Hugging Face's logo

unsloth
/
OpenReasoning-Nemotron-32B

Text Generation
Transformers
Safetensors
English
qwen2
nvidia
unsloth
code
conversational
text-generation-inference
Model card Files
xet
 Community
danielhanchen commited on
Commit
efd135a
·
verified ·
1 Parent(s): 60c7f02

Upload folder using huggingface_hub

Browse files
Files changed (23) hide show
  1. .gitattributes +1 -0
  2. BIAS.md +4 -0
  3. EXPLAINABILITY.md +13 -0
  4. PRIVACY.md +10 -0
  5. README.md +277 -0
  6. SAFETY.md +7 -0
  7. added_tokens.json +24 -0
  8. chat_template.jinja +20 -0
  9. config.json +95 -0
  10. generation_config.json +6 -0
  11. merges.txt +0 -0
  12. model-00001-of-00007.safetensors +3 -0
  13. model-00002-of-00007.safetensors +3 -0
  14. model-00003-of-00007.safetensors +3 -0
  15. model-00004-of-00007.safetensors +3 -0
  16. model-00005-of-00007.safetensors +3 -0
  17. model-00006-of-00007.safetensors +3 -0
  18. model-00007-of-00007.safetensors +3 -0
  19. model.safetensors.index.json +778 -0
  20. special_tokens_map.json +31 -0
  21. tokenizer.json +3 -0
  22. tokenizer_config.json +209 -0
  23. vocab.json +0 -0
.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
BIAS.md ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ Field | Response
2
+ :---------------------------------------------------------------------------------------------------|:---------------
3
+ Participation considerations from adversely impacted groups [protected classes](https://www.senate.ca.gov/content/protected-classes) in model design and testing: | None
4
+ Measures taken to mitigate against unwanted bias: | None
EXPLAINABILITY.md ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ Field | Response
2
+ :------------------------------------------------------------------------------------------------------|:---------------------------------------------------------------------------------
3
+ Intended Task/Domain: | Reasoning for Math, Code Science Solution Generation
4
+ Model Type: | Transformer
5
+ Intended Users: | Solving competitive programming questions and evaluation for benchmark comparison.
6
+ Output: | Text
7
+ Describe how the model works: | The model generates a reasoning trace and responds with a final solution in response to a user prompting a programming question.
8
+ Name the adversely impacted groups this has been tested to deliver comparable outcomes regardless of: | Not Applicable
9
+ Technical Limitations & Mitigation: | This model is not applicable for Software Engineering tasks. It primarily should be used for competitive coding challenges that require optimized code solutions that can operate in appropriate space and time complexity.
10
+ Verified to have met prescribed NVIDIA quality standards: | Yes
11
+ Performance Metrics: | Pass@1 score
12
+ Potential Known Risks: | The model may provide incorrect code solutions that fail to solve the problem. The model may enter a feedback loop and constantly generate reasoning tokens without generating the final solution.
13
+ Licensing: | [CC-BY-4.0](https://creativecommons.org/licenses/by/4.0/deed.en/)
PRIVACY.md ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ Field | Response
2
+ :----------------------------------------------------------------------------------------------------------------------------------|:-----------------------------------------------
3
+ Generatable or reverse engineerable personal data? | No
4
+ Personal data used to create this model? | No
5
+ How often is the dataset reviewed? | Before Release
6
+ Is there provenance for all datasets used in training? | Yes
7
+ Does data labeling (annotation, metadata) comply with privacy laws? | Yes
8
+ Is data compliant with data subject requests for data correction or removal, if such a request was made? | No, not possible with externally-sourced data.
9
+ Applicable Privacy Policy | https://www.nvidia.com/en-us/about-nvidia/privacy-policy/
10
+
README.md ADDED
@@ -0,0 +1,277 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: cc-by-4.0
3
+ language:
4
+ - en
5
+ base_model:
6
+ - nvidia/OpenReasoning-Nemotron-32B
7
+ pipeline_tag: text-generation
8
+ library_name: transformers
9
+ tags:
10
+ - nvidia
11
+ - unsloth
12
+ - code
13
+ ---
14
+ > [!NOTE]
15
+ > Includes Unsloth **chat template fixes**! <br> For `llama.cpp`, use `--jinja`
16
+ >
17
+
18
+ <div>
19
+ <p style="margin-top: 0;margin-bottom: 0;">
20
+ <em><a href="https://docs.unsloth.ai/basics/unsloth-dynamic-v2.0-gguf">Unsloth Dynamic 2.0</a> achieves superior accuracy & outperforms other leading quants.</em>
21
+ </p>
22
+ <div style="display: flex; gap: 5px; align-items: center; ">
23
+ <a href="https://github.com/unslothai/unsloth/">
24
+ <img src="https://github.com/unslothai/unsloth/raw/main/images/unsloth%20new%20logo.png" width="133">
25
+ </a>
26
+ <a href="https://discord.gg/unsloth">
27
+ <img src="https://github.com/unslothai/unsloth/raw/main/images/Discord%20button.png" width="173">
28
+ </a>
29
+ <a href="https://docs.unsloth.ai/">
30
+ <img src="https://raw.githubusercontent.com/unslothai/unsloth/refs/heads/main/images/documentation%20green%20button.png" width="143">
31
+ </a>
32
+ </div>
33
+ </div>
34
+
35
+ # OpenReasoning-Nemotron-32B Overview
36
+
37
+ ## Description: <br>
38
+ OpenReasoning-Nemotron-32B is a large language model (LLM) which is a derivative of Qwen2.5-32B-Instruct (AKA the reference model). It is a reasoning model that is post-trained for reasoning about math, code and science solution generation. We evaluated this model with up to 64K output tokens. The OpenReasoning model is available in the following sizes: 1.5B, 7B and 14B and 32B. <br>
39
+
40
+ This model is ready for commercial/non-commercial research use. <br>
41
+
42
+ ### License/Terms of Use: <br>
43
+ GOVERNING TERMS: Use of the models listed above are governed by the [Creative Commons Attribution 4.0 International License (CC-BY-4.0)](https://creativecommons.org/licenses/by/4.0/legalcode.en). ADDITIONAL INFORMATION: [Apache 2.0 License](https://huggingface.co/Qwen/Qwen2.5-32B-Instruct/blob/main/LICENSE)
44
+
45
+ ## Scores on Reasoning Benchmarks
46
+
47
+ ![Evaluation Results with pass@1](https://raw.githubusercontent.com/NVIDIA/NeMo-Skills/main/docs/releases/openreasoning/pass-1.png)
48
+
49
+ Our models demonstrate exceptional performance across a suite of challenging reasoning benchmarks. The 7B, 14B, and 32B models consistently set new state-of-the-art records for their size classes.
50
+
51
+ | **Model** | **AritificalAnalysisIndex*** | **GPQA** | **MMLU-PRO** | **HLE** | **LiveCodeBench*** | **SciCode** | **AIME24** | **AIME25** | **HMMT FEB 25** |
52
+ | :--- | :--- | :--- | :--- | :--- | :--- | :--- | :--- | :--- | :--- |
53
+ | **1.5B**| 31.0 | 31.6 | 47.5 | 5.5 | 28.6 | 2.2 | 55.5 | 45.6 | 31.5 |
54
+ | **7B** | 54.7 | 61.1 | 71.9 | 8.3 | 63.3 | 16.2 | 84.7 | 78.2 | 63.5 |
55
+ | **14B** | 60.9 | 71.6 | 77.5 | 10.1 | 67.8 | 23.5 | 87.8 | 82.0 | 71.2 |
56
+ | **32B** | 64.3 | 73.1 | 80.0 | 11.9 | 70.2 | 28.5 | 89.2 | 84.0 | 73.8 |
57
+
58
+ \* This is our estimation of the Artificial Analysis Intelligence Index, not an official score.
59
+
60
+ \* LiveCodeBench version 6, date range 2408-2505.
61
+
62
+ ## Combining the work of multiple agents
63
+ OpenReasoning-Nemotron models can be used in a "heavy" mode by starting multiple parallel generations and combining them together via [generative solution selection (GenSelect)](https://arxiv.org/abs/2504.16891). To add this "skill" we follow the original GenSelect training pipeline except we do not train on the selection summary but use the full reasoning trace of DeepSeek R1 0528 671B instead. We only train models to select the best solution for math problems but surprisingly find that this capability directly generalizes to code and science questions! With this "heavy" GenSelect inference mode, OpenReasoning-Nemotron-32B model surpasses O3 (High) on math and coding benchmarks.
64
+
65
+ ![Evaluation Results with GenSelect](https://raw.githubusercontent.com/NVIDIA/NeMo-Skills/main/docs/releases/openreasoning/genselect.png)
66
+
67
+ | **Model** | **Pass@1 (Avg@64)** | **Majority@64** | **GenSelect** |
68
+ | :--- | :--- | :--- | :--- |
69
+ | **1.5B** | | | |
70
+ | **AIME24** | 55.5 | 76.7 | 76.7 |
71
+ | **AIME25** | 45.6 | 70.0 | 70.0 |
72
+ | **HMMT Feb 25** | 31.5 | 46.7 | 53.3 |
73
+ | **7B** | | | |
74
+ | **AIME24** | 84.7 | 93.3 | 93.3 |
75
+ | **AIME25** | 78.2 | 86.7 | 93.3 |
76
+ | **HMMT Feb 25** | 63.5 | 83.3 | 90.0 |
77
+ | **LCB v6 2408-2505** | 63.4 | n/a | 67.7 |
78
+ | **14B** | | | |
79
+ | **AIME24** | 87.8 | 93.3 | 93.3 |
80
+ | **AIME25** | 82.0 | 90.0 | 90.0 |
81
+ | **HMMT Feb 25** | 71.2 | 86.7 | 93.3 |
82
+ | **LCB v6 2408-2505** | 67.9 | n/a | 69.1 |
83
+ | **32B** | | | |
84
+ | **AIME24** | 89.2 | 93.3 | 93.3 |
85
+ | **AIME25** | 84.0 | 90.0 | 93.3 |
86
+ | **HMMT Feb 25** | 73.8 | 86.7 | 96.7 |
87
+ | **LCB v6 2408-2505** | 70.2 | n/a | 75.3 |
88
+ | **HLE** | 11.8 | 13.4 | 15.5 |
89
+
90
+
91
+ ## How to use the models?
92
+
93
+ To run inference on coding problems:
94
+
95
+ ````python
96
+ import transformers
97
+ import torch
98
+ model_id = "nvidia/OpenReasoning-Nemotron-32B"
99
+ pipeline = transformers.pipeline(
100
+ "text-generation",
101
+ model=model_id,
102
+ model_kwargs={"torch_dtype": torch.bfloat16},
103
+ device_map="auto",
104
+ )
105
+ # Code generation prompt
106
+ prompt = """You are a helpful and harmless assistant. You should think step-by-step before responding to the instruction below.
107
+ Please use python programming language only.
108
+ You must use ```python for just the final solution code block with the following format:
109
+ ```python
110
+ # Your code here
111
+ ```
112
+ {user}
113
+ """
114
+
115
+ # Math generation prompt
116
+ # prompt = """Solve the following math problem. Make sure to put the answer (and only answer) inside \\boxed{}.
117
+ #
118
+ # {user}
119
+ # """
120
+
121
+ # Science generation prompt
122
+ # You can refer to prompts here -
123
+ # https://github.com/NVIDIA/NeMo-Skills/blob/main/nemo_skills/prompt/config/generic/hle.yaml (HLE)
124
+ # https://github.com/NVIDIA/NeMo-Skills/blob/main/nemo_skills/prompt/config/eval/aai/mcq-4choices-boxed.yaml (for GPQA)
125
+ # https://github.com/NVIDIA/NeMo-Skills/blob/main/nemo_skills/prompt/config/eval/aai/mcq-10choices-boxed.yaml (MMLU-Pro)
126
+
127
+ messages = [
128
+ {
129
+ "role": "user",
130
+ "content": prompt.format(user="Write a program to calculate the sum of the first $N$ fibonacci numbers")},
131
+ ]
132
+ outputs = pipeline(
133
+ messages,
134
+ max_new_tokens=64000,
135
+ )
136
+ print(outputs[0]["generated_text"][-1]['content'])
137
+ ````
138
+
139
+ ## Citation
140
+
141
+ If you find the data useful, please cite:
142
+ ```
143
+ @article{ahmad2025opencodereasoning,
144
+ title={OpenCodeReasoning: Advancing Data Distillation for Competitive Coding},
145
+ author={Wasi Uddin Ahmad, Sean Narenthiran, Somshubra Majumdar, Aleksander Ficek, Siddhartha Jain, Jocelyn Huang, Vahid Noroozi, Boris Ginsburg},
146
+ year={2025},
147
+ eprint={2504.01943},
148
+ archivePrefix={arXiv},
149
+ primaryClass={cs.CL},
150
+ url={https://arxiv.org/abs/2504.01943},
151
+ }
152
+ ```
153
+
154
+ ```
155
+ @misc{ahmad2025opencodereasoningiisimpletesttime,
156
+ title={OpenCodeReasoning-II: A Simple Test Time Scaling Approach via Self-Critique},
157
+ author={Wasi Uddin Ahmad and Somshubra Majumdar and Aleksander Ficek and Sean Narenthiran and Mehrzad Samadi and Jocelyn Huang and Siddhartha Jain and Vahid Noroozi and Boris Ginsburg},
158
+ year={2025},
159
+ eprint={2507.09075},
160
+ archivePrefix={arXiv},
161
+ primaryClass={cs.CL},
162
+ url={https://arxiv.org/abs/2507.09075},
163
+ }
164
+ ```
165
+
166
+ ```
167
+ @misc{moshkov2025aimo2winningsolutionbuilding,
168
+ title={AIMO-2 Winning Solution: Building State-of-the-Art Mathematical Reasoning Models with OpenMathReasoning dataset},
169
+ author={Ivan Moshkov and Darragh Hanley and Ivan Sorokin and Shubham Toshniwal and Christof Henkel and Benedikt Schifferer and Wei Du and Igor Gitman},
170
+ year={2025},
171
+ eprint={2504.16891},
172
+ archivePrefix={arXiv},
173
+ primaryClass={cs.AI},
174
+ url={https://arxiv.org/abs/2504.16891},
175
+ }
176
+ ```
177
+
178
+ ## Additional Information:
179
+
180
+ ### Deployment Geography:
181
+ Global<br>
182
+
183
+ ### Use Case: <br>
184
+ This model is intended for developers and researchers who work on competitive math, code and science problems. It has been trained via only supervised fine-tuning to achieve strong scores on benchmarks. <br>
185
+
186
+ ### Release Date: <br>
187
+ Huggingface [07/16/2025] via https://huggingface.co/nvidia/OpenReasoning-Nemotron-32B/ <br>
188
+
189
+ ## Reference(s):
190
+ * [2504.01943] OpenCodeReasoning: Advancing Data Distillation for Competitive Coding
191
+ * [2504.01943] OpenCodeReasoning: Advancing Data Distillation for Competitive Coding
192
+ * [2504.16891] AIMO-2 Winning Solution: Building State-of-the-Art Mathematical Reasoning Models with OpenMathReasoning dataset
193
+ <br>
194
+
195
+ ## Model Architecture: <br>
196
+ Architecture Type: Dense decoder-only Transformer model
197
+ Network Architecture: Qwen-32B-Instruct
198
+ <br>
199
+ **This model was developed based on Qwen2.5-32B-Instruct and has 32B model parameters. <br>**
200
+
201
+ **OpenReasoning-Nemotron-1.5B was developed based on Qwen2.5-1.5B-Instruct and has 1.5B model parameters. <br>**
202
+
203
+ **OpenReasoning-Nemotron-7B was developed based on Qwen2.5-7B-Instruct and has 7B model parameters. <br>**
204
+
205
+ **OpenReasoning-Nemotron-14B was developed based on Qwen2.5-14B-Instruct and has 14B model parameters. <br>**
206
+
207
+ **OpenReasoning-Nemotron-32B was developed based on Qwen2.5-32B-Instruct and has 32B model parameters. <br>**
208
+
209
+ ## Input: <br>
210
+ **Input Type(s):** Text <br>
211
+ **Input Format(s):** String <br>
212
+ **Input Parameters:** One-Dimensional (1D) <br>
213
+ **Other Properties Related to Input:** Trained for up to 64,000 output tokens <br>
214
+
215
+ ## Output: <br>
216
+ **Output Type(s):** Text <br>
217
+ **Output Format:** String <br>
218
+ **Output Parameters:** One-Dimensional (1D) <br>
219
+ **Other Properties Related to Output:** Trained for up to 64,000 output tokens <br>
220
+
221
+ Our AI models are designed and/or optimized to run on NVIDIA GPU-accelerated systems. By leveraging NVIDIA’s hardware (e.g. GPU cores) and software frameworks (e.g., CUDA libraries), the model achieves faster training and inference times compared to CPU-only solutions. <br>
222
+
223
+ ## Software Integration : <br>
224
+ * Runtime Engine: NeMo 2.3.0 <br>
225
+ * Recommended Hardware Microarchitecture Compatibility: <br>
226
+ NVIDIA Ampere <br>
227
+ NVIDIA Hopper <br>
228
+ * Preferred/Supported Operating System(s): Linux <br>
229
+
230
+ ## Model Version(s):
231
+ 1.0 (7/16/2025) <br>
232
+ OpenReasoning-Nemotron-32B<br>
233
+ OpenReasoning-Nemotron-14B<br>
234
+ OpenReasoning-Nemotron-7B<br>
235
+ OpenReasoning-Nemotron-1.5B<br>
236
+
237
+ # Training and Evaluation Datasets: <br>
238
+
239
+ ## Training Dataset:
240
+
241
+ The training corpus for OpenReasoning-Nemotron-32B is comprised of questions from [OpenCodeReasoning](https://huggingface.co/datasets/nvidia/OpenCodeReasoning) dataset, [OpenCodeReasoning-II](https://arxiv.org/abs/2507.09075), [OpenMathReasoning](https://huggingface.co/datasets/nvidia/OpenMathReasoning), and the Synthetic Science questions from the [Llama-Nemotron-Post-Training-Dataset](https://huggingface.co/datasets/nvidia/Llama-Nemotron-Post-Training-Dataset). All responses are generated using DeepSeek-R1-0528. We also include the instruction following and tool calling data from Llama-Nemotron-Post-Training-Dataset without modification.
242
+
243
+ Data Collection Method: Hybrid: Automated, Human, Synthetic <br>
244
+ Labeling Method: Hybrid: Automated, Human, Synthetic <br>
245
+ Properties: 5M DeepSeek-R1-0528 generated responses from OpenCodeReasoning questions (https://huggingface.co/datasets/nvidia/OpenCodeReasoning), [OpenMathReasoning](https://huggingface.co/datasets/nvidia/OpenMathReasoning), and the Synthetic Science questions from the [Llama-Nemotron-Post-Training-Dataset](https://huggingface.co/datasets/nvidia/Llama-Nemotron-Post-Training-Dataset). We also include the instruction following and tool calling data from Llama-Nemotron-Post-Training-Dataset without modification.
246
+
247
+ ## Evaluation Dataset:
248
+ We used the following benchmarks to evaluate the model holistically.
249
+
250
+ ### Math
251
+ - AIME 2024/2025 <br>
252
+ - HMMT <br>
253
+ - BRUNO 2025 <br>
254
+
255
+ ### Code
256
+ - LiveCodeBench <br>
257
+ - SciCode <br>
258
+
259
+ ### Science
260
+ - GPQA <br>
261
+ - MMLU-PRO <br>
262
+ - HLE <br>
263
+
264
+
265
+ Data Collection Method: Hybrid: Automated, Human, Synthetic <br>
266
+ Labeling Method: Hybrid: Automated, Human, Synthetic <br>
267
+
268
+ ## Inference:
269
+ **Acceleration Engine:** vLLM, Tensor(RT)-LLM <br>
270
+ **Test Hardware** NVIDIA H100-80GB <br>
271
+
272
+ ## Ethical Considerations:
273
+ NVIDIA believes Trustworthy AI is a shared responsibility and we have established policies and practices to enable development for a wide array of AI applications. When downloaded or used in accordance with our terms of service, developers should work with their internal model team to ensure this model meets requirements for the relevant industry and use case and addresses unforeseen product misuse.
274
+
275
+ For more detailed information on ethical considerations for this model, please see the Model Card++ Explainability, Bias, Safety & Security, and Privacy Subcards.
276
+
277
+ Please report model quality, risk, security vulnerabilities or NVIDIA AI Concerns [here](https://www.nvidia.com/en-us/support/submit-security-vulnerability/).
SAFETY.md ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ Field | Response
2
+ :---------------------------------------------------|:----------------------------------
3
+ Model Application Field(s): | Reasoning for Code Generation<br>
4
+ Describe the life critical impact (if present). | Not Applicable <br>
5
+ Use Case Restrictions: | Abide by CC BY 4.0 <br>
6
+ Model and dataset restrictions: | The Principle of least privilege (PoLP) is applied limiting access for dataset generation and model development. Restrictions enforce dataset access during training, and dataset license constraints adhered to.
7
+
added_tokens.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "</tool_call>": 151658,
3
+ "<tool_call>": 151657,
4
+ "<|box_end|>": 151649,
5
+ "<|box_start|>": 151648,
6
+ "<|endoftext|>": 151643,
7
+ "<|file_sep|>": 151664,
8
+ "<|fim_middle|>": 151660,
9
+ "<|fim_pad|>": 151662,
10
+ "<|fim_prefix|>": 151659,
11
+ "<|fim_suffix|>": 151661,
12
+ "<|im_end|>": 151645,
13
+ "<|im_start|>": 151644,
14
+ "<|image_pad|>": 151655,
15
+ "<|object_ref_end|>": 151647,
16
+ "<|object_ref_start|>": 151646,
17
+ "<|quad_end|>": 151651,
18
+ "<|quad_start|>": 151650,
19
+ "<|repo_name|>": 151663,
20
+ "<|video_pad|>": 151656,
21
+ "<|vision_end|>": 151653,
22
+ "<|vision_pad|>": 151654,
23
+ "<|vision_start|>": 151652
24
+ }
chat_template.jinja ADDED
@@ -0,0 +1,20 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {%- if messages[0]['role'] == 'system' %}
2
+ {{- '<|im_start|>system
3
+ ' + messages[0]['content'] + '<|im_end|>
4
+ ' }}
5
+ {%- else %}
6
+ {{- '<|im_start|>system
7
+ <|im_end|>
8
+ ' }}
9
+ {%- endif %}
10
+ {%- for message in messages %}
11
+ {%- if (message.role == 'user') or (message.role == 'system' and not loop.first) or (message.role == 'assistant') %}
12
+ {{- '<|im_start|>' + message.role + '
13
+ ' + message.content + '<|im_end|>' + '
14
+ ' }}
15
+ {%- endif %}
16
+ {%- endfor %}
17
+ {%- if add_generation_prompt %}
18
+ {{- '<|im_start|>assistant
19
+ ' }}
20
+ {%- endif %}
config.json ADDED
@@ -0,0 +1,95 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Qwen2ForCausalLM"
4
+ ],
5
+ "attention_dropout": 0.0,
6
+ "eos_token_id": 151643,
7
+ "hidden_act": "silu",
8
+ "hidden_size": 5120,
9
+ "initializer_range": 0.02,
10
+ "intermediate_size": 27648,
11
+ "layer_types": [
12
+ "full_attention",
13
+ "full_attention",
14
+ "full_attention",
15
+ "full_attention",
16
+ "full_attention",
17
+ "full_attention",
18
+ "full_attention",
19
+ "full_attention",
20
+ "full_attention",
21
+ "full_attention",
22
+ "full_attention",
23
+ "full_attention",
24
+ "full_attention",
25
+ "full_attention",
26
+ "full_attention",
27
+ "full_attention",
28
+ "full_attention",
29
+ "full_attention",
30
+ "full_attention",
31
+ "full_attention",
32
+ "full_attention",
33
+ "full_attention",
34
+ "full_attention",
35
+ "full_attention",
36
+ "full_attention",
37
+ "full_attention",
38
+ "full_attention",
39
+ "full_attention",
40
+ "full_attention",
41
+ "full_attention",
42
+ "full_attention",
43
+ "full_attention",
44
+ "full_attention",
45
+ "full_attention",
46
+ "full_attention",
47
+ "full_attention",
48
+ "full_attention",
49
+ "full_attention",
50
+ "full_attention",
51
+ "full_attention",
52
+ "full_attention",
53
+ "full_attention",
54
+ "full_attention",
55
+ "full_attention",
56
+ "full_attention",
57
+ "full_attention",
58
+ "full_attention",
59
+ "full_attention",
60
+ "full_attention",
61
+ "full_attention",
62
+ "full_attention",
63
+ "full_attention",
64
+ "full_attention",
65
+ "full_attention",
66
+ "full_attention",
67
+ "full_attention",
68
+ "full_attention",
69
+ "full_attention",
70
+ "full_attention",
71
+ "full_attention",
72
+ "full_attention",
73
+ "full_attention",
74
+ "full_attention",
75
+ "full_attention"
76
+ ],
77
+ "max_position_embeddings": 131072,
78
+ "max_window_layers": 64,
79
+ "model_type": "qwen2",
80
+ "num_attention_heads": 40,
81
+ "num_hidden_layers": 64,
82
+ "num_key_value_heads": 8,
83
+ "pad_token_id": 151654,
84
+ "rms_norm_eps": 1e-05,
85
+ "rope_scaling": null,
86
+ "rope_theta": 1000000.0,
87
+ "sliding_window": null,
88
+ "tie_word_embeddings": false,
89
+ "torch_dtype": "bfloat16",
90
+ "transformers_version": "4.53.2",
91
+ "unsloth_fixed": true,
92
+ "use_cache": true,
93
+ "use_sliding_window": false,
94
+ "vocab_size": 152064
95
+ }
generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 151643,
4
+ "eos_token_id": 151643,
5
+ "transformers_version": "4.47.1"
6
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
model-00001-of-00007.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a33b4071d66ce4b7619d6c6afc58a94c4c502e0bbabad04d88e54b481798cc59
3
+ size 9767790336
model-00002-of-00007.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:01d1f06666b14c42151739d69a76fc9054236e6192d99d595f1f19920a92319d
3
+ size 9752118784
model-00003-of-00007.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:18bf2cd1f1dd2c559272627ad8460b8ad7f83c7ae60a6a268315f0b96dd92491
3
+ size 9752118816
model-00004-of-00007.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c56e81bc54f1cff3ce84d244a65c1126bafb8a1e4b80a19b44618fba9ce479d
3
+ size 9752118816
model-00005-of-00007.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:82997b9f1ba9457dc9b863b817b6952c6a750c188f37e842c1d862ede02febba
3
+ size 9752118816
model-00006-of-00007.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f3baa296d7d556ee239179714f4f1dfb0b693e8a7b0fd68d5e0725c915acfa6a
3
+ size 9752118816
model-00007-of-00007.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:354a694ed0b7e0d5961cfe2f36cc970066ec39414abfb8170cc2f3c4c0c5ad59
3
+ size 6999457200
model.safetensors.index.json ADDED
@@ -0,0 +1,778 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 65527752704
4
+ },
5
+ "weight_map": {
6
+ "lm_head.weight": "model-00007-of-00007.safetensors",
7
+ "model.embed_tokens.weight": "model-00001-of-00007.safetensors",
8
+ "model.layers.0.input_layernorm.weight": "model-00001-of-00007.safetensors",
9
+ "model.layers.0.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
10
+ "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
11
+ "model.layers.0.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
12
+ "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
13
+ "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00007.safetensors",
14
+ "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
15
+ "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
16
+ "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00007.safetensors",
17
+ "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
18
+ "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00007.safetensors",
19
+ "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
20
+ "model.layers.1.input_layernorm.weight": "model-00001-of-00007.safetensors",
21
+ "model.layers.1.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
22
+ "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
23
+ "model.layers.1.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
24
+ "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
25
+ "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00007.safetensors",
26
+ "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
27
+ "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
28
+ "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00007.safetensors",
29
+ "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
30
+ "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00007.safetensors",
31
+ "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
32
+ "model.layers.10.input_layernorm.weight": "model-00002-of-00007.safetensors",
33
+ "model.layers.10.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
34
+ "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
35
+ "model.layers.10.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
36
+ "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
37
+ "model.layers.10.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
38
+ "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
39
+ "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
40
+ "model.layers.10.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
41
+ "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
42
+ "model.layers.10.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
43
+ "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
44
+ "model.layers.11.input_layernorm.weight": "model-00002-of-00007.safetensors",
45
+ "model.layers.11.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
46
+ "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
47
+ "model.layers.11.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
48
+ "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
49
+ "model.layers.11.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
50
+ "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
51
+ "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
52
+ "model.layers.11.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
53
+ "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
54
+ "model.layers.11.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
55
+ "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
56
+ "model.layers.12.input_layernorm.weight": "model-00002-of-00007.safetensors",
57
+ "model.layers.12.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
58
+ "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
59
+ "model.layers.12.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
60
+ "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
61
+ "model.layers.12.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
62
+ "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
63
+ "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
64
+ "model.layers.12.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
65
+ "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
66
+ "model.layers.12.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
67
+ "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
68
+ "model.layers.13.input_layernorm.weight": "model-00002-of-00007.safetensors",
69
+ "model.layers.13.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
70
+ "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
71
+ "model.layers.13.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
72
+ "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
73
+ "model.layers.13.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
74
+ "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
75
+ "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
76
+ "model.layers.13.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
77
+ "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
78
+ "model.layers.13.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
79
+ "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
80
+ "model.layers.14.input_layernorm.weight": "model-00002-of-00007.safetensors",
81
+ "model.layers.14.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
82
+ "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
83
+ "model.layers.14.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
84
+ "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
85
+ "model.layers.14.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
86
+ "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
87
+ "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
88
+ "model.layers.14.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
89
+ "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
90
+ "model.layers.14.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
91
+ "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
92
+ "model.layers.15.input_layernorm.weight": "model-00002-of-00007.safetensors",
93
+ "model.layers.15.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
94
+ "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
95
+ "model.layers.15.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
96
+ "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
97
+ "model.layers.15.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
98
+ "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
99
+ "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
100
+ "model.layers.15.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
101
+ "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
102
+ "model.layers.15.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
103
+ "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
104
+ "model.layers.16.input_layernorm.weight": "model-00002-of-00007.safetensors",
105
+ "model.layers.16.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
106
+ "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
107
+ "model.layers.16.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
108
+ "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
109
+ "model.layers.16.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
110
+ "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
111
+ "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
112
+ "model.layers.16.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
113
+ "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
114
+ "model.layers.16.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
115
+ "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
116
+ "model.layers.17.input_layernorm.weight": "model-00002-of-00007.safetensors",
117
+ "model.layers.17.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
118
+ "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
119
+ "model.layers.17.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
120
+ "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
121
+ "model.layers.17.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
122
+ "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
123
+ "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
124
+ "model.layers.17.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
125
+ "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
126
+ "model.layers.17.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
127
+ "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
128
+ "model.layers.18.input_layernorm.weight": "model-00003-of-00007.safetensors",
129
+ "model.layers.18.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
130
+ "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
131
+ "model.layers.18.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
132
+ "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
133
+ "model.layers.18.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
134
+ "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
135
+ "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
136
+ "model.layers.18.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
137
+ "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
138
+ "model.layers.18.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
139
+ "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
140
+ "model.layers.19.input_layernorm.weight": "model-00003-of-00007.safetensors",
141
+ "model.layers.19.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
142
+ "model.layers.19.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
143
+ "model.layers.19.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
144
+ "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
145
+ "model.layers.19.self_attn.k_proj.bias": "model-00003-of-00007.safetensors",
146
+ "model.layers.19.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
147
+ "model.layers.19.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
148
+ "model.layers.19.self_attn.q_proj.bias": "model-00003-of-00007.safetensors",
149
+ "model.layers.19.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
150
+ "model.layers.19.self_attn.v_proj.bias": "model-00003-of-00007.safetensors",
151
+ "model.layers.19.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
152
+ "model.layers.2.input_layernorm.weight": "model-00001-of-00007.safetensors",
153
+ "model.layers.2.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
154
+ "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
155
+ "model.layers.2.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
156
+ "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
157
+ "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00007.safetensors",
158
+ "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
159
+ "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
160
+ "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00007.safetensors",
161
+ "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
162
+ "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00007.safetensors",
163
+ "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
164
+ "model.layers.20.input_layernorm.weight": "model-00003-of-00007.safetensors",
165
+ "model.layers.20.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
166
+ "model.layers.20.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
167
+ "model.layers.20.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
168
+ "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
169
+ "model.layers.20.self_attn.k_proj.bias": "model-00003-of-00007.safetensors",
170
+ "model.layers.20.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
171
+ "model.layers.20.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
172
+ "model.layers.20.self_attn.q_proj.bias": "model-00003-of-00007.safetensors",
173
+ "model.layers.20.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
174
+ "model.layers.20.self_attn.v_proj.bias": "model-00003-of-00007.safetensors",
175
+ "model.layers.20.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
176
+ "model.layers.21.input_layernorm.weight": "model-00003-of-00007.safetensors",
177
+ "model.layers.21.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
178
+ "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
179
+ "model.layers.21.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
180
+ "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
181
+ "model.layers.21.self_attn.k_proj.bias": "model-00003-of-00007.safetensors",
182
+ "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
183
+ "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
184
+ "model.layers.21.self_attn.q_proj.bias": "model-00003-of-00007.safetensors",
185
+ "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
186
+ "model.layers.21.self_attn.v_proj.bias": "model-00003-of-00007.safetensors",
187
+ "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
188
+ "model.layers.22.input_layernorm.weight": "model-00003-of-00007.safetensors",
189
+ "model.layers.22.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
190
+ "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
191
+ "model.layers.22.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
192
+ "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
193
+ "model.layers.22.self_attn.k_proj.bias": "model-00003-of-00007.safetensors",
194
+ "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
195
+ "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
196
+ "model.layers.22.self_attn.q_proj.bias": "model-00003-of-00007.safetensors",
197
+ "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
198
+ "model.layers.22.self_attn.v_proj.bias": "model-00003-of-00007.safetensors",
199
+ "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
200
+ "model.layers.23.input_layernorm.weight": "model-00003-of-00007.safetensors",
201
+ "model.layers.23.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
202
+ "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
203
+ "model.layers.23.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
204
+ "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
205
+ "model.layers.23.self_attn.k_proj.bias": "model-00003-of-00007.safetensors",
206
+ "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
207
+ "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
208
+ "model.layers.23.self_attn.q_proj.bias": "model-00003-of-00007.safetensors",
209
+ "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
210
+ "model.layers.23.self_attn.v_proj.bias": "model-00003-of-00007.safetensors",
211
+ "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
212
+ "model.layers.24.input_layernorm.weight": "model-00003-of-00007.safetensors",
213
+ "model.layers.24.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
214
+ "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
215
+ "model.layers.24.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
216
+ "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
217
+ "model.layers.24.self_attn.k_proj.bias": "model-00003-of-00007.safetensors",
218
+ "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
219
+ "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
220
+ "model.layers.24.self_attn.q_proj.bias": "model-00003-of-00007.safetensors",
221
+ "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
222
+ "model.layers.24.self_attn.v_proj.bias": "model-00003-of-00007.safetensors",
223
+ "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
224
+ "model.layers.25.input_layernorm.weight": "model-00003-of-00007.safetensors",
225
+ "model.layers.25.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
226
+ "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
227
+ "model.layers.25.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
228
+ "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
229
+ "model.layers.25.self_attn.k_proj.bias": "model-00003-of-00007.safetensors",
230
+ "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
231
+ "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
232
+ "model.layers.25.self_attn.q_proj.bias": "model-00003-of-00007.safetensors",
233
+ "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
234
+ "model.layers.25.self_attn.v_proj.bias": "model-00003-of-00007.safetensors",
235
+ "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
236
+ "model.layers.26.input_layernorm.weight": "model-00003-of-00007.safetensors",
237
+ "model.layers.26.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
238
+ "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
239
+ "model.layers.26.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
240
+ "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
241
+ "model.layers.26.self_attn.k_proj.bias": "model-00003-of-00007.safetensors",
242
+ "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
243
+ "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
244
+ "model.layers.26.self_attn.q_proj.bias": "model-00003-of-00007.safetensors",
245
+ "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
246
+ "model.layers.26.self_attn.v_proj.bias": "model-00003-of-00007.safetensors",
247
+ "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
248
+ "model.layers.27.input_layernorm.weight": "model-00003-of-00007.safetensors",
249
+ "model.layers.27.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
250
+ "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
251
+ "model.layers.27.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
252
+ "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
253
+ "model.layers.27.self_attn.k_proj.bias": "model-00003-of-00007.safetensors",
254
+ "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
255
+ "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
256
+ "model.layers.27.self_attn.q_proj.bias": "model-00003-of-00007.safetensors",
257
+ "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
258
+ "model.layers.27.self_attn.v_proj.bias": "model-00003-of-00007.safetensors",
259
+ "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
260
+ "model.layers.28.input_layernorm.weight": "model-00004-of-00007.safetensors",
261
+ "model.layers.28.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
262
+ "model.layers.28.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
263
+ "model.layers.28.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
264
+ "model.layers.28.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
265
+ "model.layers.28.self_attn.k_proj.bias": "model-00003-of-00007.safetensors",
266
+ "model.layers.28.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
267
+ "model.layers.28.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
268
+ "model.layers.28.self_attn.q_proj.bias": "model-00003-of-00007.safetensors",
269
+ "model.layers.28.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
270
+ "model.layers.28.self_attn.v_proj.bias": "model-00003-of-00007.safetensors",
271
+ "model.layers.28.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
272
+ "model.layers.29.input_layernorm.weight": "model-00004-of-00007.safetensors",
273
+ "model.layers.29.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
274
+ "model.layers.29.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
275
+ "model.layers.29.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
276
+ "model.layers.29.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
277
+ "model.layers.29.self_attn.k_proj.bias": "model-00004-of-00007.safetensors",
278
+ "model.layers.29.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
279
+ "model.layers.29.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
280
+ "model.layers.29.self_attn.q_proj.bias": "model-00004-of-00007.safetensors",
281
+ "model.layers.29.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
282
+ "model.layers.29.self_attn.v_proj.bias": "model-00004-of-00007.safetensors",
283
+ "model.layers.29.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
284
+ "model.layers.3.input_layernorm.weight": "model-00001-of-00007.safetensors",
285
+ "model.layers.3.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
286
+ "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
287
+ "model.layers.3.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
288
+ "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
289
+ "model.layers.3.self_attn.k_proj.bias": "model-00001-of-00007.safetensors",
290
+ "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
291
+ "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
292
+ "model.layers.3.self_attn.q_proj.bias": "model-00001-of-00007.safetensors",
293
+ "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
294
+ "model.layers.3.self_attn.v_proj.bias": "model-00001-of-00007.safetensors",
295
+ "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
296
+ "model.layers.30.input_layernorm.weight": "model-00004-of-00007.safetensors",
297
+ "model.layers.30.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
298
+ "model.layers.30.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
299
+ "model.layers.30.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
300
+ "model.layers.30.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
301
+ "model.layers.30.self_attn.k_proj.bias": "model-00004-of-00007.safetensors",
302
+ "model.layers.30.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
303
+ "model.layers.30.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
304
+ "model.layers.30.self_attn.q_proj.bias": "model-00004-of-00007.safetensors",
305
+ "model.layers.30.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
306
+ "model.layers.30.self_attn.v_proj.bias": "model-00004-of-00007.safetensors",
307
+ "model.layers.30.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
308
+ "model.layers.31.input_layernorm.weight": "model-00004-of-00007.safetensors",
309
+ "model.layers.31.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
310
+ "model.layers.31.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
311
+ "model.layers.31.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
312
+ "model.layers.31.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
313
+ "model.layers.31.self_attn.k_proj.bias": "model-00004-of-00007.safetensors",
314
+ "model.layers.31.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
315
+ "model.layers.31.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
316
+ "model.layers.31.self_attn.q_proj.bias": "model-00004-of-00007.safetensors",
317
+ "model.layers.31.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
318
+ "model.layers.31.self_attn.v_proj.bias": "model-00004-of-00007.safetensors",
319
+ "model.layers.31.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
320
+ "model.layers.32.input_layernorm.weight": "model-00004-of-00007.safetensors",
321
+ "model.layers.32.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
322
+ "model.layers.32.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
323
+ "model.layers.32.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
324
+ "model.layers.32.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
325
+ "model.layers.32.self_attn.k_proj.bias": "model-00004-of-00007.safetensors",
326
+ "model.layers.32.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
327
+ "model.layers.32.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
328
+ "model.layers.32.self_attn.q_proj.bias": "model-00004-of-00007.safetensors",
329
+ "model.layers.32.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
330
+ "model.layers.32.self_attn.v_proj.bias": "model-00004-of-00007.safetensors",
331
+ "model.layers.32.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
332
+ "model.layers.33.input_layernorm.weight": "model-00004-of-00007.safetensors",
333
+ "model.layers.33.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
334
+ "model.layers.33.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
335
+ "model.layers.33.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
336
+ "model.layers.33.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
337
+ "model.layers.33.self_attn.k_proj.bias": "model-00004-of-00007.safetensors",
338
+ "model.layers.33.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
339
+ "model.layers.33.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
340
+ "model.layers.33.self_attn.q_proj.bias": "model-00004-of-00007.safetensors",
341
+ "model.layers.33.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
342
+ "model.layers.33.self_attn.v_proj.bias": "model-00004-of-00007.safetensors",
343
+ "model.layers.33.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
344
+ "model.layers.34.input_layernorm.weight": "model-00004-of-00007.safetensors",
345
+ "model.layers.34.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
346
+ "model.layers.34.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
347
+ "model.layers.34.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
348
+ "model.layers.34.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
349
+ "model.layers.34.self_attn.k_proj.bias": "model-00004-of-00007.safetensors",
350
+ "model.layers.34.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
351
+ "model.layers.34.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
352
+ "model.layers.34.self_attn.q_proj.bias": "model-00004-of-00007.safetensors",
353
+ "model.layers.34.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
354
+ "model.layers.34.self_attn.v_proj.bias": "model-00004-of-00007.safetensors",
355
+ "model.layers.34.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
356
+ "model.layers.35.input_layernorm.weight": "model-00004-of-00007.safetensors",
357
+ "model.layers.35.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
358
+ "model.layers.35.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
359
+ "model.layers.35.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
360
+ "model.layers.35.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
361
+ "model.layers.35.self_attn.k_proj.bias": "model-00004-of-00007.safetensors",
362
+ "model.layers.35.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
363
+ "model.layers.35.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
364
+ "model.layers.35.self_attn.q_proj.bias": "model-00004-of-00007.safetensors",
365
+ "model.layers.35.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
366
+ "model.layers.35.self_attn.v_proj.bias": "model-00004-of-00007.safetensors",
367
+ "model.layers.35.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
368
+ "model.layers.36.input_layernorm.weight": "model-00004-of-00007.safetensors",
369
+ "model.layers.36.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
370
+ "model.layers.36.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
371
+ "model.layers.36.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
372
+ "model.layers.36.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
373
+ "model.layers.36.self_attn.k_proj.bias": "model-00004-of-00007.safetensors",
374
+ "model.layers.36.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
375
+ "model.layers.36.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
376
+ "model.layers.36.self_attn.q_proj.bias": "model-00004-of-00007.safetensors",
377
+ "model.layers.36.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
378
+ "model.layers.36.self_attn.v_proj.bias": "model-00004-of-00007.safetensors",
379
+ "model.layers.36.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
380
+ "model.layers.37.input_layernorm.weight": "model-00004-of-00007.safetensors",
381
+ "model.layers.37.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
382
+ "model.layers.37.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
383
+ "model.layers.37.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
384
+ "model.layers.37.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
385
+ "model.layers.37.self_attn.k_proj.bias": "model-00004-of-00007.safetensors",
386
+ "model.layers.37.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
387
+ "model.layers.37.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
388
+ "model.layers.37.self_attn.q_proj.bias": "model-00004-of-00007.safetensors",
389
+ "model.layers.37.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
390
+ "model.layers.37.self_attn.v_proj.bias": "model-00004-of-00007.safetensors",
391
+ "model.layers.37.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
392
+ "model.layers.38.input_layernorm.weight": "model-00005-of-00007.safetensors",
393
+ "model.layers.38.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
394
+ "model.layers.38.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
395
+ "model.layers.38.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
396
+ "model.layers.38.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
397
+ "model.layers.38.self_attn.k_proj.bias": "model-00004-of-00007.safetensors",
398
+ "model.layers.38.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
399
+ "model.layers.38.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
400
+ "model.layers.38.self_attn.q_proj.bias": "model-00004-of-00007.safetensors",
401
+ "model.layers.38.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
402
+ "model.layers.38.self_attn.v_proj.bias": "model-00004-of-00007.safetensors",
403
+ "model.layers.38.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
404
+ "model.layers.39.input_layernorm.weight": "model-00005-of-00007.safetensors",
405
+ "model.layers.39.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
406
+ "model.layers.39.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
407
+ "model.layers.39.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
408
+ "model.layers.39.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
409
+ "model.layers.39.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
410
+ "model.layers.39.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
411
+ "model.layers.39.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
412
+ "model.layers.39.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
413
+ "model.layers.39.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
414
+ "model.layers.39.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
415
+ "model.layers.39.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
416
+ "model.layers.4.input_layernorm.weight": "model-00001-of-00007.safetensors",
417
+ "model.layers.4.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
418
+ "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
419
+ "model.layers.4.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
420
+ "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
421
+ "model.layers.4.self_attn.k_proj.bias": "model-00001-of-00007.safetensors",
422
+ "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
423
+ "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
424
+ "model.layers.4.self_attn.q_proj.bias": "model-00001-of-00007.safetensors",
425
+ "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
426
+ "model.layers.4.self_attn.v_proj.bias": "model-00001-of-00007.safetensors",
427
+ "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
428
+ "model.layers.40.input_layernorm.weight": "model-00005-of-00007.safetensors",
429
+ "model.layers.40.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
430
+ "model.layers.40.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
431
+ "model.layers.40.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
432
+ "model.layers.40.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
433
+ "model.layers.40.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
434
+ "model.layers.40.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
435
+ "model.layers.40.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
436
+ "model.layers.40.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
437
+ "model.layers.40.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
438
+ "model.layers.40.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
439
+ "model.layers.40.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
440
+ "model.layers.41.input_layernorm.weight": "model-00005-of-00007.safetensors",
441
+ "model.layers.41.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
442
+ "model.layers.41.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
443
+ "model.layers.41.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
444
+ "model.layers.41.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
445
+ "model.layers.41.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
446
+ "model.layers.41.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
447
+ "model.layers.41.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
448
+ "model.layers.41.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
449
+ "model.layers.41.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
450
+ "model.layers.41.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
451
+ "model.layers.41.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
452
+ "model.layers.42.input_layernorm.weight": "model-00005-of-00007.safetensors",
453
+ "model.layers.42.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
454
+ "model.layers.42.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
455
+ "model.layers.42.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
456
+ "model.layers.42.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
457
+ "model.layers.42.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
458
+ "model.layers.42.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
459
+ "model.layers.42.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
460
+ "model.layers.42.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
461
+ "model.layers.42.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
462
+ "model.layers.42.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
463
+ "model.layers.42.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
464
+ "model.layers.43.input_layernorm.weight": "model-00005-of-00007.safetensors",
465
+ "model.layers.43.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
466
+ "model.layers.43.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
467
+ "model.layers.43.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
468
+ "model.layers.43.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
469
+ "model.layers.43.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
470
+ "model.layers.43.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
471
+ "model.layers.43.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
472
+ "model.layers.43.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
473
+ "model.layers.43.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
474
+ "model.layers.43.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
475
+ "model.layers.43.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
476
+ "model.layers.44.input_layernorm.weight": "model-00005-of-00007.safetensors",
477
+ "model.layers.44.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
478
+ "model.layers.44.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
479
+ "model.layers.44.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
480
+ "model.layers.44.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
481
+ "model.layers.44.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
482
+ "model.layers.44.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
483
+ "model.layers.44.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
484
+ "model.layers.44.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
485
+ "model.layers.44.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
486
+ "model.layers.44.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
487
+ "model.layers.44.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
488
+ "model.layers.45.input_layernorm.weight": "model-00005-of-00007.safetensors",
489
+ "model.layers.45.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
490
+ "model.layers.45.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
491
+ "model.layers.45.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
492
+ "model.layers.45.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
493
+ "model.layers.45.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
494
+ "model.layers.45.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
495
+ "model.layers.45.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
496
+ "model.layers.45.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
497
+ "model.layers.45.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
498
+ "model.layers.45.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
499
+ "model.layers.45.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
500
+ "model.layers.46.input_layernorm.weight": "model-00005-of-00007.safetensors",
501
+ "model.layers.46.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
502
+ "model.layers.46.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
503
+ "model.layers.46.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
504
+ "model.layers.46.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
505
+ "model.layers.46.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
506
+ "model.layers.46.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
507
+ "model.layers.46.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
508
+ "model.layers.46.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
509
+ "model.layers.46.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
510
+ "model.layers.46.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
511
+ "model.layers.46.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
512
+ "model.layers.47.input_layernorm.weight": "model-00005-of-00007.safetensors",
513
+ "model.layers.47.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
514
+ "model.layers.47.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
515
+ "model.layers.47.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
516
+ "model.layers.47.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
517
+ "model.layers.47.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
518
+ "model.layers.47.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
519
+ "model.layers.47.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
520
+ "model.layers.47.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
521
+ "model.layers.47.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
522
+ "model.layers.47.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
523
+ "model.layers.47.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
524
+ "model.layers.48.input_layernorm.weight": "model-00006-of-00007.safetensors",
525
+ "model.layers.48.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
526
+ "model.layers.48.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
527
+ "model.layers.48.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
528
+ "model.layers.48.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
529
+ "model.layers.48.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
530
+ "model.layers.48.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
531
+ "model.layers.48.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
532
+ "model.layers.48.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
533
+ "model.layers.48.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
534
+ "model.layers.48.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
535
+ "model.layers.48.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
536
+ "model.layers.49.input_layernorm.weight": "model-00006-of-00007.safetensors",
537
+ "model.layers.49.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
538
+ "model.layers.49.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
539
+ "model.layers.49.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
540
+ "model.layers.49.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
541
+ "model.layers.49.self_attn.k_proj.bias": "model-00006-of-00007.safetensors",
542
+ "model.layers.49.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
543
+ "model.layers.49.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
544
+ "model.layers.49.self_attn.q_proj.bias": "model-00006-of-00007.safetensors",
545
+ "model.layers.49.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
546
+ "model.layers.49.self_attn.v_proj.bias": "model-00006-of-00007.safetensors",
547
+ "model.layers.49.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
548
+ "model.layers.5.input_layernorm.weight": "model-00001-of-00007.safetensors",
549
+ "model.layers.5.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
550
+ "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
551
+ "model.layers.5.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
552
+ "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
553
+ "model.layers.5.self_attn.k_proj.bias": "model-00001-of-00007.safetensors",
554
+ "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
555
+ "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
556
+ "model.layers.5.self_attn.q_proj.bias": "model-00001-of-00007.safetensors",
557
+ "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
558
+ "model.layers.5.self_attn.v_proj.bias": "model-00001-of-00007.safetensors",
559
+ "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
560
+ "model.layers.50.input_layernorm.weight": "model-00006-of-00007.safetensors",
561
+ "model.layers.50.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
562
+ "model.layers.50.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
563
+ "model.layers.50.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
564
+ "model.layers.50.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
565
+ "model.layers.50.self_attn.k_proj.bias": "model-00006-of-00007.safetensors",
566
+ "model.layers.50.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
567
+ "model.layers.50.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
568
+ "model.layers.50.self_attn.q_proj.bias": "model-00006-of-00007.safetensors",
569
+ "model.layers.50.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
570
+ "model.layers.50.self_attn.v_proj.bias": "model-00006-of-00007.safetensors",
571
+ "model.layers.50.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
572
+ "model.layers.51.input_layernorm.weight": "model-00006-of-00007.safetensors",
573
+ "model.layers.51.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
574
+ "model.layers.51.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
575
+ "model.layers.51.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
576
+ "model.layers.51.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
577
+ "model.layers.51.self_attn.k_proj.bias": "model-00006-of-00007.safetensors",
578
+ "model.layers.51.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
579
+ "model.layers.51.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
580
+ "model.layers.51.self_attn.q_proj.bias": "model-00006-of-00007.safetensors",
581
+ "model.layers.51.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
582
+ "model.layers.51.self_attn.v_proj.bias": "model-00006-of-00007.safetensors",
583
+ "model.layers.51.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
584
+ "model.layers.52.input_layernorm.weight": "model-00006-of-00007.safetensors",
585
+ "model.layers.52.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
586
+ "model.layers.52.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
587
+ "model.layers.52.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
588
+ "model.layers.52.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
589
+ "model.layers.52.self_attn.k_proj.bias": "model-00006-of-00007.safetensors",
590
+ "model.layers.52.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
591
+ "model.layers.52.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
592
+ "model.layers.52.self_attn.q_proj.bias": "model-00006-of-00007.safetensors",
593
+ "model.layers.52.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
594
+ "model.layers.52.self_attn.v_proj.bias": "model-00006-of-00007.safetensors",
595
+ "model.layers.52.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
596
+ "model.layers.53.input_layernorm.weight": "model-00006-of-00007.safetensors",
597
+ "model.layers.53.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
598
+ "model.layers.53.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
599
+ "model.layers.53.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
600
+ "model.layers.53.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
601
+ "model.layers.53.self_attn.k_proj.bias": "model-00006-of-00007.safetensors",
602
+ "model.layers.53.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
603
+ "model.layers.53.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
604
+ "model.layers.53.self_attn.q_proj.bias": "model-00006-of-00007.safetensors",
605
+ "model.layers.53.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
606
+ "model.layers.53.self_attn.v_proj.bias": "model-00006-of-00007.safetensors",
607
+ "model.layers.53.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
608
+ "model.layers.54.input_layernorm.weight": "model-00006-of-00007.safetensors",
609
+ "model.layers.54.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
610
+ "model.layers.54.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
611
+ "model.layers.54.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
612
+ "model.layers.54.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
613
+ "model.layers.54.self_attn.k_proj.bias": "model-00006-of-00007.safetensors",
614
+ "model.layers.54.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
615
+ "model.layers.54.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
616
+ "model.layers.54.self_attn.q_proj.bias": "model-00006-of-00007.safetensors",
617
+ "model.layers.54.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
618
+ "model.layers.54.self_attn.v_proj.bias": "model-00006-of-00007.safetensors",
619
+ "model.layers.54.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
620
+ "model.layers.55.input_layernorm.weight": "model-00006-of-00007.safetensors",
621
+ "model.layers.55.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
622
+ "model.layers.55.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
623
+ "model.layers.55.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
624
+ "model.layers.55.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
625
+ "model.layers.55.self_attn.k_proj.bias": "model-00006-of-00007.safetensors",
626
+ "model.layers.55.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
627
+ "model.layers.55.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
628
+ "model.layers.55.self_attn.q_proj.bias": "model-00006-of-00007.safetensors",
629
+ "model.layers.55.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
630
+ "model.layers.55.self_attn.v_proj.bias": "model-00006-of-00007.safetensors",
631
+ "model.layers.55.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
632
+ "model.layers.56.input_layernorm.weight": "model-00006-of-00007.safetensors",
633
+ "model.layers.56.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
634
+ "model.layers.56.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
635
+ "model.layers.56.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
636
+ "model.layers.56.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
637
+ "model.layers.56.self_attn.k_proj.bias": "model-00006-of-00007.safetensors",
638
+ "model.layers.56.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
639
+ "model.layers.56.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
640
+ "model.layers.56.self_attn.q_proj.bias": "model-00006-of-00007.safetensors",
641
+ "model.layers.56.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
642
+ "model.layers.56.self_attn.v_proj.bias": "model-00006-of-00007.safetensors",
643
+ "model.layers.56.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
644
+ "model.layers.57.input_layernorm.weight": "model-00006-of-00007.safetensors",
645
+ "model.layers.57.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
646
+ "model.layers.57.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
647
+ "model.layers.57.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
648
+ "model.layers.57.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
649
+ "model.layers.57.self_attn.k_proj.bias": "model-00006-of-00007.safetensors",
650
+ "model.layers.57.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
651
+ "model.layers.57.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
652
+ "model.layers.57.self_attn.q_proj.bias": "model-00006-of-00007.safetensors",
653
+ "model.layers.57.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
654
+ "model.layers.57.self_attn.v_proj.bias": "model-00006-of-00007.safetensors",
655
+ "model.layers.57.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
656
+ "model.layers.58.input_layernorm.weight": "model-00007-of-00007.safetensors",
657
+ "model.layers.58.mlp.down_proj.weight": "model-00007-of-00007.safetensors",
658
+ "model.layers.58.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
659
+ "model.layers.58.mlp.up_proj.weight": "model-00007-of-00007.safetensors",
660
+ "model.layers.58.post_attention_layernorm.weight": "model-00007-of-00007.safetensors",
661
+ "model.layers.58.self_attn.k_proj.bias": "model-00006-of-00007.safetensors",
662
+ "model.layers.58.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
663
+ "model.layers.58.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
664
+ "model.layers.58.self_attn.q_proj.bias": "model-00006-of-00007.safetensors",
665
+ "model.layers.58.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
666
+ "model.layers.58.self_attn.v_proj.bias": "model-00006-of-00007.safetensors",
667
+ "model.layers.58.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
668
+ "model.layers.59.input_layernorm.weight": "model-00007-of-00007.safetensors",
669
+ "model.layers.59.mlp.down_proj.weight": "model-00007-of-00007.safetensors",
670
+ "model.layers.59.mlp.gate_proj.weight": "model-00007-of-00007.safetensors",
671
+ "model.layers.59.mlp.up_proj.weight": "model-00007-of-00007.safetensors",
672
+ "model.layers.59.post_attention_layernorm.weight": "model-00007-of-00007.safetensors",
673
+ "model.layers.59.self_attn.k_proj.bias": "model-00007-of-00007.safetensors",
674
+ "model.layers.59.self_attn.k_proj.weight": "model-00007-of-00007.safetensors",
675
+ "model.layers.59.self_attn.o_proj.weight": "model-00007-of-00007.safetensors",
676
+ "model.layers.59.self_attn.q_proj.bias": "model-00007-of-00007.safetensors",
677
+ "model.layers.59.self_attn.q_proj.weight": "model-00007-of-00007.safetensors",
678
+ "model.layers.59.self_attn.v_proj.bias": "model-00007-of-00007.safetensors",
679
+ "model.layers.59.self_attn.v_proj.weight": "model-00007-of-00007.safetensors",
680
+ "model.layers.6.input_layernorm.weight": "model-00001-of-00007.safetensors",
681
+ "model.layers.6.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
682
+ "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
683
+ "model.layers.6.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
684
+ "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
685
+ "model.layers.6.self_attn.k_proj.bias": "model-00001-of-00007.safetensors",
686
+ "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
687
+ "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
688
+ "model.layers.6.self_attn.q_proj.bias": "model-00001-of-00007.safetensors",
689
+ "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
690
+ "model.layers.6.self_attn.v_proj.bias": "model-00001-of-00007.safetensors",
691
+ "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
692
+ "model.layers.60.input_layernorm.weight": "model-00007-of-00007.safetensors",
693
+ "model.layers.60.mlp.down_proj.weight": "model-00007-of-00007.safetensors",
694
+ "model.layers.60.mlp.gate_proj.weight": "model-00007-of-00007.safetensors",
695
+ "model.layers.60.mlp.up_proj.weight": "model-00007-of-00007.safetensors",
696
+ "model.layers.60.post_attention_layernorm.weight": "model-00007-of-00007.safetensors",
697
+ "model.layers.60.self_attn.k_proj.bias": "model-00007-of-00007.safetensors",
698
+ "model.layers.60.self_attn.k_proj.weight": "model-00007-of-00007.safetensors",
699
+ "model.layers.60.self_attn.o_proj.weight": "model-00007-of-00007.safetensors",
700
+ "model.layers.60.self_attn.q_proj.bias": "model-00007-of-00007.safetensors",
701
+ "model.layers.60.self_attn.q_proj.weight": "model-00007-of-00007.safetensors",
702
+ "model.layers.60.self_attn.v_proj.bias": "model-00007-of-00007.safetensors",
703
+ "model.layers.60.self_attn.v_proj.weight": "model-00007-of-00007.safetensors",
704
+ "model.layers.61.input_layernorm.weight": "model-00007-of-00007.safetensors",
705
+ "model.layers.61.mlp.down_proj.weight": "model-00007-of-00007.safetensors",
706
+ "model.layers.61.mlp.gate_proj.weight": "model-00007-of-00007.safetensors",
707
+ "model.layers.61.mlp.up_proj.weight": "model-00007-of-00007.safetensors",
708
+ "model.layers.61.post_attention_layernorm.weight": "model-00007-of-00007.safetensors",
709
+ "model.layers.61.self_attn.k_proj.bias": "model-00007-of-00007.safetensors",
710
+ "model.layers.61.self_attn.k_proj.weight": "model-00007-of-00007.safetensors",
711
+ "model.layers.61.self_attn.o_proj.weight": "model-00007-of-00007.safetensors",
712
+ "model.layers.61.self_attn.q_proj.bias": "model-00007-of-00007.safetensors",
713
+ "model.layers.61.self_attn.q_proj.weight": "model-00007-of-00007.safetensors",
714
+ "model.layers.61.self_attn.v_proj.bias": "model-00007-of-00007.safetensors",
715
+ "model.layers.61.self_attn.v_proj.weight": "model-00007-of-00007.safetensors",
716
+ "model.layers.62.input_layernorm.weight": "model-00007-of-00007.safetensors",
717
+ "model.layers.62.mlp.down_proj.weight": "model-00007-of-00007.safetensors",
718
+ "model.layers.62.mlp.gate_proj.weight": "model-00007-of-00007.safetensors",
719
+ "model.layers.62.mlp.up_proj.weight": "model-00007-of-00007.safetensors",
720
+ "model.layers.62.post_attention_layernorm.weight": "model-00007-of-00007.safetensors",
721
+ "model.layers.62.self_attn.k_proj.bias": "model-00007-of-00007.safetensors",
722
+ "model.layers.62.self_attn.k_proj.weight": "model-00007-of-00007.safetensors",
723
+ "model.layers.62.self_attn.o_proj.weight": "model-00007-of-00007.safetensors",
724
+ "model.layers.62.self_attn.q_proj.bias": "model-00007-of-00007.safetensors",
725
+ "model.layers.62.self_attn.q_proj.weight": "model-00007-of-00007.safetensors",
726
+ "model.layers.62.self_attn.v_proj.bias": "model-00007-of-00007.safetensors",
727
+ "model.layers.62.self_attn.v_proj.weight": "model-00007-of-00007.safetensors",
728
+ "model.layers.63.input_layernorm.weight": "model-00007-of-00007.safetensors",
729
+ "model.layers.63.mlp.down_proj.weight": "model-00007-of-00007.safetensors",
730
+ "model.layers.63.mlp.gate_proj.weight": "model-00007-of-00007.safetensors",
731
+ "model.layers.63.mlp.up_proj.weight": "model-00007-of-00007.safetensors",
732
+ "model.layers.63.post_attention_layernorm.weight": "model-00007-of-00007.safetensors",
733
+ "model.layers.63.self_attn.k_proj.bias": "model-00007-of-00007.safetensors",
734
+ "model.layers.63.self_attn.k_proj.weight": "model-00007-of-00007.safetensors",
735
+ "model.layers.63.self_attn.o_proj.weight": "model-00007-of-00007.safetensors",
736
+ "model.layers.63.self_attn.q_proj.bias": "model-00007-of-00007.safetensors",
737
+ "model.layers.63.self_attn.q_proj.weight": "model-00007-of-00007.safetensors",
738
+ "model.layers.63.self_attn.v_proj.bias": "model-00007-of-00007.safetensors",
739
+ "model.layers.63.self_attn.v_proj.weight": "model-00007-of-00007.safetensors",
740
+ "model.layers.7.input_layernorm.weight": "model-00001-of-00007.safetensors",
741
+ "model.layers.7.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
742
+ "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
743
+ "model.layers.7.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
744
+ "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
745
+ "model.layers.7.self_attn.k_proj.bias": "model-00001-of-00007.safetensors",
746
+ "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
747
+ "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
748
+ "model.layers.7.self_attn.q_proj.bias": "model-00001-of-00007.safetensors",
749
+ "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
750
+ "model.layers.7.self_attn.v_proj.bias": "model-00001-of-00007.safetensors",
751
+ "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
752
+ "model.layers.8.input_layernorm.weight": "model-00002-of-00007.safetensors",
753
+ "model.layers.8.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
754
+ "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
755
+ "model.layers.8.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
756
+ "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
757
+ "model.layers.8.self_attn.k_proj.bias": "model-00001-of-00007.safetensors",
758
+ "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
759
+ "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
760
+ "model.layers.8.self_attn.q_proj.bias": "model-00001-of-00007.safetensors",
761
+ "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
762
+ "model.layers.8.self_attn.v_proj.bias": "model-00001-of-00007.safetensors",
763
+ "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
764
+ "model.layers.9.input_layernorm.weight": "model-00002-of-00007.safetensors",
765
+ "model.layers.9.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
766
+ "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
767
+ "model.layers.9.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
768
+ "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
769
+ "model.layers.9.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
770
+ "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
771
+ "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
772
+ "model.layers.9.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
773
+ "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
774
+ "model.layers.9.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
775
+ "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
776
+ "model.norm.weight": "model-00007-of-00007.safetensors"
777
+ }
778
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|im_start|>",
4
+ "<|im_end|>",
5
+ "<|object_ref_start|>",
6
+ "<|object_ref_end|>",
7
+ "<|box_start|>",
8
+ "<|box_end|>",
9
+ "<|quad_start|>",
10
+ "<|quad_end|>",
11
+ "<|vision_start|>",
12
+ "<|vision_end|>",
13
+ "<|vision_pad|>",
14
+ "<|image_pad|>",
15
+ "<|video_pad|>"
16
+ ],
17
+ "eos_token": {
18
+ "content": "<|im_end|>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ },
24
+ "pad_token": {
25
+ "content": "<|vision_pad|>",
26
+ "lstrip": false,
27
+ "normalized": false,
28
+ "rstrip": false,
29
+ "single_word": false
30
+ }
31
+ }
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
3
+ size 11421896
tokenizer_config.json ADDED
@@ -0,0 +1,209 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_prefix_space": false,
4
+ "added_tokens_decoder": {
5
+ "151643": {
6
+ "content": "<|endoftext|>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "151644": {
14
+ "content": "<|im_start|>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "151645": {
22
+ "content": "<|im_end|>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ },
29
+ "151646": {
30
+ "content": "<|object_ref_start|>",
31
+ "lstrip": false,
32
+ "normalized": false,
33
+ "rstrip": false,
34
+ "single_word": false,
35
+ "special": true
36
+ },
37
+ "151647": {
38
+ "content": "<|object_ref_end|>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false,
43
+ "special": true
44
+ },
45
+ "151648": {
46
+ "content": "<|box_start|>",
47
+ "lstrip": false,
48
+ "normalized": false,
49
+ "rstrip": false,
50
+ "single_word": false,
51
+ "special": true
52
+ },
53
+ "151649": {
54
+ "content": "<|box_end|>",
55
+ "lstrip": false,
56
+ "normalized": false,
57
+ "rstrip": false,
58
+ "single_word": false,
59
+ "special": true
60
+ },
61
+ "151650": {
62
+ "content": "<|quad_start|>",
63
+ "lstrip": false,
64
+ "normalized": false,
65
+ "rstrip": false,
66
+ "single_word": false,
67
+ "special": true
68
+ },
69
+ "151651": {
70
+ "content": "<|quad_end|>",
71
+ "lstrip": false,
72
+ "normalized": false,
73
+ "rstrip": false,
74
+ "single_word": false,
75
+ "special": true
76
+ },
77
+ "151652": {
78
+ "content": "<|vision_start|>",
79
+ "lstrip": false,
80
+ "normalized": false,
81
+ "rstrip": false,
82
+ "single_word": false,
83
+ "special": true
84
+ },
85
+ "151653": {
86
+ "content": "<|vision_end|>",
87
+ "lstrip": false,
88
+ "normalized": false,
89
+ "rstrip": false,
90
+ "single_word": false,
91
+ "special": true
92
+ },
93
+ "151654": {
94
+ "content": "<|vision_pad|>",
95
+ "lstrip": false,
96
+ "normalized": false,
97
+ "rstrip": false,
98
+ "single_word": false,
99
+ "special": true
100
+ },
101
+ "151655": {
102
+ "content": "<|image_pad|>",
103
+ "lstrip": false,
104
+ "normalized": false,
105
+ "rstrip": false,
106
+ "single_word": false,
107
+ "special": true
108
+ },
109
+ "151656": {
110
+ "content": "<|video_pad|>",
111
+ "lstrip": false,
112
+ "normalized": false,
113
+ "rstrip": false,
114
+ "single_word": false,
115
+ "special": true
116
+ },
117
+ "151657": {
118
+ "content": "<tool_call>",
119
+ "lstrip": false,
120
+ "normalized": false,
121
+ "rstrip": false,
122
+ "single_word": false,
123
+ "special": false
124
+ },
125
+ "151658": {
126
+ "content": "</tool_call>",
127
+ "lstrip": false,
128
+ "normalized": false,
129
+ "rstrip": false,
130
+ "single_word": false,
131
+ "special": false
132
+ },
133
+ "151659": {
134
+ "content": "<|fim_prefix|>",
135
+ "lstrip": false,
136
+ "normalized": false,
137
+ "rstrip": false,
138
+ "single_word": false,
139
+ "special": false
140
+ },
141
+ "151660": {
142
+ "content": "<|fim_middle|>",
143
+ "lstrip": false,
144
+ "normalized": false,
145
+ "rstrip": false,
146
+ "single_word": false,
147
+ "special": false
148
+ },
149
+ "151661": {
150
+ "content": "<|fim_suffix|>",
151
+ "lstrip": false,
152
+ "normalized": false,
153
+ "rstrip": false,
154
+ "single_word": false,
155
+ "special": false
156
+ },
157
+ "151662": {
158
+ "content": "<|fim_pad|>",
159
+ "lstrip": false,
160
+ "normalized": false,
161
+ "rstrip": false,
162
+ "single_word": false,
163
+ "special": false
164
+ },
165
+ "151663": {
166
+ "content": "<|repo_name|>",
167
+ "lstrip": false,
168
+ "normalized": false,
169
+ "rstrip": false,
170
+ "single_word": false,
171
+ "special": false
172
+ },
173
+ "151664": {
174
+ "content": "<|file_sep|>",
175
+ "lstrip": false,
176
+ "normalized": false,
177
+ "rstrip": false,
178
+ "single_word": false,
179
+ "special": false
180
+ }
181
+ },
182
+ "additional_special_tokens": [
183
+ "<|im_start|>",
184
+ "<|im_end|>",
185
+ "<|object_ref_start|>",
186
+ "<|object_ref_end|>",
187
+ "<|box_start|>",
188
+ "<|box_end|>",
189
+ "<|quad_start|>",
190
+ "<|quad_end|>",
191
+ "<|vision_start|>",
192
+ "<|vision_end|>",
193
+ "<|vision_pad|>",
194
+ "<|image_pad|>",
195
+ "<|video_pad|>"
196
+ ],
197
+ "bos_token": null,
198
+ "clean_up_tokenization_spaces": false,
199
+ "eos_token": "<|im_end|>",
200
+ "errors": "replace",
201
+ "extra_special_tokens": {},
202
+ "model_max_length": 131072,
203
+ "pad_token": "<|vision_pad|>",
204
+ "padding_side": "left",
205
+ "split_special_tokens": false,
206
+ "tokenizer_class": "Qwen2Tokenizer",
207
+ "unk_token": null,
208
+ "chat_template": "{%- if messages[0]['role'] == 'system' %}\n {{- '<|im_start|>system\n' + messages[0]['content'] + '<|im_end|>\n' }}\n{%- else %}\n {{- '<|im_start|>system\n<|im_end|>\n' }}\n{%- endif %}\n{%- for message in messages %}\n {%- if (message.role == 'user') or (message.role == 'system' and not loop.first) or (message.role == 'assistant') %}\n {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|im_start|>assistant\n' }}\n{%- endif %}"
209
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff