Hugging Face's logo

MikeRoz
/
deepseek-ai_DeepSeek-R1-Distill-Llama-70B-8.0bpw-h8-exl2

Safetensors
llama
8-bit precision
exl2
Model card Files Community
MikeRoz commited on
Commit
1060da5
·
verified ·
1 Parent(s): 6c5ae72

Upload folder using huggingface_hub

Browse files
Files changed (15) hide show
  1. README.md +209 -0
  2. config.json +50 -0
  3. huggingface-metadata.txt +21 -0
  4. measurement.json +0 -0
  5. model.safetensors.index.json +730 -0
  6. output-00001-of-00008.safetensors +3 -0
  7. output-00002-of-00008.safetensors +3 -0
  8. output-00003-of-00008.safetensors +3 -0
  9. output-00004-of-00008.safetensors +3 -0
  10. output-00005-of-00008.safetensors +3 -0
  11. output-00006-of-00008.safetensors +3 -0
  12. output-00007-of-00008.safetensors +3 -0
  13. output-00008-of-00008.safetensors +3 -0
  14. tokenizer.json +0 -0
  15. tokenizer_config.json +35 -0
README.md ADDED
@@ -0,0 +1,209 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ # DeepSeek-R1
2
+ <!-- markdownlint-disable first-line-h1 -->
3
+ <!-- markdownlint-disable html -->
4
+ <!-- markdownlint-disable no-duplicate-header -->
5
+
6
+ <div align="center">
7
+ <img src="https://github.com/deepseek-ai/DeepSeek-V2/blob/main/figures/logo.svg?raw=true" width="60%" alt="DeepSeek-V3" />
8
+ </div>
9
+ <hr>
10
+ <div align="center" style="line-height: 1;">
11
+ <a href="https://www.deepseek.com/" target="_blank" style="margin: 2px;">
12
+ <img alt="Homepage" src="https://github.com/deepseek-ai/DeepSeek-V2/blob/main/figures/badge.svg?raw=true" style="display: inline-block; vertical-align: middle;"/>
13
+ </a>
14
+ <a href="https://chat.deepseek.com/" target="_blank" style="margin: 2px;">
15
+ <img alt="Chat" src="https://img.shields.io/badge/🤖%20Chat-DeepSeek%20R1-536af5?color=536af5&logoColor=white" style="display: inline-block; vertical-align: middle;"/>
16
+ </a>
17
+ <a href="https://huggingface.co/deepseek-ai" target="_blank" style="margin: 2px;">
18
+ <img alt="Hugging Face" src="https://img.shields.io/badge/%F0%9F%A4%97%20Hugging%20Face-DeepSeek%20AI-ffc107?color=ffc107&logoColor=white" style="display: inline-block; vertical-align: middle;"/>
19
+ </a>
20
+ </div>
21
+
22
+ <div align="center" style="line-height: 1;">
23
+ <a href="https://discord.gg/Tc7c45Zzu5" target="_blank" style="margin: 2px;">
24
+ <img alt="Discord" src="https://img.shields.io/badge/Discord-DeepSeek%20AI-7289da?logo=discord&logoColor=white&color=7289da" style="display: inline-block; vertical-align: middle;"/>
25
+ </a>
26
+ <a href="https://github.com/deepseek-ai/DeepSeek-V2/blob/main/figures/qr.jpeg?raw=true" target="_blank" style="margin: 2px;">
27
+ <img alt="Wechat" src="https://img.shields.io/badge/WeChat-DeepSeek%20AI-brightgreen?logo=wechat&logoColor=white" style="display: inline-block; vertical-align: middle;"/>
28
+ </a>
29
+ <a href="https://twitter.com/deepseek_ai" target="_blank" style="margin: 2px;">
30
+ <img alt="Twitter Follow" src="https://img.shields.io/badge/Twitter-deepseek_ai-white?logo=x&logoColor=white" style="display: inline-block; vertical-align: middle;"/>
31
+ </a>
32
+ </div>
33
+
34
+ <div align="center" style="line-height: 1;">
35
+ <a href="https://github.com/deepseek-ai/DeepSeek-R1/blob/main/LICENSE-CODE" style="margin: 2px;">
36
+ <img alt="Code License" src="https://img.shields.io/badge/Code_License-MIT-f5de53?&color=f5de53" style="display: inline-block; vertical-align: middle;"/>
37
+ </a>
38
+ <a href="https://github.com/deepseek-ai/DeepSeek-R1/blob/main/LICENSE-MODEL" style="margin: 2px;">
39
+ <img alt="Model License" src="https://img.shields.io/badge/Model_License-Model_Agreement-f5de53?&color=f5de53" style="display: inline-block; vertical-align: middle;"/>
40
+ </a>
41
+ </div>
42
+
43
+
44
+ <p align="center">
45
+ <a href="https://github.com/deepseek-ai/DeepSeek-R1/blob/main/DeepSeek_R1.pdf"><b>Paper Link</b>👁️</a>
46
+ </p>
47
+
48
+
49
+ ## 1. Introduction
50
+
51
+ We introduce our first-generation reasoning models, DeepSeek-R1-Zero and DeepSeek-R1.
52
+ DeepSeek-R1-Zero, a model trained via large-scale reinforcement learning (RL) without supervised fine-tuning (SFT) as a preliminary step, demonstrated remarkable performance on reasoning.
53
+ With RL, DeepSeek-R1-Zero naturally emerged with numerous powerful and interesting reasoning behaviors.
54
+ However, DeepSeek-R1-Zero encounters challenges such as endless repetition, poor readability, and language mixing. To address these issues and further enhance reasoning performance,
55
+ we introduce DeepSeek-R1, which incorporates cold-start data before RL.
56
+ DeepSeek-R1 achieves performance comparable to OpenAI-o1 across math, code, and reasoning tasks.
57
+ To support the research community, we have open-sourced DeepSeek-R1-Zero, DeepSeek-R1, and six dense models distilled from DeepSeek-R1 based on Llama and Qwen. DeepSeek-R1-Distill-Qwen-32B outperforms OpenAI-o1-mini across various benchmarks, achieving new state-of-the-art results for dense models.
58
+
59
+ <p align="center">
60
+ <img width="80%" src="figures/benchmark.jpg">
61
+ </p>
62
+
63
+ ## 2. Model Summary
64
+
65
+ ---
66
+
67
+ **Post-Training: Large-Scale Reinforcement Learning on the Base Model**
68
+
69
+ - We directly apply reinforcement learning (RL) to the base model without relying on supervised fine-tuning (SFT) as a preliminary step. This approach allows the model to explore chain-of-thought (CoT) for solving complex problems, resulting in the development of DeepSeek-R1-Zero. DeepSeek-R1-Zero demonstrates capabilities such as self-verification, reflection, and generating long CoTs, marking a significant milestone for the research community. Notably, it is the first open research to validate that reasoning capabilities of LLMs can be incentivized purely through RL, without the need for SFT. This breakthrough paves the way for future advancements in this area.
70
+
71
+ - We introduce our pipeline to develop DeepSeek-R1. The pipeline incorporates two RL stages aimed at discovering improved reasoning patterns and aligning with human preferences, as well as two SFT stages that serve as the seed for the model's reasoning and non-reasoning capabilities.
72
+ We believe the pipeline will benefit the industry by creating better models.
73
+
74
+ ---
75
+
76
+ **Distillation: Smaller Models Can Be Powerful Too**
77
+
78
+ - We demonstrate that the reasoning patterns of larger models can be distilled into smaller models, resulting in better performance compared to the reasoning patterns discovered through RL on small models. The open source DeepSeek-R1, as well as its API, will benefit the research community to distill better smaller models in the future.
79
+ - Using the reasoning data generated by DeepSeek-R1, we fine-tuned several dense models that are widely used in the research community. The evaluation results demonstrate that the distilled smaller dense models perform exceptionally well on benchmarks. We open-source distilled 1.5B, 7B, 8B, 14B, 32B, and 70B checkpoints based on Qwen2.5 and Llama3 series to the community.
80
+
81
+ ## 3. Model Downloads
82
+
83
+ ### DeepSeek-R1 Models
84
+
85
+ <div align="center">
86
+
87
+ | **Model** | **#Total Params** | **#Activated Params** | **Context Length** | **Download** |
88
+ | :------------: | :------------: | :------------: | :------------: | :------------: |
89
+ | DeepSeek-R1-Zero | 671B | 37B | 128K | [🤗 HuggingFace](https://huggingface.co/deepseek-ai/DeepSeek-R1-Zero) |
90
+ | DeepSeek-R1 | 671B | 37B | 128K | [🤗 HuggingFace](https://huggingface.co/deepseek-ai/DeepSeek-R1) |
91
+
92
+ </div>
93
+
94
+ DeepSeek-R1-Zero & DeepSeek-R1 are trained based on DeepSeek-V3-Base.
95
+ For more details regrading the model architecture, please refer to [DeepSeek-V3](https://github.com/deepseek-ai/DeepSeek-V3) repository.
96
+
97
+ ### DeepSeek-R1-Distill Models
98
+
99
+ <div align="center">
100
+
101
+ | **Model** | **Base Model** | **Download** |
102
+ | :------------: | :------------: | :------------: |
103
+ | DeepSeek-R1-Distill-Qwen-1.5B | [Qwen2.5-Math-1.5B](https://huggingface.co/Qwen/Qwen2.5-Math-1.5B) | [🤗 HuggingFace](https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B) |
104
+ | DeepSeek-R1-Distill-Qwen-7B | [Qwen2.5-Math-7B](https://huggingface.co/Qwen/Qwen2.5-Math-7B) | [🤗 HuggingFace](https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-7B) |
105
+ | DeepSeek-R1-Distill-Llama-8B | [Llama-3.1-8B](https://huggingface.co/meta-llama/Llama-3.1-8B) | [🤗 HuggingFace](https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Llama-8B) |
106
+ | DeepSeek-R1-Distill-Qwen-14B | [Qwen2.5-14B](https://huggingface.co/Qwen/Qwen2.5-14B) | [🤗 HuggingFace](https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-14B) |
107
+ |DeepSeek-R1-Distill-Qwen-32B | [Qwen2.5-32B](https://huggingface.co/Qwen/Qwen2.5-32B) | [🤗 HuggingFace](https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-32B) |
108
+ | DeepSeek-R1-Distill-Llama-70B | [Llama-3.3-70B-Instruct](https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct) | [🤗 HuggingFace](https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Llama-70B) |
109
+
110
+ </div>
111
+
112
+ DeepSeek-R1-Distill models are fine-tuned based on open-source models, using samples generated by DeepSeek-R1.
113
+ We slightly change their configs and tokenizers. Please use our setting to run these models.
114
+
115
+ ## 4. Evaluation Results
116
+
117
+ ### DeepSeek-R1-Evaluation
118
+ For all our models, the maximum generation length is set to 32,768 tokens. For benchmarks requiring sampling, we use a temperature of $0.6$, a top-p value of $0.95$, and generate 64 responses per query to estimate pass@1.
119
+ <div align="center">
120
+
121
+
122
+ | Category | Benchmark (Metric) | Claude-3.5-Sonnet-1022 | GPT-4o 0513 | DeepSeek V3 | OpenAI o1-mini | OpenAI o1-1217 | DeepSeek R1 |
123
+ |----------|-------------------|----------------------|------------|--------------|----------------|------------|--------------|
124
+ | | Architecture | - | - | MoE | - | - | MoE |
125
+ | | # Activated Params | - | - | 37B | - | - | 37B |
126
+ | | # Total Params | - | - | 671B | - | - | 671B |
127
+ | English | MMLU (Pass@1) | 88.3 | 87.2 | 88.5 | 85.2 | **91.8** | 90.8 |
128
+ | | MMLU-Redux (EM) | 88.9 | 88.0 | 89.1 | 86.7 | - | **92.9** |
129
+ | | MMLU-Pro (EM) | 78.0 | 72.6 | 75.9 | 80.3 | - | **84.0** |
130
+ | | DROP (3-shot F1) | 88.3 | 83.7 | 91.6 | 83.9 | 90.2 | **92.2** |
131
+ | | IF-Eval (Prompt Strict) | **86.5** | 84.3 | 86.1 | 84.8 | - | 83.3 |
132
+ | | GPQA-Diamond (Pass@1) | 65.0 | 49.9 | 59.1 | 60.0 | **75.7** | 71.5 |
133
+ | | SimpleQA (Correct) | 28.4 | 38.2 | 24.9 | 7.0 | **47.0** | 30.1 |
134
+ | | FRAMES (Acc.) | 72.5 | 80.5 | 73.3 | 76.9 | - | **82.5** |
135
+ | | AlpacaEval2.0 (LC-winrate) | 52.0 | 51.1 | 70.0 | 57.8 | - | **87.6** |
136
+ | | ArenaHard (GPT-4-1106) | 85.2 | 80.4 | 85.5 | 92.0 | - | **92.3** |
137
+ | Code | LiveCodeBench (Pass@1-COT) | 33.8 | 34.2 | - | 53.8 | 63.4 | **65.9** |
138
+ | | Codeforces (Percentile) | 20.3 | 23.6 | 58.7 | 93.4 | **96.6** | 96.3 |
139
+ | | Codeforces (Rating) | 717 | 759 | 1134 | 1820 | **2061** | 2029 |
140
+ | | SWE Verified (Resolved) | **50.8** | 38.8 | 42.0 | 41.6 | 48.9 | 49.2 |
141
+ | | Aider-Polyglot (Acc.) | 45.3 | 16.0 | 49.6 | 32.9 | **61.7** | 53.3 |
142
+ | Math | AIME 2024 (Pass@1) | 16.0 | 9.3 | 39.2 | 63.6 | 79.2 | **79.8** |
143
+ | | MATH-500 (Pass@1) | 78.3 | 74.6 | 90.2 | 90.0 | 96.4 | **97.3** |
144
+ | | CNMO 2024 (Pass@1) | 13.1 | 10.8 | 43.2 | 67.6 | - | **78.8** |
145
+ | Chinese | CLUEWSC (EM) | 85.4 | 87.9 | 90.9 | 89.9 | - | **92.8** |
146
+ | | C-Eval (EM) | 76.7 | 76.0 | 86.5 | 68.9 | - | **91.8** |
147
+ | | C-SimpleQA (Correct) | 55.4 | 58.7 | **68.0** | 40.3 | - | 63.7 |
148
+
149
+ </div>
150
+
151
+
152
+ ### Distilled Model Evaluation
153
+
154
+
155
+ <div align="center">
156
+
157
+ | Model | AIME 2024 pass@1 | AIME 2024 cons@64 | MATH-500 pass@1 | GPQA Diamond pass@1 | LiveCodeBench pass@1 | CodeForces rating |
158
+ |------------------------------------------|------------------|-------------------|-----------------|----------------------|----------------------|-------------------|
159
+ | GPT-4o-0513 | 9.3 | 13.4 | 74.6 | 49.9 | 32.9 | 759 |
160
+ | Claude-3.5-Sonnet-1022 | 16.0 | 26.7 | 78.3 | 65.0 | 38.9 | 717 |
161
+ | o1-mini | 63.6 | 80.0 | 90.0 | 60.0 | 53.8 | **1820** |
162
+ | QwQ-32B-Preview | 44.0 | 60.0 | 90.6 | 54.5 | 41.9 | 1316 |
163
+ | DeepSeek-R1-Distill-Qwen-1.5B | 28.9 | 52.7 | 83.9 | 33.8 | 16.9 | 954 |
164
+ | DeepSeek-R1-Distill-Qwen-7B | 55.5 | 83.3 | 92.8 | 49.1 | 37.6 | 1189 |
165
+ | DeepSeek-R1-Distill-Qwen-14B | 69.7 | 80.0 | 93.9 | 59.1 | 53.1 | 1481 |
166
+ | DeepSeek-R1-Distill-Qwen-32B | **72.6** | 83.3 | 94.3 | 62.1 | 57.2 | 1691 |
167
+ | DeepSeek-R1-Distill-Llama-8B | 50.4 | 80.0 | 89.1 | 49.0 | 39.6 | 1205 |
168
+ | DeepSeek-R1-Distill-Llama-70B | 70.0 | **86.7** | **94.5** | **65.2** | **57.5** | 1633 |
169
+
170
+ </div>
171
+
172
+
173
+ ## 5. Chat Website & API Platform
174
+ You can chat with DeepSeek-R1 on DeepSeek's official website: [chat.deepseek.com](https://chat.deepseek.com), and switch on the button "DeepThink"
175
+
176
+ We also provide OpenAI-Compatible API at DeepSeek Platform: [platform.deepseek.com](https://platform.deepseek.com/)
177
+
178
+ ## 6. How to Run Locally
179
+
180
+ ### DeepSeek-R1 Models
181
+
182
+ Please visit [DeepSeek-V3](https://github.com/deepseek-ai/DeepSeek-V3) repo for more information about running DeepSeek-R1 locally.
183
+
184
+ ### DeepSeek-R1-Distill Models
185
+
186
+ DeepSeek-R1-Distill models can be utilized in the same manner as Qwen or Llama models.
187
+
188
+ For instance, you can easily start a service using [vLLM](https://github.com/vllm-project/vllm):
189
+
190
+ ```shell
191
+ vllm serve deepseek-ai/DeepSeek-R1-Distill-Qwen-32B --tensor-parallel-size 2 --max-model-len 32768 --enforce-eager
192
+ ```
193
+
194
+ **NOTE: We recommend setting an appropriate temperature (between 0.5 and 0.7) when running these models, otherwise you may encounter issues with endless repetition or incoherent output.**
195
+
196
+ ## 7. License
197
+ This code repository and the model weights are licensed under the [MIT License](https://github.com/deepseek-ai/DeepSeek-R1/blob/main/LICENSE).
198
+ DeepSeek-R1 series support commercial use, allow for any modifications and derivative works, including, but not limited to, distillation for training other LLMs. Please note that:
199
+ - DeepSeek-R1-Distill-Qwen-1.5B, DeepSeek-R1-Distill-Qwen-7B, DeepSeek-R1-Distill-Qwen-14B and DeepSeek-R1-Distill-Qwen-32B are derived from [Qwen-2.5 series](https://github.com/QwenLM/Qwen2.5), which are originally licensed under [Apache 2.0 License](https://huggingface.co/Qwen/Qwen2.5-1.5B/blob/main/LICENSE), and now finetuned with 800k samples curated with DeepSeek-R1.
200
+ - DeepSeek-R1-Distill-Llama-8B is derived from Llama3.1-8B-Base and is originally licensed under [llama3.1 license](https://huggingface.co/meta-llama/Llama-3.1-8B/blob/main/LICENSE).
201
+ - DeepSeek-R1-Distill-Llama-70B is derived from Llama3.3-70B-Instruct and is originally licensed under [llama3.3 license](https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct/blob/main/LICENSE).
202
+
203
+ ## 8. Citation
204
+ ```
205
+
206
+ ```
207
+
208
+ ## 9. Contact
209
+ If you have any questions, please raise an issue or contact us at [[email protected]]([email protected]).
config.json ADDED
@@ -0,0 +1,50 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "LlamaForCausalLM"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 128000,
8
+ "eos_token_id": [
9
+ 128001,
10
+ 128008,
11
+ 128009
12
+ ],
13
+ "head_dim": 128,
14
+ "hidden_act": "silu",
15
+ "hidden_size": 8192,
16
+ "initializer_range": 0.02,
17
+ "intermediate_size": 28672,
18
+ "max_position_embeddings": 131072,
19
+ "mlp_bias": false,
20
+ "model_type": "llama",
21
+ "num_attention_heads": 64,
22
+ "num_hidden_layers": 80,
23
+ "num_key_value_heads": 8,
24
+ "pretraining_tp": 1,
25
+ "rms_norm_eps": 1e-05,
26
+ "rope_scaling": {
27
+ "factor": 8.0,
28
+ "high_freq_factor": 4.0,
29
+ "low_freq_factor": 1.0,
30
+ "original_max_position_embeddings": 8192,
31
+ "rope_type": "llama3"
32
+ },
33
+ "rope_theta": 500000.0,
34
+ "tie_word_embeddings": false,
35
+ "torch_dtype": "bfloat16",
36
+ "transformers_version": "4.47.0.dev0",
37
+ "use_cache": true,
38
+ "vocab_size": 128256,
39
+ "quantization_config": {
40
+ "quant_method": "exl2",
41
+ "version": "0.2.7",
42
+ "bits": 8.0,
43
+ "head_bits": 8,
44
+ "calibration": {
45
+ "rows": 115,
46
+ "length": 2048,
47
+ "dataset": "(default)"
48
+ }
49
+ }
50
+ }
huggingface-metadata.txt ADDED
@@ -0,0 +1,21 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ url: https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Llama-70B
2
+ branch: main
3
+ download date: 2025-01-20 16:35:02
4
+ sha256sum:
5
+ 4f57a2538539d61f9f22785d3c48f089227829948ee66572808dd13d5b08d63e model-00001-of-000017.safetensors
6
+ 3f948c2df3e4f3e678e1b4c75b345ce646c4843a23e7c9089462cf3995d2af45 model-00002-of-000017.safetensors
7
+ aa4b0afa70d26873dabc927e59b7dbc24a0e8eda323d4fdba17927d316d3516c model-00003-of-000017.safetensors
8
+ 077f51bc9eb56b50868cb95c7cf0d6d0f0a524b824ba3af8b248c78a46593e97 model-00004-of-000017.safetensors
9
+ e826381017b2d8a9d8704be34ee0e0ceeb0a3a9abca27beaa4555d370d5a4f10 model-00005-of-000017.safetensors
10
+ b1d4326d0d4187830fcea956d8ccfafbf6871fa7baed1b759c1ed843cafe92c0 model-00006-of-000017.safetensors
11
+ 62a83ba7af95d532065e46322ae2c17ee020c3c8e92b7285420c09ca0d6f68f0 model-00007-of-000017.safetensors
12
+ 8189753d14d5f9b3c31466d1f5a185bb7ffc7fc346cbc06a5453e48e07c2b97b model-00008-of-000017.safetensors
13
+ 928bea3ae97c3962b3eb3f51a66f674be4cd5858caae541becd3e175f3305403 model-00009-of-000017.safetensors
14
+ 1db6d4f8387897b0f40e505310a1542f6d0308370526fa86c42cdc99451d2200 model-00010-of-000017.safetensors
15
+ 31a5eb90d0773f1514ae7b240ed62961412e48f9eb160fdac6226221b87fe61f model-00011-of-000017.safetensors
16
+ d01c2823a0393ded7f97556995b69965dad78665664853f1c8a2be901e643a44 model-00012-of-000017.safetensors
17
+ 3c43532c1b128f0135edc587ace540dfa53759916836960db06b73ab718e5eca model-00013-of-000017.safetensors
18
+ 0f2ce0194b017ae009448602d7fd4ac24d7f25059c0a87d42fc496000f7bdacc model-00014-of-000017.safetensors
19
+ 572ed974eb237aacf3de9ddfeaa373c62d39038a96ffd7f2beec6ea8f8a7b16e model-00015-of-000017.safetensors
20
+ e5a581377b62f0a918bf515d05f2514281eec031ea2748e7ce8123b910403bba model-00016-of-000017.safetensors
21
+ 605b29e86ec80aaa3a38bb3aab4bc859e4df26928fe49bbca00f127f55897e8d model-00017-of-000017.safetensors
measurement.json ADDED
The diff for this file is too large to render. See raw diff
 
model.safetensors.index.json ADDED
@@ -0,0 +1,730 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 141107412992
4
+ },
5
+ "weight_map": {
6
+ "model.embed_tokens.weight": "model-00001-of-000017.safetensors",
7
+ "model.layers.0.self_attn.q_proj.weight": "model-00001-of-000017.safetensors",
8
+ "model.layers.0.self_attn.k_proj.weight": "model-00001-of-000017.safetensors",
9
+ "model.layers.0.self_attn.v_proj.weight": "model-00001-of-000017.safetensors",
10
+ "model.layers.0.self_attn.o_proj.weight": "model-00001-of-000017.safetensors",
11
+ "model.layers.0.mlp.gate_proj.weight": "model-00001-of-000017.safetensors",
12
+ "model.layers.0.mlp.up_proj.weight": "model-00001-of-000017.safetensors",
13
+ "model.layers.0.mlp.down_proj.weight": "model-00001-of-000017.safetensors",
14
+ "model.layers.0.input_layernorm.weight": "model-00001-of-000017.safetensors",
15
+ "model.layers.0.post_attention_layernorm.weight": "model-00001-of-000017.safetensors",
16
+ "model.layers.1.self_attn.q_proj.weight": "model-00001-of-000017.safetensors",
17
+ "model.layers.1.self_attn.k_proj.weight": "model-00001-of-000017.safetensors",
18
+ "model.layers.1.self_attn.v_proj.weight": "model-00001-of-000017.safetensors",
19
+ "model.layers.1.self_attn.o_proj.weight": "model-00001-of-000017.safetensors",
20
+ "model.layers.1.mlp.gate_proj.weight": "model-00001-of-000017.safetensors",
21
+ "model.layers.1.mlp.up_proj.weight": "model-00001-of-000017.safetensors",
22
+ "model.layers.1.mlp.down_proj.weight": "model-00001-of-000017.safetensors",
23
+ "model.layers.1.input_layernorm.weight": "model-00001-of-000017.safetensors",
24
+ "model.layers.1.post_attention_layernorm.weight": "model-00001-of-000017.safetensors",
25
+ "model.layers.2.self_attn.q_proj.weight": "model-00001-of-000017.safetensors",
26
+ "model.layers.2.self_attn.k_proj.weight": "model-00001-of-000017.safetensors",
27
+ "model.layers.2.self_attn.v_proj.weight": "model-00001-of-000017.safetensors",
28
+ "model.layers.2.self_attn.o_proj.weight": "model-00001-of-000017.safetensors",
29
+ "model.layers.2.mlp.gate_proj.weight": "model-00001-of-000017.safetensors",
30
+ "model.layers.2.mlp.up_proj.weight": "model-00001-of-000017.safetensors",
31
+ "model.layers.2.mlp.down_proj.weight": "model-00001-of-000017.safetensors",
32
+ "model.layers.2.input_layernorm.weight": "model-00001-of-000017.safetensors",
33
+ "model.layers.2.post_attention_layernorm.weight": "model-00001-of-000017.safetensors",
34
+ "model.layers.3.self_attn.q_proj.weight": "model-00001-of-000017.safetensors",
35
+ "model.layers.3.self_attn.k_proj.weight": "model-00001-of-000017.safetensors",
36
+ "model.layers.3.self_attn.v_proj.weight": "model-00001-of-000017.safetensors",
37
+ "model.layers.3.self_attn.o_proj.weight": "model-00001-of-000017.safetensors",
38
+ "model.layers.3.mlp.gate_proj.weight": "model-00001-of-000017.safetensors",
39
+ "model.layers.3.mlp.up_proj.weight": "model-00001-of-000017.safetensors",
40
+ "model.layers.3.mlp.down_proj.weight": "model-00001-of-000017.safetensors",
41
+ "model.layers.3.input_layernorm.weight": "model-00002-of-000017.safetensors",
42
+ "model.layers.3.post_attention_layernorm.weight": "model-00002-of-000017.safetensors",
43
+ "model.layers.4.self_attn.q_proj.weight": "model-00002-of-000017.safetensors",
44
+ "model.layers.4.self_attn.k_proj.weight": "model-00002-of-000017.safetensors",
45
+ "model.layers.4.self_attn.v_proj.weight": "model-00002-of-000017.safetensors",
46
+ "model.layers.4.self_attn.o_proj.weight": "model-00002-of-000017.safetensors",
47
+ "model.layers.4.mlp.gate_proj.weight": "model-00002-of-000017.safetensors",
48
+ "model.layers.4.mlp.up_proj.weight": "model-00002-of-000017.safetensors",
49
+ "model.layers.4.mlp.down_proj.weight": "model-00002-of-000017.safetensors",
50
+ "model.layers.4.input_layernorm.weight": "model-00002-of-000017.safetensors",
51
+ "model.layers.4.post_attention_layernorm.weight": "model-00002-of-000017.safetensors",
52
+ "model.layers.5.self_attn.q_proj.weight": "model-00002-of-000017.safetensors",
53
+ "model.layers.5.self_attn.k_proj.weight": "model-00002-of-000017.safetensors",
54
+ "model.layers.5.self_attn.v_proj.weight": "model-00002-of-000017.safetensors",
55
+ "model.layers.5.self_attn.o_proj.weight": "model-00002-of-000017.safetensors",
56
+ "model.layers.5.mlp.gate_proj.weight": "model-00002-of-000017.safetensors",
57
+ "model.layers.5.mlp.up_proj.weight": "model-00002-of-000017.safetensors",
58
+ "model.layers.5.mlp.down_proj.weight": "model-00002-of-000017.safetensors",
59
+ "model.layers.5.input_layernorm.weight": "model-00002-of-000017.safetensors",
60
+ "model.layers.5.post_attention_layernorm.weight": "model-00002-of-000017.safetensors",
61
+ "model.layers.6.self_attn.q_proj.weight": "model-00002-of-000017.safetensors",
62
+ "model.layers.6.self_attn.k_proj.weight": "model-00002-of-000017.safetensors",
63
+ "model.layers.6.self_attn.v_proj.weight": "model-00002-of-000017.safetensors",
64
+ "model.layers.6.self_attn.o_proj.weight": "model-00002-of-000017.safetensors",
65
+ "model.layers.6.mlp.gate_proj.weight": "model-00002-of-000017.safetensors",
66
+ "model.layers.6.mlp.up_proj.weight": "model-00002-of-000017.safetensors",
67
+ "model.layers.6.mlp.down_proj.weight": "model-00002-of-000017.safetensors",
68
+ "model.layers.6.input_layernorm.weight": "model-00002-of-000017.safetensors",
69
+ "model.layers.6.post_attention_layernorm.weight": "model-00002-of-000017.safetensors",
70
+ "model.layers.7.self_attn.q_proj.weight": "model-00002-of-000017.safetensors",
71
+ "model.layers.7.self_attn.k_proj.weight": "model-00002-of-000017.safetensors",
72
+ "model.layers.7.self_attn.v_proj.weight": "model-00002-of-000017.safetensors",
73
+ "model.layers.7.self_attn.o_proj.weight": "model-00002-of-000017.safetensors",
74
+ "model.layers.7.mlp.gate_proj.weight": "model-00002-of-000017.safetensors",
75
+ "model.layers.7.mlp.up_proj.weight": "model-00002-of-000017.safetensors",
76
+ "model.layers.7.mlp.down_proj.weight": "model-00002-of-000017.safetensors",
77
+ "model.layers.7.input_layernorm.weight": "model-00002-of-000017.safetensors",
78
+ "model.layers.7.post_attention_layernorm.weight": "model-00002-of-000017.safetensors",
79
+ "model.layers.8.self_attn.q_proj.weight": "model-00002-of-000017.safetensors",
80
+ "model.layers.8.self_attn.k_proj.weight": "model-00002-of-000017.safetensors",
81
+ "model.layers.8.self_attn.v_proj.weight": "model-00002-of-000017.safetensors",
82
+ "model.layers.8.self_attn.o_proj.weight": "model-00002-of-000017.safetensors",
83
+ "model.layers.8.mlp.gate_proj.weight": "model-00002-of-000017.safetensors",
84
+ "model.layers.8.mlp.up_proj.weight": "model-00002-of-000017.safetensors",
85
+ "model.layers.8.mlp.down_proj.weight": "model-00002-of-000017.safetensors",
86
+ "model.layers.8.input_layernorm.weight": "model-00002-of-000017.safetensors",
87
+ "model.layers.8.post_attention_layernorm.weight": "model-00002-of-000017.safetensors",
88
+ "model.layers.9.self_attn.q_proj.weight": "model-00002-of-000017.safetensors",
89
+ "model.layers.9.self_attn.k_proj.weight": "model-00003-of-000017.safetensors",
90
+ "model.layers.9.self_attn.v_proj.weight": "model-00003-of-000017.safetensors",
91
+ "model.layers.9.self_attn.o_proj.weight": "model-00003-of-000017.safetensors",
92
+ "model.layers.9.mlp.gate_proj.weight": "model-00003-of-000017.safetensors",
93
+ "model.layers.9.mlp.up_proj.weight": "model-00003-of-000017.safetensors",
94
+ "model.layers.9.mlp.down_proj.weight": "model-00003-of-000017.safetensors",
95
+ "model.layers.9.input_layernorm.weight": "model-00003-of-000017.safetensors",
96
+ "model.layers.9.post_attention_layernorm.weight": "model-00003-of-000017.safetensors",
97
+ "model.layers.10.self_attn.q_proj.weight": "model-00004-of-000017.safetensors",
98
+ "model.layers.10.self_attn.k_proj.weight": "model-00004-of-000017.safetensors",
99
+ "model.layers.10.self_attn.v_proj.weight": "model-00004-of-000017.safetensors",
100
+ "model.layers.10.self_attn.o_proj.weight": "model-00004-of-000017.safetensors",
101
+ "model.layers.10.mlp.gate_proj.weight": "model-00004-of-000017.safetensors",
102
+ "model.layers.10.mlp.up_proj.weight": "model-00004-of-000017.safetensors",
103
+ "model.layers.10.mlp.down_proj.weight": "model-00004-of-000017.safetensors",
104
+ "model.layers.10.input_layernorm.weight": "model-00004-of-000017.safetensors",
105
+ "model.layers.10.post_attention_layernorm.weight": "model-00004-of-000017.safetensors",
106
+ "model.layers.11.self_attn.q_proj.weight": "model-00004-of-000017.safetensors",
107
+ "model.layers.11.self_attn.k_proj.weight": "model-00004-of-000017.safetensors",
108
+ "model.layers.11.self_attn.v_proj.weight": "model-00004-of-000017.safetensors",
109
+ "model.layers.11.self_attn.o_proj.weight": "model-00004-of-000017.safetensors",
110
+ "model.layers.11.mlp.gate_proj.weight": "model-00004-of-000017.safetensors",
111
+ "model.layers.11.mlp.up_proj.weight": "model-00004-of-000017.safetensors",
112
+ "model.layers.11.mlp.down_proj.weight": "model-00004-of-000017.safetensors",
113
+ "model.layers.11.input_layernorm.weight": "model-00004-of-000017.safetensors",
114
+ "model.layers.11.post_attention_layernorm.weight": "model-00004-of-000017.safetensors",
115
+ "model.layers.12.self_attn.q_proj.weight": "model-00004-of-000017.safetensors",
116
+ "model.layers.12.self_attn.k_proj.weight": "model-00004-of-000017.safetensors",
117
+ "model.layers.12.self_attn.v_proj.weight": "model-00004-of-000017.safetensors",
118
+ "model.layers.12.self_attn.o_proj.weight": "model-00004-of-000017.safetensors",
119
+ "model.layers.12.mlp.gate_proj.weight": "model-00004-of-000017.safetensors",
120
+ "model.layers.12.mlp.up_proj.weight": "model-00004-of-000017.safetensors",
121
+ "model.layers.12.mlp.down_proj.weight": "model-00004-of-000017.safetensors",
122
+ "model.layers.12.input_layernorm.weight": "model-00004-of-000017.safetensors",
123
+ "model.layers.12.post_attention_layernorm.weight": "model-00004-of-000017.safetensors",
124
+ "model.layers.13.self_attn.q_proj.weight": "model-00004-of-000017.safetensors",
125
+ "model.layers.13.self_attn.k_proj.weight": "model-00004-of-000017.safetensors",
126
+ "model.layers.13.self_attn.v_proj.weight": "model-00004-of-000017.safetensors",
127
+ "model.layers.13.self_attn.o_proj.weight": "model-00004-of-000017.safetensors",
128
+ "model.layers.13.mlp.gate_proj.weight": "model-00004-of-000017.safetensors",
129
+ "model.layers.13.mlp.up_proj.weight": "model-00004-of-000017.safetensors",
130
+ "model.layers.13.mlp.down_proj.weight": "model-00004-of-000017.safetensors",
131
+ "model.layers.13.input_layernorm.weight": "model-00004-of-000017.safetensors",
132
+ "model.layers.13.post_attention_layernorm.weight": "model-00004-of-000017.safetensors",
133
+ "model.layers.14.self_attn.q_proj.weight": "model-00004-of-000017.safetensors",
134
+ "model.layers.14.self_attn.k_proj.weight": "model-00004-of-000017.safetensors",
135
+ "model.layers.14.self_attn.v_proj.weight": "model-00004-of-000017.safetensors",
136
+ "model.layers.14.self_attn.o_proj.weight": "model-00004-of-000017.safetensors",
137
+ "model.layers.14.mlp.gate_proj.weight": "model-00004-of-000017.safetensors",
138
+ "model.layers.14.mlp.up_proj.weight": "model-00004-of-000017.safetensors",
139
+ "model.layers.14.mlp.down_proj.weight": "model-00004-of-000017.safetensors",
140
+ "model.layers.14.input_layernorm.weight": "model-00004-of-000017.safetensors",
141
+ "model.layers.14.post_attention_layernorm.weight": "model-00004-of-000017.safetensors",
142
+ "model.layers.15.self_attn.q_proj.weight": "model-00004-of-000017.safetensors",
143
+ "model.layers.15.self_attn.k_proj.weight": "model-00005-of-000017.safetensors",
144
+ "model.layers.15.self_attn.v_proj.weight": "model-00005-of-000017.safetensors",
145
+ "model.layers.15.self_attn.o_proj.weight": "model-00005-of-000017.safetensors",
146
+ "model.layers.15.mlp.gate_proj.weight": "model-00005-of-000017.safetensors",
147
+ "model.layers.15.mlp.up_proj.weight": "model-00005-of-000017.safetensors",
148
+ "model.layers.15.mlp.down_proj.weight": "model-00005-of-000017.safetensors",
149
+ "model.layers.15.input_layernorm.weight": "model-00005-of-000017.safetensors",
150
+ "model.layers.15.post_attention_layernorm.weight": "model-00005-of-000017.safetensors",
151
+ "model.layers.16.self_attn.q_proj.weight": "model-00005-of-000017.safetensors",
152
+ "model.layers.16.self_attn.k_proj.weight": "model-00005-of-000017.safetensors",
153
+ "model.layers.16.self_attn.v_proj.weight": "model-00005-of-000017.safetensors",
154
+ "model.layers.16.self_attn.o_proj.weight": "model-00005-of-000017.safetensors",
155
+ "model.layers.16.mlp.gate_proj.weight": "model-00005-of-000017.safetensors",
156
+ "model.layers.16.mlp.up_proj.weight": "model-00005-of-000017.safetensors",
157
+ "model.layers.16.mlp.down_proj.weight": "model-00005-of-000017.safetensors",
158
+ "model.layers.16.input_layernorm.weight": "model-00005-of-000017.safetensors",
159
+ "model.layers.16.post_attention_layernorm.weight": "model-00005-of-000017.safetensors",
160
+ "model.layers.17.self_attn.q_proj.weight": "model-00005-of-000017.safetensors",
161
+ "model.layers.17.self_attn.k_proj.weight": "model-00005-of-000017.safetensors",
162
+ "model.layers.17.self_attn.v_proj.weight": "model-00005-of-000017.safetensors",
163
+ "model.layers.17.self_attn.o_proj.weight": "model-00005-of-000017.safetensors",
164
+ "model.layers.17.mlp.gate_proj.weight": "model-00005-of-000017.safetensors",
165
+ "model.layers.17.mlp.up_proj.weight": "model-00005-of-000017.safetensors",
166
+ "model.layers.17.mlp.down_proj.weight": "model-00005-of-000017.safetensors",
167
+ "model.layers.17.input_layernorm.weight": "model-00005-of-000017.safetensors",
168
+ "model.layers.17.post_attention_layernorm.weight": "model-00005-of-000017.safetensors",
169
+ "model.layers.18.self_attn.q_proj.weight": "model-00005-of-000017.safetensors",
170
+ "model.layers.18.self_attn.k_proj.weight": "model-00005-of-000017.safetensors",
171
+ "model.layers.18.self_attn.v_proj.weight": "model-00005-of-000017.safetensors",
172
+ "model.layers.18.self_attn.o_proj.weight": "model-00005-of-000017.safetensors",
173
+ "model.layers.18.mlp.gate_proj.weight": "model-00005-of-000017.safetensors",
174
+ "model.layers.18.mlp.up_proj.weight": "model-00005-of-000017.safetensors",
175
+ "model.layers.18.mlp.down_proj.weight": "model-00005-of-000017.safetensors",
176
+ "model.layers.18.input_layernorm.weight": "model-00005-of-000017.safetensors",
177
+ "model.layers.18.post_attention_layernorm.weight": "model-00005-of-000017.safetensors",
178
+ "model.layers.19.self_attn.q_proj.weight": "model-00005-of-000017.safetensors",
179
+ "model.layers.19.self_attn.k_proj.weight": "model-00005-of-000017.safetensors",
180
+ "model.layers.19.self_attn.v_proj.weight": "model-00005-of-000017.safetensors",
181
+ "model.layers.19.self_attn.o_proj.weight": "model-00005-of-000017.safetensors",
182
+ "model.layers.19.mlp.gate_proj.weight": "model-00005-of-000017.safetensors",
183
+ "model.layers.19.mlp.up_proj.weight": "model-00005-of-000017.safetensors",
184
+ "model.layers.19.mlp.down_proj.weight": "model-00005-of-000017.safetensors",
185
+ "model.layers.19.input_layernorm.weight": "model-00005-of-000017.safetensors",
186
+ "model.layers.19.post_attention_layernorm.weight": "model-00005-of-000017.safetensors",
187
+ "model.layers.20.self_attn.q_proj.weight": "model-00006-of-000017.safetensors",
188
+ "model.layers.20.self_attn.k_proj.weight": "model-00006-of-000017.safetensors",
189
+ "model.layers.20.self_attn.v_proj.weight": "model-00006-of-000017.safetensors",
190
+ "model.layers.20.self_attn.o_proj.weight": "model-00006-of-000017.safetensors",
191
+ "model.layers.20.mlp.gate_proj.weight": "model-00006-of-000017.safetensors",
192
+ "model.layers.20.mlp.up_proj.weight": "model-00006-of-000017.safetensors",
193
+ "model.layers.20.mlp.down_proj.weight": "model-00006-of-000017.safetensors",
194
+ "model.layers.20.input_layernorm.weight": "model-00006-of-000017.safetensors",
195
+ "model.layers.20.post_attention_layernorm.weight": "model-00006-of-000017.safetensors",
196
+ "model.layers.21.self_attn.q_proj.weight": "model-00006-of-000017.safetensors",
197
+ "model.layers.21.self_attn.k_proj.weight": "model-00006-of-000017.safetensors",
198
+ "model.layers.21.self_attn.v_proj.weight": "model-00006-of-000017.safetensors",
199
+ "model.layers.21.self_attn.o_proj.weight": "model-00006-of-000017.safetensors",
200
+ "model.layers.21.mlp.gate_proj.weight": "model-00006-of-000017.safetensors",
201
+ "model.layers.21.mlp.up_proj.weight": "model-00006-of-000017.safetensors",
202
+ "model.layers.21.mlp.down_proj.weight": "model-00006-of-000017.safetensors",
203
+ "model.layers.21.input_layernorm.weight": "model-00006-of-000017.safetensors",
204
+ "model.layers.21.post_attention_layernorm.weight": "model-00006-of-000017.safetensors",
205
+ "model.layers.22.self_attn.q_proj.weight": "model-00006-of-000017.safetensors",
206
+ "model.layers.22.self_attn.k_proj.weight": "model-00006-of-000017.safetensors",
207
+ "model.layers.22.self_attn.v_proj.weight": "model-00006-of-000017.safetensors",
208
+ "model.layers.22.self_attn.o_proj.weight": "model-00006-of-000017.safetensors",
209
+ "model.layers.22.mlp.gate_proj.weight": "model-00006-of-000017.safetensors",
210
+ "model.layers.22.mlp.up_proj.weight": "model-00006-of-000017.safetensors",
211
+ "model.layers.22.mlp.down_proj.weight": "model-00006-of-000017.safetensors",
212
+ "model.layers.22.input_layernorm.weight": "model-00006-of-000017.safetensors",
213
+ "model.layers.22.post_attention_layernorm.weight": "model-00006-of-000017.safetensors",
214
+ "model.layers.23.self_attn.q_proj.weight": "model-00006-of-000017.safetensors",
215
+ "model.layers.23.self_attn.k_proj.weight": "model-00006-of-000017.safetensors",
216
+ "model.layers.23.self_attn.v_proj.weight": "model-00006-of-000017.safetensors",
217
+ "model.layers.23.self_attn.o_proj.weight": "model-00006-of-000017.safetensors",
218
+ "model.layers.23.mlp.gate_proj.weight": "model-00006-of-000017.safetensors",
219
+ "model.layers.23.mlp.up_proj.weight": "model-00006-of-000017.safetensors",
220
+ "model.layers.23.mlp.down_proj.weight": "model-00006-of-000017.safetensors",
221
+ "model.layers.23.input_layernorm.weight": "model-00006-of-000017.safetensors",
222
+ "model.layers.23.post_attention_layernorm.weight": "model-00006-of-000017.safetensors",
223
+ "model.layers.24.self_attn.q_proj.weight": "model-00006-of-000017.safetensors",
224
+ "model.layers.24.self_attn.k_proj.weight": "model-00006-of-000017.safetensors",
225
+ "model.layers.24.self_attn.v_proj.weight": "model-00006-of-000017.safetensors",
226
+ "model.layers.24.self_attn.o_proj.weight": "model-00006-of-000017.safetensors",
227
+ "model.layers.24.mlp.gate_proj.weight": "model-00006-of-000017.safetensors",
228
+ "model.layers.24.mlp.up_proj.weight": "model-00006-of-000017.safetensors",
229
+ "model.layers.24.mlp.down_proj.weight": "model-00006-of-000017.safetensors",
230
+ "model.layers.24.input_layernorm.weight": "model-00006-of-000017.safetensors",
231
+ "model.layers.24.post_attention_layernorm.weight": "model-00006-of-000017.safetensors",
232
+ "model.layers.25.self_attn.q_proj.weight": "model-00006-of-000017.safetensors",
233
+ "model.layers.25.self_attn.k_proj.weight": "model-00007-of-000017.safetensors",
234
+ "model.layers.25.self_attn.v_proj.weight": "model-00007-of-000017.safetensors",
235
+ "model.layers.25.self_attn.o_proj.weight": "model-00007-of-000017.safetensors",
236
+ "model.layers.25.mlp.gate_proj.weight": "model-00007-of-000017.safetensors",
237
+ "model.layers.25.mlp.up_proj.weight": "model-00007-of-000017.safetensors",
238
+ "model.layers.25.mlp.down_proj.weight": "model-00007-of-000017.safetensors",
239
+ "model.layers.25.input_layernorm.weight": "model-00007-of-000017.safetensors",
240
+ "model.layers.25.post_attention_layernorm.weight": "model-00007-of-000017.safetensors",
241
+ "model.layers.26.self_attn.q_proj.weight": "model-00007-of-000017.safetensors",
242
+ "model.layers.26.self_attn.k_proj.weight": "model-00007-of-000017.safetensors",
243
+ "model.layers.26.self_attn.v_proj.weight": "model-00007-of-000017.safetensors",
244
+ "model.layers.26.self_attn.o_proj.weight": "model-00007-of-000017.safetensors",
245
+ "model.layers.26.mlp.gate_proj.weight": "model-00007-of-000017.safetensors",
246
+ "model.layers.26.mlp.up_proj.weight": "model-00007-of-000017.safetensors",
247
+ "model.layers.26.mlp.down_proj.weight": "model-00007-of-000017.safetensors",
248
+ "model.layers.26.input_layernorm.weight": "model-00007-of-000017.safetensors",
249
+ "model.layers.26.post_attention_layernorm.weight": "model-00007-of-000017.safetensors",
250
+ "model.layers.27.self_attn.q_proj.weight": "model-00007-of-000017.safetensors",
251
+ "model.layers.27.self_attn.k_proj.weight": "model-00007-of-000017.safetensors",
252
+ "model.layers.27.self_attn.v_proj.weight": "model-00007-of-000017.safetensors",
253
+ "model.layers.27.self_attn.o_proj.weight": "model-00007-of-000017.safetensors",
254
+ "model.layers.27.mlp.gate_proj.weight": "model-00007-of-000017.safetensors",
255
+ "model.layers.27.mlp.up_proj.weight": "model-00007-of-000017.safetensors",
256
+ "model.layers.27.mlp.down_proj.weight": "model-00007-of-000017.safetensors",
257
+ "model.layers.27.input_layernorm.weight": "model-00007-of-000017.safetensors",
258
+ "model.layers.27.post_attention_layernorm.weight": "model-00007-of-000017.safetensors",
259
+ "model.layers.28.self_attn.q_proj.weight": "model-00007-of-000017.safetensors",
260
+ "model.layers.28.self_attn.k_proj.weight": "model-00007-of-000017.safetensors",
261
+ "model.layers.28.self_attn.v_proj.weight": "model-00007-of-000017.safetensors",
262
+ "model.layers.28.self_attn.o_proj.weight": "model-00007-of-000017.safetensors",
263
+ "model.layers.28.mlp.gate_proj.weight": "model-00007-of-000017.safetensors",
264
+ "model.layers.28.mlp.up_proj.weight": "model-00007-of-000017.safetensors",
265
+ "model.layers.28.mlp.down_proj.weight": "model-00007-of-000017.safetensors",
266
+ "model.layers.28.input_layernorm.weight": "model-00007-of-000017.safetensors",
267
+ "model.layers.28.post_attention_layernorm.weight": "model-00007-of-000017.safetensors",
268
+ "model.layers.29.self_attn.q_proj.weight": "model-00007-of-000017.safetensors",
269
+ "model.layers.29.self_attn.k_proj.weight": "model-00007-of-000017.safetensors",
270
+ "model.layers.29.self_attn.v_proj.weight": "model-00007-of-000017.safetensors",
271
+ "model.layers.29.self_attn.o_proj.weight": "model-00007-of-000017.safetensors",
272
+ "model.layers.29.mlp.gate_proj.weight": "model-00007-of-000017.safetensors",
273
+ "model.layers.29.mlp.up_proj.weight": "model-00007-of-000017.safetensors",
274
+ "model.layers.29.mlp.down_proj.weight": "model-00007-of-000017.safetensors",
275
+ "model.layers.29.input_layernorm.weight": "model-00007-of-000017.safetensors",
276
+ "model.layers.29.post_attention_layernorm.weight": "model-00007-of-000017.safetensors",
277
+ "model.layers.30.self_attn.q_proj.weight": "model-00008-of-000017.safetensors",
278
+ "model.layers.30.self_attn.k_proj.weight": "model-00008-of-000017.safetensors",
279
+ "model.layers.30.self_attn.v_proj.weight": "model-00008-of-000017.safetensors",
280
+ "model.layers.30.self_attn.o_proj.weight": "model-00008-of-000017.safetensors",
281
+ "model.layers.30.mlp.gate_proj.weight": "model-00008-of-000017.safetensors",
282
+ "model.layers.30.mlp.up_proj.weight": "model-00008-of-000017.safetensors",
283
+ "model.layers.30.mlp.down_proj.weight": "model-00008-of-000017.safetensors",
284
+ "model.layers.30.input_layernorm.weight": "model-00008-of-000017.safetensors",
285
+ "model.layers.30.post_attention_layernorm.weight": "model-00008-of-000017.safetensors",
286
+ "model.layers.31.self_attn.q_proj.weight": "model-00008-of-000017.safetensors",
287
+ "model.layers.31.self_attn.k_proj.weight": "model-00008-of-000017.safetensors",
288
+ "model.layers.31.self_attn.v_proj.weight": "model-00008-of-000017.safetensors",
289
+ "model.layers.31.self_attn.o_proj.weight": "model-00008-of-000017.safetensors",
290
+ "model.layers.31.mlp.gate_proj.weight": "model-00008-of-000017.safetensors",
291
+ "model.layers.31.mlp.up_proj.weight": "model-00008-of-000017.safetensors",
292
+ "model.layers.31.mlp.down_proj.weight": "model-00008-of-000017.safetensors",
293
+ "model.layers.31.input_layernorm.weight": "model-00008-of-000017.safetensors",
294
+ "model.layers.31.post_attention_layernorm.weight": "model-00008-of-000017.safetensors",
295
+ "model.layers.32.self_attn.q_proj.weight": "model-00008-of-000017.safetensors",
296
+ "model.layers.32.self_attn.k_proj.weight": "model-00008-of-000017.safetensors",
297
+ "model.layers.32.self_attn.v_proj.weight": "model-00008-of-000017.safetensors",
298
+ "model.layers.32.self_attn.o_proj.weight": "model-00008-of-000017.safetensors",
299
+ "model.layers.32.mlp.gate_proj.weight": "model-00008-of-000017.safetensors",
300
+ "model.layers.32.mlp.up_proj.weight": "model-00008-of-000017.safetensors",
301
+ "model.layers.32.mlp.down_proj.weight": "model-00008-of-000017.safetensors",
302
+ "model.layers.32.input_layernorm.weight": "model-00008-of-000017.safetensors",
303
+ "model.layers.32.post_attention_layernorm.weight": "model-00008-of-000017.safetensors",
304
+ "model.layers.33.self_attn.q_proj.weight": "model-00008-of-000017.safetensors",
305
+ "model.layers.33.self_attn.k_proj.weight": "model-00008-of-000017.safetensors",
306
+ "model.layers.33.self_attn.v_proj.weight": "model-00008-of-000017.safetensors",
307
+ "model.layers.33.self_attn.o_proj.weight": "model-00008-of-000017.safetensors",
308
+ "model.layers.33.mlp.gate_proj.weight": "model-00008-of-000017.safetensors",
309
+ "model.layers.33.mlp.up_proj.weight": "model-00008-of-000017.safetensors",
310
+ "model.layers.33.mlp.down_proj.weight": "model-00008-of-000017.safetensors",
311
+ "model.layers.33.input_layernorm.weight": "model-00008-of-000017.safetensors",
312
+ "model.layers.33.post_attention_layernorm.weight": "model-00008-of-000017.safetensors",
313
+ "model.layers.34.self_attn.q_proj.weight": "model-00008-of-000017.safetensors",
314
+ "model.layers.34.self_attn.k_proj.weight": "model-00008-of-000017.safetensors",
315
+ "model.layers.34.self_attn.v_proj.weight": "model-00008-of-000017.safetensors",
316
+ "model.layers.34.self_attn.o_proj.weight": "model-00008-of-000017.safetensors",
317
+ "model.layers.34.mlp.gate_proj.weight": "model-00008-of-000017.safetensors",
318
+ "model.layers.34.mlp.up_proj.weight": "model-00008-of-000017.safetensors",
319
+ "model.layers.34.mlp.down_proj.weight": "model-00008-of-000017.safetensors",
320
+ "model.layers.34.input_layernorm.weight": "model-00008-of-000017.safetensors",
321
+ "model.layers.34.post_attention_layernorm.weight": "model-00008-of-000017.safetensors",
322
+ "model.layers.35.self_attn.q_proj.weight": "model-00008-of-000017.safetensors",
323
+ "model.layers.35.self_attn.k_proj.weight": "model-00009-of-000017.safetensors",
324
+ "model.layers.35.self_attn.v_proj.weight": "model-00009-of-000017.safetensors",
325
+ "model.layers.35.self_attn.o_proj.weight": "model-00009-of-000017.safetensors",
326
+ "model.layers.35.mlp.gate_proj.weight": "model-00009-of-000017.safetensors",
327
+ "model.layers.35.mlp.up_proj.weight": "model-00009-of-000017.safetensors",
328
+ "model.layers.35.mlp.down_proj.weight": "model-00009-of-000017.safetensors",
329
+ "model.layers.35.input_layernorm.weight": "model-00009-of-000017.safetensors",
330
+ "model.layers.35.post_attention_layernorm.weight": "model-00009-of-000017.safetensors",
331
+ "model.layers.36.self_attn.q_proj.weight": "model-00009-of-000017.safetensors",
332
+ "model.layers.36.self_attn.k_proj.weight": "model-00009-of-000017.safetensors",
333
+ "model.layers.36.self_attn.v_proj.weight": "model-00009-of-000017.safetensors",
334
+ "model.layers.36.self_attn.o_proj.weight": "model-00009-of-000017.safetensors",
335
+ "model.layers.36.mlp.gate_proj.weight": "model-00009-of-000017.safetensors",
336
+ "model.layers.36.mlp.up_proj.weight": "model-00009-of-000017.safetensors",
337
+ "model.layers.36.mlp.down_proj.weight": "model-00009-of-000017.safetensors",
338
+ "model.layers.36.input_layernorm.weight": "model-00009-of-000017.safetensors",
339
+ "model.layers.36.post_attention_layernorm.weight": "model-00009-of-000017.safetensors",
340
+ "model.layers.37.self_attn.q_proj.weight": "model-00009-of-000017.safetensors",
341
+ "model.layers.37.self_attn.k_proj.weight": "model-00009-of-000017.safetensors",
342
+ "model.layers.37.self_attn.v_proj.weight": "model-00009-of-000017.safetensors",
343
+ "model.layers.37.self_attn.o_proj.weight": "model-00009-of-000017.safetensors",
344
+ "model.layers.37.mlp.gate_proj.weight": "model-00009-of-000017.safetensors",
345
+ "model.layers.37.mlp.up_proj.weight": "model-00009-of-000017.safetensors",
346
+ "model.layers.37.mlp.down_proj.weight": "model-00009-of-000017.safetensors",
347
+ "model.layers.37.input_layernorm.weight": "model-00009-of-000017.safetensors",
348
+ "model.layers.37.post_attention_layernorm.weight": "model-00009-of-000017.safetensors",
349
+ "model.layers.38.self_attn.q_proj.weight": "model-00009-of-000017.safetensors",
350
+ "model.layers.38.self_attn.k_proj.weight": "model-00009-of-000017.safetensors",
351
+ "model.layers.38.self_attn.v_proj.weight": "model-00009-of-000017.safetensors",
352
+ "model.layers.38.self_attn.o_proj.weight": "model-00009-of-000017.safetensors",
353
+ "model.layers.38.mlp.gate_proj.weight": "model-00009-of-000017.safetensors",
354
+ "model.layers.38.mlp.up_proj.weight": "model-00009-of-000017.safetensors",
355
+ "model.layers.38.mlp.down_proj.weight": "model-00009-of-000017.safetensors",
356
+ "model.layers.38.input_layernorm.weight": "model-00009-of-000017.safetensors",
357
+ "model.layers.38.post_attention_layernorm.weight": "model-00009-of-000017.safetensors",
358
+ "model.layers.39.self_attn.q_proj.weight": "model-00009-of-000017.safetensors",
359
+ "model.layers.39.self_attn.k_proj.weight": "model-00009-of-000017.safetensors",
360
+ "model.layers.39.self_attn.v_proj.weight": "model-00009-of-000017.safetensors",
361
+ "model.layers.39.self_attn.o_proj.weight": "model-00009-of-000017.safetensors",
362
+ "model.layers.39.mlp.gate_proj.weight": "model-00009-of-000017.safetensors",
363
+ "model.layers.39.mlp.up_proj.weight": "model-00009-of-000017.safetensors",
364
+ "model.layers.39.mlp.down_proj.weight": "model-00009-of-000017.safetensors",
365
+ "model.layers.39.input_layernorm.weight": "model-00009-of-000017.safetensors",
366
+ "model.layers.39.post_attention_layernorm.weight": "model-00009-of-000017.safetensors",
367
+ "model.layers.40.self_attn.q_proj.weight": "model-00010-of-000017.safetensors",
368
+ "model.layers.40.self_attn.k_proj.weight": "model-00010-of-000017.safetensors",
369
+ "model.layers.40.self_attn.v_proj.weight": "model-00010-of-000017.safetensors",
370
+ "model.layers.40.self_attn.o_proj.weight": "model-00010-of-000017.safetensors",
371
+ "model.layers.40.mlp.gate_proj.weight": "model-00010-of-000017.safetensors",
372
+ "model.layers.40.mlp.up_proj.weight": "model-00010-of-000017.safetensors",
373
+ "model.layers.40.mlp.down_proj.weight": "model-00010-of-000017.safetensors",
374
+ "model.layers.40.input_layernorm.weight": "model-00010-of-000017.safetensors",
375
+ "model.layers.40.post_attention_layernorm.weight": "model-00010-of-000017.safetensors",
376
+ "model.layers.41.self_attn.q_proj.weight": "model-00010-of-000017.safetensors",
377
+ "model.layers.41.self_attn.k_proj.weight": "model-00010-of-000017.safetensors",
378
+ "model.layers.41.self_attn.v_proj.weight": "model-00010-of-000017.safetensors",
379
+ "model.layers.41.self_attn.o_proj.weight": "model-00010-of-000017.safetensors",
380
+ "model.layers.41.mlp.gate_proj.weight": "model-00010-of-000017.safetensors",
381
+ "model.layers.41.mlp.up_proj.weight": "model-00010-of-000017.safetensors",
382
+ "model.layers.41.mlp.down_proj.weight": "model-00010-of-000017.safetensors",
383
+ "model.layers.41.input_layernorm.weight": "model-00010-of-000017.safetensors",
384
+ "model.layers.41.post_attention_layernorm.weight": "model-00010-of-000017.safetensors",
385
+ "model.layers.42.self_attn.q_proj.weight": "model-00010-of-000017.safetensors",
386
+ "model.layers.42.self_attn.k_proj.weight": "model-00010-of-000017.safetensors",
387
+ "model.layers.42.self_attn.v_proj.weight": "model-00010-of-000017.safetensors",
388
+ "model.layers.42.self_attn.o_proj.weight": "model-00010-of-000017.safetensors",
389
+ "model.layers.42.mlp.gate_proj.weight": "model-00010-of-000017.safetensors",
390
+ "model.layers.42.mlp.up_proj.weight": "model-00010-of-000017.safetensors",
391
+ "model.layers.42.mlp.down_proj.weight": "model-00010-of-000017.safetensors",
392
+ "model.layers.42.input_layernorm.weight": "model-00010-of-000017.safetensors",
393
+ "model.layers.42.post_attention_layernorm.weight": "model-00010-of-000017.safetensors",
394
+ "model.layers.43.self_attn.q_proj.weight": "model-00010-of-000017.safetensors",
395
+ "model.layers.43.self_attn.k_proj.weight": "model-00010-of-000017.safetensors",
396
+ "model.layers.43.self_attn.v_proj.weight": "model-00010-of-000017.safetensors",
397
+ "model.layers.43.self_attn.o_proj.weight": "model-00010-of-000017.safetensors",
398
+ "model.layers.43.mlp.gate_proj.weight": "model-00010-of-000017.safetensors",
399
+ "model.layers.43.mlp.up_proj.weight": "model-00010-of-000017.safetensors",
400
+ "model.layers.43.mlp.down_proj.weight": "model-00010-of-000017.safetensors",
401
+ "model.layers.43.input_layernorm.weight": "model-00010-of-000017.safetensors",
402
+ "model.layers.43.post_attention_layernorm.weight": "model-00010-of-000017.safetensors",
403
+ "model.layers.44.self_attn.q_proj.weight": "model-00010-of-000017.safetensors",
404
+ "model.layers.44.self_attn.k_proj.weight": "model-00010-of-000017.safetensors",
405
+ "model.layers.44.self_attn.v_proj.weight": "model-00010-of-000017.safetensors",
406
+ "model.layers.44.self_attn.o_proj.weight": "model-00010-of-000017.safetensors",
407
+ "model.layers.44.mlp.gate_proj.weight": "model-00010-of-000017.safetensors",
408
+ "model.layers.44.mlp.up_proj.weight": "model-00010-of-000017.safetensors",
409
+ "model.layers.44.mlp.down_proj.weight": "model-00010-of-000017.safetensors",
410
+ "model.layers.44.input_layernorm.weight": "model-00010-of-000017.safetensors",
411
+ "model.layers.44.post_attention_layernorm.weight": "model-00010-of-000017.safetensors",
412
+ "model.layers.45.self_attn.q_proj.weight": "model-00010-of-000017.safetensors",
413
+ "model.layers.45.self_attn.k_proj.weight": "model-00011-of-000017.safetensors",
414
+ "model.layers.45.self_attn.v_proj.weight": "model-00011-of-000017.safetensors",
415
+ "model.layers.45.self_attn.o_proj.weight": "model-00011-of-000017.safetensors",
416
+ "model.layers.45.mlp.gate_proj.weight": "model-00011-of-000017.safetensors",
417
+ "model.layers.45.mlp.up_proj.weight": "model-00011-of-000017.safetensors",
418
+ "model.layers.45.mlp.down_proj.weight": "model-00011-of-000017.safetensors",
419
+ "model.layers.45.input_layernorm.weight": "model-00011-of-000017.safetensors",
420
+ "model.layers.45.post_attention_layernorm.weight": "model-00011-of-000017.safetensors",
421
+ "model.layers.46.self_attn.q_proj.weight": "model-00011-of-000017.safetensors",
422
+ "model.layers.46.self_attn.k_proj.weight": "model-00011-of-000017.safetensors",
423
+ "model.layers.46.self_attn.v_proj.weight": "model-00011-of-000017.safetensors",
424
+ "model.layers.46.self_attn.o_proj.weight": "model-00011-of-000017.safetensors",
425
+ "model.layers.46.mlp.gate_proj.weight": "model-00011-of-000017.safetensors",
426
+ "model.layers.46.mlp.up_proj.weight": "model-00011-of-000017.safetensors",
427
+ "model.layers.46.mlp.down_proj.weight": "model-00011-of-000017.safetensors",
428
+ "model.layers.46.input_layernorm.weight": "model-00011-of-000017.safetensors",
429
+ "model.layers.46.post_attention_layernorm.weight": "model-00011-of-000017.safetensors",
430
+ "model.layers.47.self_attn.q_proj.weight": "model-00011-of-000017.safetensors",
431
+ "model.layers.47.self_attn.k_proj.weight": "model-00011-of-000017.safetensors",
432
+ "model.layers.47.self_attn.v_proj.weight": "model-00011-of-000017.safetensors",
433
+ "model.layers.47.self_attn.o_proj.weight": "model-00011-of-000017.safetensors",
434
+ "model.layers.47.mlp.gate_proj.weight": "model-00011-of-000017.safetensors",
435
+ "model.layers.47.mlp.up_proj.weight": "model-00011-of-000017.safetensors",
436
+ "model.layers.47.mlp.down_proj.weight": "model-00011-of-000017.safetensors",
437
+ "model.layers.47.input_layernorm.weight": "model-00011-of-000017.safetensors",
438
+ "model.layers.47.post_attention_layernorm.weight": "model-00011-of-000017.safetensors",
439
+ "model.layers.48.self_attn.q_proj.weight": "model-00011-of-000017.safetensors",
440
+ "model.layers.48.self_attn.k_proj.weight": "model-00011-of-000017.safetensors",
441
+ "model.layers.48.self_attn.v_proj.weight": "model-00011-of-000017.safetensors",
442
+ "model.layers.48.self_attn.o_proj.weight": "model-00011-of-000017.safetensors",
443
+ "model.layers.48.mlp.gate_proj.weight": "model-00011-of-000017.safetensors",
444
+ "model.layers.48.mlp.up_proj.weight": "model-00011-of-000017.safetensors",
445
+ "model.layers.48.mlp.down_proj.weight": "model-00011-of-000017.safetensors",
446
+ "model.layers.48.input_layernorm.weight": "model-00011-of-000017.safetensors",
447
+ "model.layers.48.post_attention_layernorm.weight": "model-00011-of-000017.safetensors",
448
+ "model.layers.49.self_attn.q_proj.weight": "model-00011-of-000017.safetensors",
449
+ "model.layers.49.self_attn.k_proj.weight": "model-00011-of-000017.safetensors",
450
+ "model.layers.49.self_attn.v_proj.weight": "model-00011-of-000017.safetensors",
451
+ "model.layers.49.self_attn.o_proj.weight": "model-00011-of-000017.safetensors",
452
+ "model.layers.49.mlp.gate_proj.weight": "model-00011-of-000017.safetensors",
453
+ "model.layers.49.mlp.up_proj.weight": "model-00011-of-000017.safetensors",
454
+ "model.layers.49.mlp.down_proj.weight": "model-00011-of-000017.safetensors",
455
+ "model.layers.49.input_layernorm.weight": "model-00011-of-000017.safetensors",
456
+ "model.layers.49.post_attention_layernorm.weight": "model-00011-of-000017.safetensors",
457
+ "model.layers.50.self_attn.q_proj.weight": "model-00012-of-000017.safetensors",
458
+ "model.layers.50.self_attn.k_proj.weight": "model-00012-of-000017.safetensors",
459
+ "model.layers.50.self_attn.v_proj.weight": "model-00012-of-000017.safetensors",
460
+ "model.layers.50.self_attn.o_proj.weight": "model-00012-of-000017.safetensors",
461
+ "model.layers.50.mlp.gate_proj.weight": "model-00012-of-000017.safetensors",
462
+ "model.layers.50.mlp.up_proj.weight": "model-00012-of-000017.safetensors",
463
+ "model.layers.50.mlp.down_proj.weight": "model-00012-of-000017.safetensors",
464
+ "model.layers.50.input_layernorm.weight": "model-00012-of-000017.safetensors",
465
+ "model.layers.50.post_attention_layernorm.weight": "model-00012-of-000017.safetensors",
466
+ "model.layers.51.self_attn.q_proj.weight": "model-00012-of-000017.safetensors",
467
+ "model.layers.51.self_attn.k_proj.weight": "model-00012-of-000017.safetensors",
468
+ "model.layers.51.self_attn.v_proj.weight": "model-00012-of-000017.safetensors",
469
+ "model.layers.51.self_attn.o_proj.weight": "model-00012-of-000017.safetensors",
470
+ "model.layers.51.mlp.gate_proj.weight": "model-00012-of-000017.safetensors",
471
+ "model.layers.51.mlp.up_proj.weight": "model-00012-of-000017.safetensors",
472
+ "model.layers.51.mlp.down_proj.weight": "model-00012-of-000017.safetensors",
473
+ "model.layers.51.input_layernorm.weight": "model-00012-of-000017.safetensors",
474
+ "model.layers.51.post_attention_layernorm.weight": "model-00012-of-000017.safetensors",
475
+ "model.layers.52.self_attn.q_proj.weight": "model-00012-of-000017.safetensors",
476
+ "model.layers.52.self_attn.k_proj.weight": "model-00012-of-000017.safetensors",
477
+ "model.layers.52.self_attn.v_proj.weight": "model-00012-of-000017.safetensors",
478
+ "model.layers.52.self_attn.o_proj.weight": "model-00012-of-000017.safetensors",
479
+ "model.layers.52.mlp.gate_proj.weight": "model-00012-of-000017.safetensors",
480
+ "model.layers.52.mlp.up_proj.weight": "model-00012-of-000017.safetensors",
481
+ "model.layers.52.mlp.down_proj.weight": "model-00012-of-000017.safetensors",
482
+ "model.layers.52.input_layernorm.weight": "model-00012-of-000017.safetensors",
483
+ "model.layers.52.post_attention_layernorm.weight": "model-00012-of-000017.safetensors",
484
+ "model.layers.53.self_attn.q_proj.weight": "model-00012-of-000017.safetensors",
485
+ "model.layers.53.self_attn.k_proj.weight": "model-00012-of-000017.safetensors",
486
+ "model.layers.53.self_attn.v_proj.weight": "model-00012-of-000017.safetensors",
487
+ "model.layers.53.self_attn.o_proj.weight": "model-00012-of-000017.safetensors",
488
+ "model.layers.53.mlp.gate_proj.weight": "model-00012-of-000017.safetensors",
489
+ "model.layers.53.mlp.up_proj.weight": "model-00012-of-000017.safetensors",
490
+ "model.layers.53.mlp.down_proj.weight": "model-00012-of-000017.safetensors",
491
+ "model.layers.53.input_layernorm.weight": "model-00012-of-000017.safetensors",
492
+ "model.layers.53.post_attention_layernorm.weight": "model-00012-of-000017.safetensors",
493
+ "model.layers.54.self_attn.q_proj.weight": "model-00012-of-000017.safetensors",
494
+ "model.layers.54.self_attn.k_proj.weight": "model-00012-of-000017.safetensors",
495
+ "model.layers.54.self_attn.v_proj.weight": "model-00012-of-000017.safetensors",
496
+ "model.layers.54.self_attn.o_proj.weight": "model-00012-of-000017.safetensors",
497
+ "model.layers.54.mlp.gate_proj.weight": "model-00012-of-000017.safetensors",
498
+ "model.layers.54.mlp.up_proj.weight": "model-00012-of-000017.safetensors",
499
+ "model.layers.54.mlp.down_proj.weight": "model-00012-of-000017.safetensors",
500
+ "model.layers.54.input_layernorm.weight": "model-00012-of-000017.safetensors",
501
+ "model.layers.54.post_attention_layernorm.weight": "model-00012-of-000017.safetensors",
502
+ "model.layers.55.self_attn.q_proj.weight": "model-00012-of-000017.safetensors",
503
+ "model.layers.55.self_attn.k_proj.weight": "model-00013-of-000017.safetensors",
504
+ "model.layers.55.self_attn.v_proj.weight": "model-00013-of-000017.safetensors",
505
+ "model.layers.55.self_attn.o_proj.weight": "model-00013-of-000017.safetensors",
506
+ "model.layers.55.mlp.gate_proj.weight": "model-00013-of-000017.safetensors",
507
+ "model.layers.55.mlp.up_proj.weight": "model-00013-of-000017.safetensors",
508
+ "model.layers.55.mlp.down_proj.weight": "model-00013-of-000017.safetensors",
509
+ "model.layers.55.input_layernorm.weight": "model-00013-of-000017.safetensors",
510
+ "model.layers.55.post_attention_layernorm.weight": "model-00013-of-000017.safetensors",
511
+ "model.layers.56.self_attn.q_proj.weight": "model-00013-of-000017.safetensors",
512
+ "model.layers.56.self_attn.k_proj.weight": "model-00013-of-000017.safetensors",
513
+ "model.layers.56.self_attn.v_proj.weight": "model-00013-of-000017.safetensors",
514
+ "model.layers.56.self_attn.o_proj.weight": "model-00013-of-000017.safetensors",
515
+ "model.layers.56.mlp.gate_proj.weight": "model-00013-of-000017.safetensors",
516
+ "model.layers.56.mlp.up_proj.weight": "model-00013-of-000017.safetensors",
517
+ "model.layers.56.mlp.down_proj.weight": "model-00013-of-000017.safetensors",
518
+ "model.layers.56.input_layernorm.weight": "model-00013-of-000017.safetensors",
519
+ "model.layers.56.post_attention_layernorm.weight": "model-00013-of-000017.safetensors",
520
+ "model.layers.57.self_attn.q_proj.weight": "model-00013-of-000017.safetensors",
521
+ "model.layers.57.self_attn.k_proj.weight": "model-00013-of-000017.safetensors",
522
+ "model.layers.57.self_attn.v_proj.weight": "model-00013-of-000017.safetensors",
523
+ "model.layers.57.self_attn.o_proj.weight": "model-00013-of-000017.safetensors",
524
+ "model.layers.57.mlp.gate_proj.weight": "model-00013-of-000017.safetensors",
525
+ "model.layers.57.mlp.up_proj.weight": "model-00013-of-000017.safetensors",
526
+ "model.layers.57.mlp.down_proj.weight": "model-00013-of-000017.safetensors",
527
+ "model.layers.57.input_layernorm.weight": "model-00013-of-000017.safetensors",
528
+ "model.layers.57.post_attention_layernorm.weight": "model-00013-of-000017.safetensors",
529
+ "model.layers.58.self_attn.q_proj.weight": "model-00013-of-000017.safetensors",
530
+ "model.layers.58.self_attn.k_proj.weight": "model-00013-of-000017.safetensors",
531
+ "model.layers.58.self_attn.v_proj.weight": "model-00013-of-000017.safetensors",
532
+ "model.layers.58.self_attn.o_proj.weight": "model-00013-of-000017.safetensors",
533
+ "model.layers.58.mlp.gate_proj.weight": "model-00013-of-000017.safetensors",
534
+ "model.layers.58.mlp.up_proj.weight": "model-00013-of-000017.safetensors",
535
+ "model.layers.58.mlp.down_proj.weight": "model-00013-of-000017.safetensors",
536
+ "model.layers.58.input_layernorm.weight": "model-00013-of-000017.safetensors",
537
+ "model.layers.58.post_attention_layernorm.weight": "model-00013-of-000017.safetensors",
538
+ "model.layers.59.self_attn.q_proj.weight": "model-00013-of-000017.safetensors",
539
+ "model.layers.59.self_attn.k_proj.weight": "model-00013-of-000017.safetensors",
540
+ "model.layers.59.self_attn.v_proj.weight": "model-00013-of-000017.safetensors",
541
+ "model.layers.59.self_attn.o_proj.weight": "model-00013-of-000017.safetensors",
542
+ "model.layers.59.mlp.gate_proj.weight": "model-00013-of-000017.safetensors",
543
+ "model.layers.59.mlp.up_proj.weight": "model-00013-of-000017.safetensors",
544
+ "model.layers.59.mlp.down_proj.weight": "model-00013-of-000017.safetensors",
545
+ "model.layers.59.input_layernorm.weight": "model-00013-of-000017.safetensors",
546
+ "model.layers.59.post_attention_layernorm.weight": "model-00013-of-000017.safetensors",
547
+ "model.layers.60.self_attn.q_proj.weight": "model-00014-of-000017.safetensors",
548
+ "model.layers.60.self_attn.k_proj.weight": "model-00014-of-000017.safetensors",
549
+ "model.layers.60.self_attn.v_proj.weight": "model-00014-of-000017.safetensors",
550
+ "model.layers.60.self_attn.o_proj.weight": "model-00014-of-000017.safetensors",
551
+ "model.layers.60.mlp.gate_proj.weight": "model-00014-of-000017.safetensors",
552
+ "model.layers.60.mlp.up_proj.weight": "model-00014-of-000017.safetensors",
553
+ "model.layers.60.mlp.down_proj.weight": "model-00014-of-000017.safetensors",
554
+ "model.layers.60.input_layernorm.weight": "model-00014-of-000017.safetensors",
555
+ "model.layers.60.post_attention_layernorm.weight": "model-00014-of-000017.safetensors",
556
+ "model.layers.61.self_attn.q_proj.weight": "model-00014-of-000017.safetensors",
557
+ "model.layers.61.self_attn.k_proj.weight": "model-00014-of-000017.safetensors",
558
+ "model.layers.61.self_attn.v_proj.weight": "model-00014-of-000017.safetensors",
559
+ "model.layers.61.self_attn.o_proj.weight": "model-00014-of-000017.safetensors",
560
+ "model.layers.61.mlp.gate_proj.weight": "model-00014-of-000017.safetensors",
561
+ "model.layers.61.mlp.up_proj.weight": "model-00014-of-000017.safetensors",
562
+ "model.layers.61.mlp.down_proj.weight": "model-00014-of-000017.safetensors",
563
+ "model.layers.61.input_layernorm.weight": "model-00014-of-000017.safetensors",
564
+ "model.layers.61.post_attention_layernorm.weight": "model-00014-of-000017.safetensors",
565
+ "model.layers.62.self_attn.q_proj.weight": "model-00014-of-000017.safetensors",
566
+ "model.layers.62.self_attn.k_proj.weight": "model-00014-of-000017.safetensors",
567
+ "model.layers.62.self_attn.v_proj.weight": "model-00014-of-000017.safetensors",
568
+ "model.layers.62.self_attn.o_proj.weight": "model-00014-of-000017.safetensors",
569
+ "model.layers.62.mlp.gate_proj.weight": "model-00014-of-000017.safetensors",
570
+ "model.layers.62.mlp.up_proj.weight": "model-00014-of-000017.safetensors",
571
+ "model.layers.62.mlp.down_proj.weight": "model-00014-of-000017.safetensors",
572
+ "model.layers.62.input_layernorm.weight": "model-00014-of-000017.safetensors",
573
+ "model.layers.62.post_attention_layernorm.weight": "model-00014-of-000017.safetensors",
574
+ "model.layers.63.self_attn.q_proj.weight": "model-00014-of-000017.safetensors",
575
+ "model.layers.63.self_attn.k_proj.weight": "model-00014-of-000017.safetensors",
576
+ "model.layers.63.self_attn.v_proj.weight": "model-00014-of-000017.safetensors",
577
+ "model.layers.63.self_attn.o_proj.weight": "model-00014-of-000017.safetensors",
578
+ "model.layers.63.mlp.gate_proj.weight": "model-00014-of-000017.safetensors",
579
+ "model.layers.63.mlp.up_proj.weight": "model-00014-of-000017.safetensors",
580
+ "model.layers.63.mlp.down_proj.weight": "model-00014-of-000017.safetensors",
581
+ "model.layers.63.input_layernorm.weight": "model-00014-of-000017.safetensors",
582
+ "model.layers.63.post_attention_layernorm.weight": "model-00014-of-000017.safetensors",
583
+ "model.layers.64.self_attn.q_proj.weight": "model-00014-of-000017.safetensors",
584
+ "model.layers.64.self_attn.k_proj.weight": "model-00014-of-000017.safetensors",
585
+ "model.layers.64.self_attn.v_proj.weight": "model-00014-of-000017.safetensors",
586
+ "model.layers.64.self_attn.o_proj.weight": "model-00014-of-000017.safetensors",
587
+ "model.layers.64.mlp.gate_proj.weight": "model-00014-of-000017.safetensors",
588
+ "model.layers.64.mlp.up_proj.weight": "model-00014-of-000017.safetensors",
589
+ "model.layers.64.mlp.down_proj.weight": "model-00014-of-000017.safetensors",
590
+ "model.layers.64.input_layernorm.weight": "model-00014-of-000017.safetensors",
591
+ "model.layers.64.post_attention_layernorm.weight": "model-00014-of-000017.safetensors",
592
+ "model.layers.65.self_attn.q_proj.weight": "model-00014-of-000017.safetensors",
593
+ "model.layers.65.self_attn.k_proj.weight": "model-00015-of-000017.safetensors",
594
+ "model.layers.65.self_attn.v_proj.weight": "model-00015-of-000017.safetensors",
595
+ "model.layers.65.self_attn.o_proj.weight": "model-00015-of-000017.safetensors",
596
+ "model.layers.65.mlp.gate_proj.weight": "model-00015-of-000017.safetensors",
597
+ "model.layers.65.mlp.up_proj.weight": "model-00015-of-000017.safetensors",
598
+ "model.layers.65.mlp.down_proj.weight": "model-00015-of-000017.safetensors",
599
+ "model.layers.65.input_layernorm.weight": "model-00015-of-000017.safetensors",
600
+ "model.layers.65.post_attention_layernorm.weight": "model-00015-of-000017.safetensors",
601
+ "model.layers.66.self_attn.q_proj.weight": "model-00015-of-000017.safetensors",
602
+ "model.layers.66.self_attn.k_proj.weight": "model-00015-of-000017.safetensors",
603
+ "model.layers.66.self_attn.v_proj.weight": "model-00015-of-000017.safetensors",
604
+ "model.layers.66.self_attn.o_proj.weight": "model-00015-of-000017.safetensors",
605
+ "model.layers.66.mlp.gate_proj.weight": "model-00015-of-000017.safetensors",
606
+ "model.layers.66.mlp.up_proj.weight": "model-00015-of-000017.safetensors",
607
+ "model.layers.66.mlp.down_proj.weight": "model-00015-of-000017.safetensors",
608
+ "model.layers.66.input_layernorm.weight": "model-00015-of-000017.safetensors",
609
+ "model.layers.66.post_attention_layernorm.weight": "model-00015-of-000017.safetensors",
610
+ "model.layers.67.self_attn.q_proj.weight": "model-00015-of-000017.safetensors",
611
+ "model.layers.67.self_attn.k_proj.weight": "model-00015-of-000017.safetensors",
612
+ "model.layers.67.self_attn.v_proj.weight": "model-00015-of-000017.safetensors",
613
+ "model.layers.67.self_attn.o_proj.weight": "model-00015-of-000017.safetensors",
614
+ "model.layers.67.mlp.gate_proj.weight": "model-00015-of-000017.safetensors",
615
+ "model.layers.67.mlp.up_proj.weight": "model-00015-of-000017.safetensors",
616
+ "model.layers.67.mlp.down_proj.weight": "model-00015-of-000017.safetensors",
617
+ "model.layers.67.input_layernorm.weight": "model-00015-of-000017.safetensors",
618
+ "model.layers.67.post_attention_layernorm.weight": "model-00015-of-000017.safetensors",
619
+ "model.layers.68.self_attn.q_proj.weight": "model-00015-of-000017.safetensors",
620
+ "model.layers.68.self_attn.k_proj.weight": "model-00015-of-000017.safetensors",
621
+ "model.layers.68.self_attn.v_proj.weight": "model-00015-of-000017.safetensors",
622
+ "model.layers.68.self_attn.o_proj.weight": "model-00015-of-000017.safetensors",
623
+ "model.layers.68.mlp.gate_proj.weight": "model-00015-of-000017.safetensors",
624
+ "model.layers.68.mlp.up_proj.weight": "model-00015-of-000017.safetensors",
625
+ "model.layers.68.mlp.down_proj.weight": "model-00015-of-000017.safetensors",
626
+ "model.layers.68.input_layernorm.weight": "model-00015-of-000017.safetensors",
627
+ "model.layers.68.post_attention_layernorm.weight": "model-00015-of-000017.safetensors",
628
+ "model.layers.69.self_attn.q_proj.weight": "model-00015-of-000017.safetensors",
629
+ "model.layers.69.self_attn.k_proj.weight": "model-00015-of-000017.safetensors",
630
+ "model.layers.69.self_attn.v_proj.weight": "model-00015-of-000017.safetensors",
631
+ "model.layers.69.self_attn.o_proj.weight": "model-00015-of-000017.safetensors",
632
+ "model.layers.69.mlp.gate_proj.weight": "model-00015-of-000017.safetensors",
633
+ "model.layers.69.mlp.up_proj.weight": "model-00015-of-000017.safetensors",
634
+ "model.layers.69.mlp.down_proj.weight": "model-00015-of-000017.safetensors",
635
+ "model.layers.69.input_layernorm.weight": "model-00015-of-000017.safetensors",
636
+ "model.layers.69.post_attention_layernorm.weight": "model-00015-of-000017.safetensors",
637
+ "model.layers.70.self_attn.q_proj.weight": "model-00016-of-000017.safetensors",
638
+ "model.layers.70.self_attn.k_proj.weight": "model-00016-of-000017.safetensors",
639
+ "model.layers.70.self_attn.v_proj.weight": "model-00016-of-000017.safetensors",
640
+ "model.layers.70.self_attn.o_proj.weight": "model-00016-of-000017.safetensors",
641
+ "model.layers.70.mlp.gate_proj.weight": "model-00016-of-000017.safetensors",
642
+ "model.layers.70.mlp.up_proj.weight": "model-00016-of-000017.safetensors",
643
+ "model.layers.70.mlp.down_proj.weight": "model-00016-of-000017.safetensors",
644
+ "model.layers.70.input_layernorm.weight": "model-00016-of-000017.safetensors",
645
+ "model.layers.70.post_attention_layernorm.weight": "model-00016-of-000017.safetensors",
646
+ "model.layers.71.self_attn.q_proj.weight": "model-00016-of-000017.safetensors",
647
+ "model.layers.71.self_attn.k_proj.weight": "model-00016-of-000017.safetensors",
648
+ "model.layers.71.self_attn.v_proj.weight": "model-00016-of-000017.safetensors",
649
+ "model.layers.71.self_attn.o_proj.weight": "model-00016-of-000017.safetensors",
650
+ "model.layers.71.mlp.gate_proj.weight": "model-00016-of-000017.safetensors",
651
+ "model.layers.71.mlp.up_proj.weight": "model-00016-of-000017.safetensors",
652
+ "model.layers.71.mlp.down_proj.weight": "model-00016-of-000017.safetensors",
653
+ "model.layers.71.input_layernorm.weight": "model-00016-of-000017.safetensors",
654
+ "model.layers.71.post_attention_layernorm.weight": "model-00016-of-000017.safetensors",
655
+ "model.layers.72.self_attn.q_proj.weight": "model-00016-of-000017.safetensors",
656
+ "model.layers.72.self_attn.k_proj.weight": "model-00016-of-000017.safetensors",
657
+ "model.layers.72.self_attn.v_proj.weight": "model-00016-of-000017.safetensors",
658
+ "model.layers.72.self_attn.o_proj.weight": "model-00016-of-000017.safetensors",
659
+ "model.layers.72.mlp.gate_proj.weight": "model-00016-of-000017.safetensors",
660
+ "model.layers.72.mlp.up_proj.weight": "model-00016-of-000017.safetensors",
661
+ "model.layers.72.mlp.down_proj.weight": "model-00016-of-000017.safetensors",
662
+ "model.layers.72.input_layernorm.weight": "model-00016-of-000017.safetensors",
663
+ "model.layers.72.post_attention_layernorm.weight": "model-00016-of-000017.safetensors",
664
+ "model.layers.73.self_attn.q_proj.weight": "model-00016-of-000017.safetensors",
665
+ "model.layers.73.self_attn.k_proj.weight": "model-00016-of-000017.safetensors",
666
+ "model.layers.73.self_attn.v_proj.weight": "model-00016-of-000017.safetensors",
667
+ "model.layers.73.self_attn.o_proj.weight": "model-00016-of-000017.safetensors",
668
+ "model.layers.73.mlp.gate_proj.weight": "model-00016-of-000017.safetensors",
669
+ "model.layers.73.mlp.up_proj.weight": "model-00016-of-000017.safetensors",
670
+ "model.layers.73.mlp.down_proj.weight": "model-00016-of-000017.safetensors",
671
+ "model.layers.73.input_layernorm.weight": "model-00016-of-000017.safetensors",
672
+ "model.layers.73.post_attention_layernorm.weight": "model-00016-of-000017.safetensors",
673
+ "model.layers.74.self_attn.q_proj.weight": "model-00016-of-000017.safetensors",
674
+ "model.layers.74.self_attn.k_proj.weight": "model-00016-of-000017.safetensors",
675
+ "model.layers.74.self_attn.v_proj.weight": "model-00016-of-000017.safetensors",
676
+ "model.layers.74.self_attn.o_proj.weight": "model-00016-of-000017.safetensors",
677
+ "model.layers.74.mlp.gate_proj.weight": "model-00016-of-000017.safetensors",
678
+ "model.layers.74.mlp.up_proj.weight": "model-00016-of-000017.safetensors",
679
+ "model.layers.74.mlp.down_proj.weight": "model-00016-of-000017.safetensors",
680
+ "model.layers.74.input_layernorm.weight": "model-00016-of-000017.safetensors",
681
+ "model.layers.74.post_attention_layernorm.weight": "model-00016-of-000017.safetensors",
682
+ "model.layers.75.self_attn.q_proj.weight": "model-00016-of-000017.safetensors",
683
+ "model.layers.75.self_attn.k_proj.weight": "model-00017-of-000017.safetensors",
684
+ "model.layers.75.self_attn.v_proj.weight": "model-00017-of-000017.safetensors",
685
+ "model.layers.75.self_attn.o_proj.weight": "model-00017-of-000017.safetensors",
686
+ "model.layers.75.mlp.gate_proj.weight": "model-00017-of-000017.safetensors",
687
+ "model.layers.75.mlp.up_proj.weight": "model-00017-of-000017.safetensors",
688
+ "model.layers.75.mlp.down_proj.weight": "model-00017-of-000017.safetensors",
689
+ "model.layers.75.input_layernorm.weight": "model-00017-of-000017.safetensors",
690
+ "model.layers.75.post_attention_layernorm.weight": "model-00017-of-000017.safetensors",
691
+ "model.layers.76.self_attn.q_proj.weight": "model-00017-of-000017.safetensors",
692
+ "model.layers.76.self_attn.k_proj.weight": "model-00017-of-000017.safetensors",
693
+ "model.layers.76.self_attn.v_proj.weight": "model-00017-of-000017.safetensors",
694
+ "model.layers.76.self_attn.o_proj.weight": "model-00017-of-000017.safetensors",
695
+ "model.layers.76.mlp.gate_proj.weight": "model-00017-of-000017.safetensors",
696
+ "model.layers.76.mlp.up_proj.weight": "model-00017-of-000017.safetensors",
697
+ "model.layers.76.mlp.down_proj.weight": "model-00017-of-000017.safetensors",
698
+ "model.layers.76.input_layernorm.weight": "model-00017-of-000017.safetensors",
699
+ "model.layers.76.post_attention_layernorm.weight": "model-00017-of-000017.safetensors",
700
+ "model.layers.77.self_attn.q_proj.weight": "model-00017-of-000017.safetensors",
701
+ "model.layers.77.self_attn.k_proj.weight": "model-00017-of-000017.safetensors",
702
+ "model.layers.77.self_attn.v_proj.weight": "model-00017-of-000017.safetensors",
703
+ "model.layers.77.self_attn.o_proj.weight": "model-00017-of-000017.safetensors",
704
+ "model.layers.77.mlp.gate_proj.weight": "model-00017-of-000017.safetensors",
705
+ "model.layers.77.mlp.up_proj.weight": "model-00017-of-000017.safetensors",
706
+ "model.layers.77.mlp.down_proj.weight": "model-00017-of-000017.safetensors",
707
+ "model.layers.77.input_layernorm.weight": "model-00017-of-000017.safetensors",
708
+ "model.layers.77.post_attention_layernorm.weight": "model-00017-of-000017.safetensors",
709
+ "model.layers.78.self_attn.q_proj.weight": "model-00017-of-000017.safetensors",
710
+ "model.layers.78.self_attn.k_proj.weight": "model-00017-of-000017.safetensors",
711
+ "model.layers.78.self_attn.v_proj.weight": "model-00017-of-000017.safetensors",
712
+ "model.layers.78.self_attn.o_proj.weight": "model-00017-of-000017.safetensors",
713
+ "model.layers.78.mlp.gate_proj.weight": "model-00017-of-000017.safetensors",
714
+ "model.layers.78.mlp.up_proj.weight": "model-00017-of-000017.safetensors",
715
+ "model.layers.78.mlp.down_proj.weight": "model-00017-of-000017.safetensors",
716
+ "model.layers.78.input_layernorm.weight": "model-00017-of-000017.safetensors",
717
+ "model.layers.78.post_attention_layernorm.weight": "model-00017-of-000017.safetensors",
718
+ "model.layers.79.self_attn.q_proj.weight": "model-00017-of-000017.safetensors",
719
+ "model.layers.79.self_attn.k_proj.weight": "model-00017-of-000017.safetensors",
720
+ "model.layers.79.self_attn.v_proj.weight": "model-00017-of-000017.safetensors",
721
+ "model.layers.79.self_attn.o_proj.weight": "model-00017-of-000017.safetensors",
722
+ "model.layers.79.mlp.gate_proj.weight": "model-00017-of-000017.safetensors",
723
+ "model.layers.79.mlp.up_proj.weight": "model-00017-of-000017.safetensors",
724
+ "model.layers.79.mlp.down_proj.weight": "model-00017-of-000017.safetensors",
725
+ "model.layers.79.input_layernorm.weight": "model-00017-of-000017.safetensors",
726
+ "model.layers.79.post_attention_layernorm.weight": "model-00017-of-000017.safetensors",
727
+ "model.norm.weight": "model-00017-of-000017.safetensors",
728
+ "lm_head.weight": "model-00017-of-000017.safetensors"
729
+ }
730
+ }
output-00001-of-00008.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b287e8a97168e013848a1818192f178d9265a7a4f455c0a258f51567cafe4ca5
3
+ size 8589950304
output-00002-of-00008.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fb3f2a06b7a2fdb8954d097d2e7581b9889ff2a651652201a3694675ce490ff0
3
+ size 8545844644
output-00003-of-00008.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:559905445120e03015ce9d857419b4ed9b82947125abfd28ad60b7b066f6ee8e
3
+ size 8466270936
output-00004-of-00008.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3d6d3569047cd85c6623a3d47f520ae9c0f1e85ff6fca063a31dd97537b034d3
3
+ size 8455465360
output-00005-of-00008.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4720fd4d687191802a8adbe9657bbda6bf18655cb92bcb6ad8234077e6bc8801
3
+ size 8417433432
output-00006-of-00008.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:67d67be822e4caba82cadcb8b071eb2419ceb21e71f5c44e3a862b3007dc216b
3
+ size 8553569876
output-00007-of-00008.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fa04eaf826980cf544a6402171ff0a9f1eb99259f1d16e3edbf966dadc3cbe2b
3
+ size 8388590704
output-00008-of-00008.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ae9954b1ceaccefd4841e4dc068516683b11d5b83842cd19743c1efbcec18d1f
3
+ size 5970264776
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "bos_token": {
5
+ "__type": "AddedToken",
6
+ "content": "<｜begin▁of▁sentence｜>",
7
+ "lstrip": false,
8
+ "normalized": true,
9
+ "rstrip": false,
10
+ "single_word": false
11
+ },
12
+ "clean_up_tokenization_spaces": false,
13
+ "eos_token": {
14
+ "__type": "AddedToken",
15
+ "content": "<｜end▁of▁sentence｜>",
16
+ "lstrip": false,
17
+ "normalized": true,
18
+ "rstrip": false,
19
+ "single_word": false
20
+ },
21
+ "legacy": true,
22
+ "model_max_length": 16384,
23
+ "pad_token": {
24
+ "__type": "AddedToken",
25
+ "content": "<｜end▁of▁sentence｜>",
26
+ "lstrip": false,
27
+ "normalized": true,
28
+ "rstrip": false,
29
+ "single_word": false
30
+ },
31
+ "sp_model_kwargs": {},
32
+ "unk_token": null,
33
+ "tokenizer_class": "LlamaTokenizerFast",
34
+ "chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% set ns = namespace(is_first=false, is_tool=false, is_output_first=true, system_prompt='') %}{%- for message in messages %}{%- if message['role'] == 'system' %}{% set ns.system_prompt = message['content'] %}{%- endif %}{%- endfor %}{{bos_token}}{{ns.system_prompt}}{%- for message in messages %}{%- if message['role'] == 'user' %}{%- set ns.is_tool = false -%}{{'<｜User｜>' + message['content']}}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is none %}{%- set ns.is_tool = false -%}{%- for tool in message['tool_calls']%}{%- if not ns.is_first %}{{'<｜Assistant｜><｜tool▁calls▁begin｜><｜tool▁call▁begin｜>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\\n' + '```json' + '\\n' + tool['function']['arguments'] + '\\n' + '```' + '<｜tool▁call▁end｜>'}}{%- set ns.is_first = true -%}{%- else %}{{'\\n' + '<｜tool▁call▁begin｜>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\\n' + '```json' + '\\n' + tool['function']['arguments'] + '\\n' + '```' + '<｜tool▁call▁end｜>'}}{{'<｜tool▁calls▁end｜><｜end▁of▁sentence｜>'}}{%- endif %}{%- endfor %}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is not none %}{%- if ns.is_tool %}{{'<｜tool▁outputs▁end｜>' + message['content'] + '<｜end▁of▁sentence｜>'}}{%- set ns.is_tool = false -%}{%- else %}{% set content = message['content'] %}{% if '</think>' in content %}{% set content = content.split('</think>')[-1] %}{% endif %}{{'<｜Assistant｜>' + content + '<｜end▁of▁sentence｜>'}}{%- endif %}{%- endif %}{%- if message['role'] == 'tool' %}{%- set ns.is_tool = true -%}{%- if ns.is_output_first %}{{'<｜tool▁outputs▁begin｜><｜tool▁output▁begin｜>' + message['content'] + '<｜tool▁output▁end｜>'}}{%- set ns.is_output_first = false %}{%- else %}{{'\\n<｜tool▁output▁begin｜>' + message['content'] + '<｜tool▁output▁end｜>'}}{%- endif %}{%- endif %}{%- endfor -%}{% if ns.is_tool %}{{'<｜tool▁outputs▁end｜>'}}{% endif %}{% if add_generation_prompt and not ns.is_tool %}{{'<｜Assistant｜>'}}{% endif %}"
35
+ }