
241
+ "single_word": false,
242
+ "special": true
243
+ },
244
+ "248074": {
245
+ "content": "<tts_text_eod>",
246
+ "lstrip": false,
247
+ "normalized": false,
248
+ "rstrip": false,
249
+ "single_word": false,
250
+ "special": true
251
+ },
252
+ "248075": {
253
+ "content": "<tts_text_bos_single>",
254
+ "lstrip": false,
255
+ "normalized": false,
256
+ "rstrip": false,
257
+ "single_word": false,
258
+ "special": true
259
+ },
260
+ "248076": {
261
+ "content": "<|audio_pad|>",
262
+ "lstrip": false,
263
+ "normalized": false,
264
+ "rstrip": false,
265
+ "single_word": false,
266
+ "special": true
267
+ }
268
+ },
269
+ "additional_special_tokens": [
270
+ "<|im_start|>",
271
+ "<|im_end|>",
272
+ "<|object_ref_start|>",
273
+ "<|object_ref_end|>",
274
+ "<|box_start|>",
275
+ "<|box_end|>",
276
+ "<|quad_start|>",
277
+ "<|quad_end|>",
278
+ "<|vision_start|>",
279
+ "<|vision_end|>",
280
+ "<|vision_pad|>",
281
+ "<|image_pad|>",
282
+ "<|video_pad|>"
283
+ ],
284
+ "bos_token": null,
285
+ "chat_template": "{%- set image_count = namespace(value=0) %}\n{%- set video_count = namespace(value=0) %}\n{%- macro render_content(content, do_vision_count, is_system_content=false) %}\n {%- if content is string %}\n {{- content }}\n {%- elif content is iterable and content is not mapping %}\n {%- for item in content %}\n {%- if 'image' in item or 'image_url' in item or item.type == 'image' %}\n {%- if is_system_content %}\n {{- raise_exception('System message cannot contain images.') }}\n {%- endif %}\n {%- if do_vision_count %}\n {%- set image_count.value = image_count.value + 1 %}\n {%- endif %}\n {%- if add_vision_id %}\n {{- 'Picture ' ~ image_count.value ~ ': ' }}\n {%- endif %}\n {{- '<|vision_start|><|image_pad|><|vision_end|>' }}\n {%- elif 'video' in item or item.type == 'video' %}\n {%- if is_system_content %}\n {{- raise_exception('System message cannot contain videos.') }}\n {%- endif %}\n {%- if do_vision_count %}\n {%- set video_count.value = video_count.value + 1 %}\n {%- endif %}\n {%- if add_vision_id %}\n {{- 'Video ' ~ video_count.value ~ ': ' }}\n {%- endif %}\n {{- '<|vision_start|><|video_pad|><|vision_end|>' }}\n {%- elif 'text' in item %}\n {{- item.text }}\n {%- else %}\n {{- raise_exception('Unexpected item type in content.') }}\n {%- endif %}\n {%- endfor %}\n {%- elif content is none or content is undefined %}\n {{- '' }}\n {%- else %}\n {{- raise_exception('Unexpected content type.') }}\n {%- endif %}\n{%- endmacro %}\n{%- if not messages %}\n {{- raise_exception('No messages provided.') }}\n{%- endif %}\n{%- if tools and tools is iterable and tools is not mapping %}\n {{- '<|im_start|>system\\n' }}\n {{- \"# Tools\\n\\nYou have access to the following functions:\\n\\n<tools>\" }}\n {%- for tool in tools %}\n {{- \"\\n\" }}\n {{- tool | tojson }}\n {%- endfor %}\n {{- \"\\n</tools>\" }}\n {{- '\\n\\nIf you choose to call a function ONLY reply in the following format with NO suffix:\\n\\n<tool_call>\\n<function=example_function_name>\\n<parameter=example_parameter_1>\\nvalue_1\\n</parameter>\\n<parameter=example_parameter_2>\\nThis is the value for the second parameter\\nthat can span\\nmultiple lines\\n</parameter>\\n</function>\\n</tool_call>\\n\\n<IMPORTANT>\\nReminder:\\n- Function calls MUST follow the specified format: an inner <function=...></function> block must be nested within <tool_call></tool_call> XML tags\\n- Required parameters MUST be specified\\n- You may provide optional reasoning for your function call in natural language BEFORE the function call, but NOT after\\n- If there is no function call available, answer the question like normal with your current knowledge and do not tell the user about function calls\\n</IMPORTANT>' }}\n {%- if messages[0].role == 'system' %}\n {%- set content = render_content(messages[0].content, false, true)|trim %}\n {%- if content %}\n {{- '\\n\\n' + content }}\n {%- endif %}\n {%- endif %}\n {{- '<|im_end|>\\n' }}\n{%- else %}\n {%- if messages[0].role == 'system' %}\n {%- set content = render_content(messages[0].content, false, true)|trim %}\n {{- '<|im_start|>system\\n' + content + '<|im_end|>\\n' }}\n {%- endif %}\n{%- endif %}\n{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}\n{%- for message in messages[::-1] %}\n {%- set index = (messages|length - 1) - loop.index0 %}\n {%- if ns.multi_step_tool and message.role == \"user\" %}\n {%- set content = render_content(message.content, false)|trim %}\n {%- if not(content.startswith('<tool_response>') and content.endswith('</tool_response>')) %}\n {%- set ns.multi_step_tool = false %}\n {%- set ns.last_query_index = index %}\n {%- endif %}\n {%- endif %}\n{%- endfor %}\n{%- if ns.multi_step_tool %}\n {{- raise_exception('No user query found in messages.') }}\n{%- endif %}\n{%- for message in messages %}\n {%- set content = render_content(message.content, true)|trim %}\n {%- if message.role == \"system\" %}\n {%- if not loop.first %}\n {{- raise_exception('System message must be at the beginning.') }}\n {%- endif %}\n {%- elif message.role == \"user\" %}\n {{- '<|im_start|>' + message.role + '\\n' + content + '<|im_end|>' + '\\n' }}\n {%- elif message.role == \"assistant\" %}\n {%- set reasoning_content = '' %}\n {%- if message.reasoning_content is string %}\n {%- set reasoning_content = message.reasoning_content %}\n {%- else %}\n {%- if '</think>' in content %}\n {%- set reasoning_content = content.split('</think>')[0].rstrip('\\n').split('<think>')[-1].lstrip('\\n') %}\n {%- set content = content.split('</think>')[-1].lstrip('\\n') %}\n {%- endif %}\n {%- endif %}\n {%- set reasoning_content = reasoning_content|trim %}\n {%- if loop.index0 > ns.last_query_index %}\n {{- '<|im_start|>' + message.role + '\\n<think>\\n' + reasoning_content + '\\n</think>\\n\\n' + content }}\n {%- else %}\n {{- '<|im_start|>' + message.role + '\\n' + content }}\n {%- endif %}\n {%- if message.tool_calls and message.tool_calls is iterable and message.tool_calls is not mapping %}\n {%- for tool_call in message.tool_calls %}\n {%- if tool_call.function is defined %}\n {%- set tool_call = tool_call.function %}\n {%- endif %}\n {%- if loop.first %}\n {%- if content|trim %}\n {{- '\\n\\n<tool_call>\\n<function=' + tool_call.name + '>\\n' }}\n {%- else %}\n {{- '<tool_call>\\n<function=' + tool_call.name + '>\\n' }}\n {%- endif %}\n {%- else %}\n {{- '\\n<tool_call>\\n<function=' + tool_call.name + '>\\n' }}\n {%- endif %}\n {%- if tool_call.arguments is defined %}\n {%- for args_name, args_value in tool_call.arguments|items %}\n {{- '<parameter=' + args_name + '>\\n' }}\n {%- set args_value = args_value | tojson | safe if args_value is mapping or (args_value is sequence and args_value is not string) else args_value | string %}\n {{- args_value }}\n {{- '\\n</parameter>\\n' }}\n {%- endfor %}\n {%- endif %}\n {{- '</function>\\n</tool_call>' }}\n {%- endfor %}\n {%- endif %}\n {{- '<|im_end|>\\n' }}\n {%- elif message.role == \"tool\" %}\n {%- if loop.previtem and loop.previtem.role != \"tool\" %}\n {{- '<|im_start|>user' }}\n {%- endif %}\n {{- '\\n<tool_response>\\n' }}\n {{- content }}\n {{- '\\n</tool_response>' }}\n {%- if not loop.last and loop.nextitem.role != \"tool\" %}\n {{- '<|im_end|>\\n' }}\n {%- elif loop.last %}\n {{- '<|im_end|>\\n' }}\n {%- endif %}\n {%- else %}\n {{- raise_exception('Unexpected message role.') }}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|im_start|>assistant\\n' }}\n {%- if enable_thinking is defined and enable_thinking is false %}\n {{- '<think>\\n\\n</think>\\n\\n' }}\n {%- else %}\n {{- '<think>\\n' }}\n {%- endif %}\n{%- endif %}",
286
+ "clean_up_tokenization_spaces": false,
287
+ "eos_token": "<|im_end|>",
288
+ "errors": "replace",
289
+ "model_max_length": 262144,
290
+ "pad_token": "<|endoftext|>",
291
+ "split_special_tokens": false,
292
+ "tokenizer_class": "Qwen2Tokenizer",
293
+ "unk_token": null,
294
+ "add_bos_token": false,
295
+ "pretokenize_regex": "(?i:'s|'t|'re|'ve|'m|'ll|'d)|[^\\r\\n\\p{L}\\p{N}]?[\\p{L}\\p{M}]+|\\p{N}| ?[^\\s\\p{L}\\p{M}\\p{N}]+[\\r\\n]*|\\s*[\\r\\n]+|\\s+(?!\\S)|\\s+",
296
+ "extra_special_tokens": {
297
+ "audio_bos_token": "<|audio_start|>",
298
+ "audio_eos_token": "<|audio_end|>",
299
+ "audio_token": "<|audio_pad|>",
300
+ "image_token": "<|image_pad|>",
301
+ "video_token": "<|video_pad|>",
302
+ "vision_bos_token": "<|vision_start|>",
303
+ "vision_eos_token": "<|vision_end|>"
304
+ }
305
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff