Duplicate from deepseek-ai/DeepSeek-R1-Distill-Qwen-32B
Browse filesCo-authored-by: Shirong Ma <msr2000@users.noreply.huggingface.co>
- .gitattributes +35 -0
- LICENSE +21 -0
- README.md +239 -0
- config.json +27 -0
- figures/benchmark.jpg +0 -0
- generation_config.json +9 -0
- model-00001-of-000008.safetensors +3 -0
- model-00002-of-000008.safetensors +3 -0
- model-00003-of-000008.safetensors +3 -0
- model-00004-of-000008.safetensors +3 -0
- model-00005-of-000008.safetensors +3 -0
- model-00006-of-000008.safetensors +3 -0
- model-00007-of-000008.safetensors +3 -0
- model-00008-of-000008.safetensors +3 -0
- model.safetensors.index.json +778 -0
- tokenizer.json +0 -0
- tokenizer_config.json +35 -0
.gitattributes
ADDED
|
@@ -0,0 +1,35 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
*.7z filter=lfs diff=lfs merge=lfs -text
|
| 2 |
+
*.arrow filter=lfs diff=lfs merge=lfs -text
|
| 3 |
+
*.bin filter=lfs diff=lfs merge=lfs -text
|
| 4 |
+
*.bz2 filter=lfs diff=lfs merge=lfs -text
|
| 5 |
+
*.ckpt filter=lfs diff=lfs merge=lfs -text
|
| 6 |
+
*.ftz filter=lfs diff=lfs merge=lfs -text
|
| 7 |
+
*.gz filter=lfs diff=lfs merge=lfs -text
|
| 8 |
+
*.h5 filter=lfs diff=lfs merge=lfs -text
|
| 9 |
+
*.joblib filter=lfs diff=lfs merge=lfs -text
|
| 10 |
+
*.lfs.* filter=lfs diff=lfs merge=lfs -text
|
| 11 |
+
*.mlmodel filter=lfs diff=lfs merge=lfs -text
|
| 12 |
+
*.model filter=lfs diff=lfs merge=lfs -text
|
| 13 |
+
*.msgpack filter=lfs diff=lfs merge=lfs -text
|
| 14 |
+
*.npy filter=lfs diff=lfs merge=lfs -text
|
| 15 |
+
*.npz filter=lfs diff=lfs merge=lfs -text
|
| 16 |
+
*.onnx filter=lfs diff=lfs merge=lfs -text
|
| 17 |
+
*.ot filter=lfs diff=lfs merge=lfs -text
|
| 18 |
+
*.parquet filter=lfs diff=lfs merge=lfs -text
|
| 19 |
+
*.pb filter=lfs diff=lfs merge=lfs -text
|
| 20 |
+
*.pickle filter=lfs diff=lfs merge=lfs -text
|
| 21 |
+
*.pkl filter=lfs diff=lfs merge=lfs -text
|
| 22 |
+
*.pt filter=lfs diff=lfs merge=lfs -text
|
| 23 |
+
*.pth filter=lfs diff=lfs merge=lfs -text
|
| 24 |
+
*.rar filter=lfs diff=lfs merge=lfs -text
|
| 25 |
+
*.safetensors filter=lfs diff=lfs merge=lfs -text
|
| 26 |
+
saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
| 27 |
+
*.tar.* filter=lfs diff=lfs merge=lfs -text
|
| 28 |
+
*.tar filter=lfs diff=lfs merge=lfs -text
|
| 29 |
+
*.tflite filter=lfs diff=lfs merge=lfs -text
|
| 30 |
+
*.tgz filter=lfs diff=lfs merge=lfs -text
|
| 31 |
+
*.wasm filter=lfs diff=lfs merge=lfs -text
|
| 32 |
+
*.xz 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
|
LICENSE
ADDED
|
@@ -0,0 +1,21 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
MIT License
|
| 2 |
+
|
| 3 |
+
Copyright (c) 2023 DeepSeek
|
| 4 |
+
|
| 5 |
+
Permission is hereby granted, free of charge, to any person obtaining a copy
|
| 6 |
+
of this software and associated documentation files (the "Software"), to deal
|
| 7 |
+
in the Software without restriction, including without limitation the rights
|
| 8 |
+
to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
|
| 9 |
+
copies of the Software, and to permit persons to whom the Software is
|
| 10 |
+
furnished to do so, subject to the following conditions:
|
| 11 |
+
|
| 12 |
+
The above copyright notice and this permission notice shall be included in all
|
| 13 |
+
copies or substantial portions of the Software.
|
| 14 |
+
|
| 15 |
+
THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
|
| 16 |
+
IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
|
| 17 |
+
FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
|
| 18 |
+
AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
|
| 19 |
+
LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
|
| 20 |
+
OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
|
| 21 |
+
SOFTWARE.
|
README.md
ADDED
|
@@ -0,0 +1,239 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: mit
|
| 3 |
+
library_name: transformers
|
| 4 |
+
---
|
| 5 |
+
# DeepSeek-R1
|
| 6 |
+
<!-- markdownlint-disable first-line-h1 -->
|
| 7 |
+
<!-- markdownlint-disable html -->
|
| 8 |
+
<!-- markdownlint-disable no-duplicate-header -->
|
| 9 |
+
|
| 10 |
+
<div align="center">
|
| 11 |
+
<img src="https://github.com/deepseek-ai/DeepSeek-V2/blob/main/figures/logo.svg?raw=true" width="60%" alt="DeepSeek-V3" />
|
| 12 |
+
</div>
|
| 13 |
+
<hr>
|
| 14 |
+
<div align="center" style="line-height: 1;">
|
| 15 |
+
<a href="https://www.deepseek.com/" target="_blank" style="margin: 2px;">
|
| 16 |
+
<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;"/>
|
| 17 |
+
</a>
|
| 18 |
+
<a href="https://chat.deepseek.com/" target="_blank" style="margin: 2px;">
|
| 19 |
+
<img alt="Chat" src="https://img.shields.io/badge/🤖%20Chat-DeepSeek%20R1-536af5?color=536af5&logoColor=white" style="display: inline-block; vertical-align: middle;"/>
|
| 20 |
+
</a>
|
| 21 |
+
<a href="https://huggingface.co/deepseek-ai" target="_blank" style="margin: 2px;">
|
| 22 |
+
<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;"/>
|
| 23 |
+
</a>
|
| 24 |
+
</div>
|
| 25 |
+
|
| 26 |
+
<div align="center" style="line-height: 1;">
|
| 27 |
+
<a href="https://discord.gg/Tc7c45Zzu5" target="_blank" style="margin: 2px;">
|
| 28 |
+
<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;"/>
|
| 29 |
+
</a>
|
| 30 |
+
<a href="https://github.com/deepseek-ai/DeepSeek-V2/blob/main/figures/qr.jpeg?raw=true" target="_blank" style="margin: 2px;">
|
| 31 |
+
<img alt="Wechat" src="https://img.shields.io/badge/WeChat-DeepSeek%20AI-brightgreen?logo=wechat&logoColor=white" style="display: inline-block; vertical-align: middle;"/>
|
| 32 |
+
</a>
|
| 33 |
+
<a href="https://twitter.com/deepseek_ai" target="_blank" style="margin: 2px;">
|
| 34 |
+
<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;"/>
|
| 35 |
+
</a>
|
| 36 |
+
</div>
|
| 37 |
+
|
| 38 |
+
<div align="center" style="line-height: 1;">
|
| 39 |
+
<a href="https://github.com/deepseek-ai/DeepSeek-R1/blob/main/LICENSE" style="margin: 2px;">
|
| 40 |
+
<img alt="License" src="https://img.shields.io/badge/License-MIT-f5de53?&color=f5de53" style="display: inline-block; vertical-align: middle;"/>
|
| 41 |
+
</a>
|
| 42 |
+
</div>
|
| 43 |
+
|
| 44 |
+
|
| 45 |
+
<p align="center">
|
| 46 |
+
<a href="https://github.com/deepseek-ai/DeepSeek-R1/blob/main/DeepSeek_R1.pdf"><b>Paper Link</b>👁️</a>
|
| 47 |
+
</p>
|
| 48 |
+
|
| 49 |
+
|
| 50 |
+
## 1. Introduction
|
| 51 |
+
|
| 52 |
+
We introduce our first-generation reasoning models, DeepSeek-R1-Zero and DeepSeek-R1.
|
| 53 |
+
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.
|
| 54 |
+
With RL, DeepSeek-R1-Zero naturally emerged with numerous powerful and interesting reasoning behaviors.
|
| 55 |
+
However, DeepSeek-R1-Zero encounters challenges such as endless repetition, poor readability, and language mixing. To address these issues and further enhance reasoning performance,
|
| 56 |
+
we introduce DeepSeek-R1, which incorporates cold-start data before RL.
|
| 57 |
+
DeepSeek-R1 achieves performance comparable to OpenAI-o1 across math, code, and reasoning tasks.
|
| 58 |
+
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.
|
| 59 |
+
|
| 60 |
+
**NOTE: Before running DeepSeek-R1 series models locally, we kindly recommend reviewing the [Usage Recommendation](#usage-recommendations) section.**
|
| 61 |
+
|
| 62 |
+
<p align="center">
|
| 63 |
+
<img width="80%" src="figures/benchmark.jpg">
|
| 64 |
+
</p>
|
| 65 |
+
|
| 66 |
+
## 2. Model Summary
|
| 67 |
+
|
| 68 |
+
---
|
| 69 |
+
|
| 70 |
+
**Post-Training: Large-Scale Reinforcement Learning on the Base Model**
|
| 71 |
+
|
| 72 |
+
- 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.
|
| 73 |
+
|
| 74 |
+
- 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.
|
| 75 |
+
We believe the pipeline will benefit the industry by creating better models.
|
| 76 |
+
|
| 77 |
+
---
|
| 78 |
+
|
| 79 |
+
**Distillation: Smaller Models Can Be Powerful Too**
|
| 80 |
+
|
| 81 |
+
- 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.
|
| 82 |
+
- 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.
|
| 83 |
+
|
| 84 |
+
## 3. Model Downloads
|
| 85 |
+
|
| 86 |
+
### DeepSeek-R1 Models
|
| 87 |
+
|
| 88 |
+
<div align="center">
|
| 89 |
+
|
| 90 |
+
| **Model** | **#Total Params** | **#Activated Params** | **Context Length** | **Download** |
|
| 91 |
+
| :------------: | :------------: | :------------: | :------------: | :------------: |
|
| 92 |
+
| DeepSeek-R1-Zero | 671B | 37B | 128K | [🤗 HuggingFace](https://huggingface.co/deepseek-ai/DeepSeek-R1-Zero) |
|
| 93 |
+
| DeepSeek-R1 | 671B | 37B | 128K | [🤗 HuggingFace](https://huggingface.co/deepseek-ai/DeepSeek-R1) |
|
| 94 |
+
|
| 95 |
+
</div>
|
| 96 |
+
|
| 97 |
+
DeepSeek-R1-Zero & DeepSeek-R1 are trained based on DeepSeek-V3-Base.
|
| 98 |
+
For more details regarding the model architecture, please refer to [DeepSeek-V3](https://github.com/deepseek-ai/DeepSeek-V3) repository.
|
| 99 |
+
|
| 100 |
+
### DeepSeek-R1-Distill Models
|
| 101 |
+
|
| 102 |
+
<div align="center">
|
| 103 |
+
|
| 104 |
+
| **Model** | **Base Model** | **Download** |
|
| 105 |
+
| :------------: | :------------: | :------------: |
|
| 106 |
+
| 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) |
|
| 107 |
+
| 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) |
|
| 108 |
+
| 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) |
|
| 109 |
+
| 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) |
|
| 110 |
+
|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) |
|
| 111 |
+
| 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) |
|
| 112 |
+
|
| 113 |
+
</div>
|
| 114 |
+
|
| 115 |
+
DeepSeek-R1-Distill models are fine-tuned based on open-source models, using samples generated by DeepSeek-R1.
|
| 116 |
+
We slightly change their configs and tokenizers. Please use our setting to run these models.
|
| 117 |
+
|
| 118 |
+
## 4. Evaluation Results
|
| 119 |
+
|
| 120 |
+
### DeepSeek-R1-Evaluation
|
| 121 |
+
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.
|
| 122 |
+
<div align="center">
|
| 123 |
+
|
| 124 |
+
|
| 125 |
+
| Category | Benchmark (Metric) | Claude-3.5-Sonnet-1022 | GPT-4o 0513 | DeepSeek V3 | OpenAI o1-mini | OpenAI o1-1217 | DeepSeek R1 |
|
| 126 |
+
|----------|-------------------|----------------------|------------|--------------|----------------|------------|--------------|
|
| 127 |
+
| | Architecture | - | - | MoE | - | - | MoE |
|
| 128 |
+
| | # Activated Params | - | - | 37B | - | - | 37B |
|
| 129 |
+
| | # Total Params | - | - | 671B | - | - | 671B |
|
| 130 |
+
| English | MMLU (Pass@1) | 88.3 | 87.2 | 88.5 | 85.2 | **91.8** | 90.8 |
|
| 131 |
+
| | MMLU-Redux (EM) | 88.9 | 88.0 | 89.1 | 86.7 | - | **92.9** |
|
| 132 |
+
| | MMLU-Pro (EM) | 78.0 | 72.6 | 75.9 | 80.3 | - | **84.0** |
|
| 133 |
+
| | DROP (3-shot F1) | 88.3 | 83.7 | 91.6 | 83.9 | 90.2 | **92.2** |
|
| 134 |
+
| | IF-Eval (Prompt Strict) | **86.5** | 84.3 | 86.1 | 84.8 | - | 83.3 |
|
| 135 |
+
| | GPQA-Diamond (Pass@1) | 65.0 | 49.9 | 59.1 | 60.0 | **75.7** | 71.5 |
|
| 136 |
+
| | SimpleQA (Correct) | 28.4 | 38.2 | 24.9 | 7.0 | **47.0** | 30.1 |
|
| 137 |
+
| | FRAMES (Acc.) | 72.5 | 80.5 | 73.3 | 76.9 | - | **82.5** |
|
| 138 |
+
| | AlpacaEval2.0 (LC-winrate) | 52.0 | 51.1 | 70.0 | 57.8 | - | **87.6** |
|
| 139 |
+
| | ArenaHard (GPT-4-1106) | 85.2 | 80.4 | 85.5 | 92.0 | - | **92.3** |
|
| 140 |
+
| Code | LiveCodeBench (Pass@1-COT) | 33.8 | 34.2 | - | 53.8 | 63.4 | **65.9** |
|
| 141 |
+
| | Codeforces (Percentile) | 20.3 | 23.6 | 58.7 | 93.4 | **96.6** | 96.3 |
|
| 142 |
+
| | Codeforces (Rating) | 717 | 759 | 1134 | 1820 | **2061** | 2029 |
|
| 143 |
+
| | SWE Verified (Resolved) | **50.8** | 38.8 | 42.0 | 41.6 | 48.9 | 49.2 |
|
| 144 |
+
| | Aider-Polyglot (Acc.) | 45.3 | 16.0 | 49.6 | 32.9 | **61.7** | 53.3 |
|
| 145 |
+
| Math | AIME 2024 (Pass@1) | 16.0 | 9.3 | 39.2 | 63.6 | 79.2 | **79.8** |
|
| 146 |
+
| | MATH-500 (Pass@1) | 78.3 | 74.6 | 90.2 | 90.0 | 96.4 | **97.3** |
|
| 147 |
+
| | CNMO 2024 (Pass@1) | 13.1 | 10.8 | 43.2 | 67.6 | - | **78.8** |
|
| 148 |
+
| Chinese | CLUEWSC (EM) | 85.4 | 87.9 | 90.9 | 89.9 | - | **92.8** |
|
| 149 |
+
| | C-Eval (EM) | 76.7 | 76.0 | 86.5 | 68.9 | - | **91.8** |
|
| 150 |
+
| | C-SimpleQA (Correct) | 55.4 | 58.7 | **68.0** | 40.3 | - | 63.7 |
|
| 151 |
+
|
| 152 |
+
</div>
|
| 153 |
+
|
| 154 |
+
|
| 155 |
+
### Distilled Model Evaluation
|
| 156 |
+
|
| 157 |
+
|
| 158 |
+
<div align="center">
|
| 159 |
+
|
| 160 |
+
| Model | AIME 2024 pass@1 | AIME 2024 cons@64 | MATH-500 pass@1 | GPQA Diamond pass@1 | LiveCodeBench pass@1 | CodeForces rating |
|
| 161 |
+
|------------------------------------------|------------------|-------------------|-----------------|----------------------|----------------------|-------------------|
|
| 162 |
+
| GPT-4o-0513 | 9.3 | 13.4 | 74.6 | 49.9 | 32.9 | 759 |
|
| 163 |
+
| Claude-3.5-Sonnet-1022 | 16.0 | 26.7 | 78.3 | 65.0 | 38.9 | 717 |
|
| 164 |
+
| o1-mini | 63.6 | 80.0 | 90.0 | 60.0 | 53.8 | **1820** |
|
| 165 |
+
| QwQ-32B-Preview | 44.0 | 60.0 | 90.6 | 54.5 | 41.9 | 1316 |
|
| 166 |
+
| DeepSeek-R1-Distill-Qwen-1.5B | 28.9 | 52.7 | 83.9 | 33.8 | 16.9 | 954 |
|
| 167 |
+
| DeepSeek-R1-Distill-Qwen-7B | 55.5 | 83.3 | 92.8 | 49.1 | 37.6 | 1189 |
|
| 168 |
+
| DeepSeek-R1-Distill-Qwen-14B | 69.7 | 80.0 | 93.9 | 59.1 | 53.1 | 1481 |
|
| 169 |
+
| DeepSeek-R1-Distill-Qwen-32B | **72.6** | 83.3 | 94.3 | 62.1 | 57.2 | 1691 |
|
| 170 |
+
| DeepSeek-R1-Distill-Llama-8B | 50.4 | 80.0 | 89.1 | 49.0 | 39.6 | 1205 |
|
| 171 |
+
| DeepSeek-R1-Distill-Llama-70B | 70.0 | **86.7** | **94.5** | **65.2** | **57.5** | 1633 |
|
| 172 |
+
|
| 173 |
+
</div>
|
| 174 |
+
|
| 175 |
+
|
| 176 |
+
## 5. Chat Website & API Platform
|
| 177 |
+
You can chat with DeepSeek-R1 on DeepSeek's official website: [chat.deepseek.com](https://chat.deepseek.com), and switch on the button "DeepThink"
|
| 178 |
+
|
| 179 |
+
We also provide OpenAI-Compatible API at DeepSeek Platform: [platform.deepseek.com](https://platform.deepseek.com/)
|
| 180 |
+
|
| 181 |
+
## 6. How to Run Locally
|
| 182 |
+
|
| 183 |
+
### DeepSeek-R1 Models
|
| 184 |
+
|
| 185 |
+
Please visit [DeepSeek-V3](https://github.com/deepseek-ai/DeepSeek-V3) repo for more information about running DeepSeek-R1 locally.
|
| 186 |
+
|
| 187 |
+
**NOTE: Hugging Face's Transformers has not been directly supported yet.**
|
| 188 |
+
|
| 189 |
+
### DeepSeek-R1-Distill Models
|
| 190 |
+
|
| 191 |
+
DeepSeek-R1-Distill models can be utilized in the same manner as Qwen or Llama models.
|
| 192 |
+
|
| 193 |
+
For instance, you can easily start a service using [vLLM](https://github.com/vllm-project/vllm):
|
| 194 |
+
|
| 195 |
+
```shell
|
| 196 |
+
vllm serve deepseek-ai/DeepSeek-R1-Distill-Qwen-32B --tensor-parallel-size 2 --max-model-len 32768 --enforce-eager
|
| 197 |
+
```
|
| 198 |
+
|
| 199 |
+
You can also easily start a service using [SGLang](https://github.com/sgl-project/sglang)
|
| 200 |
+
|
| 201 |
+
```bash
|
| 202 |
+
python3 -m sglang.launch_server --model deepseek-ai/DeepSeek-R1-Distill-Qwen-32B --trust-remote-code --tp 2
|
| 203 |
+
```
|
| 204 |
+
|
| 205 |
+
### Usage Recommendations
|
| 206 |
+
|
| 207 |
+
**We recommend adhering to the following configurations when utilizing the DeepSeek-R1 series models, including benchmarking, to achieve the expected performance:**
|
| 208 |
+
|
| 209 |
+
1. Set the temperature within the range of 0.5-0.7 (0.6 is recommended) to prevent endless repetitions or incoherent outputs.
|
| 210 |
+
2. **Avoid adding a system prompt; all instructions should be contained within the user prompt.**
|
| 211 |
+
3. For mathematical problems, it is advisable to include a directive in your prompt such as: "Please reason step by step, and put your final answer within \boxed{}."
|
| 212 |
+
4. When evaluating model performance, it is recommended to conduct multiple tests and average the results.
|
| 213 |
+
|
| 214 |
+
Additionally, we have observed that the DeepSeek-R1 series models tend to bypass thinking pattern (i.e., outputting "\<think\>\n\n\</think\>") when responding to certain queries, which can adversely affect the model's performance.
|
| 215 |
+
**To ensure that the model engages in thorough reasoning, we recommend enforcing the model to initiate its response with "\<think\>\n" at the beginning of every output.**
|
| 216 |
+
|
| 217 |
+
## 7. License
|
| 218 |
+
This code repository and the model weights are licensed under the [MIT License](https://github.com/deepseek-ai/DeepSeek-R1/blob/main/LICENSE).
|
| 219 |
+
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:
|
| 220 |
+
- 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.
|
| 221 |
+
- 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).
|
| 222 |
+
- 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).
|
| 223 |
+
|
| 224 |
+
## 8. Citation
|
| 225 |
+
```
|
| 226 |
+
@misc{deepseekai2025deepseekr1incentivizingreasoningcapability,
|
| 227 |
+
title={DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning},
|
| 228 |
+
author={DeepSeek-AI},
|
| 229 |
+
year={2025},
|
| 230 |
+
eprint={2501.12948},
|
| 231 |
+
archivePrefix={arXiv},
|
| 232 |
+
primaryClass={cs.CL},
|
| 233 |
+
url={https://arxiv.org/abs/2501.12948},
|
| 234 |
+
}
|
| 235 |
+
|
| 236 |
+
```
|
| 237 |
+
|
| 238 |
+
## 9. Contact
|
| 239 |
+
If you have any questions, please raise an issue or contact us at [service@deepseek.com](service@deepseek.com).
|
config.json
ADDED
|
@@ -0,0 +1,27 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"Qwen2ForCausalLM"
|
| 4 |
+
],
|
| 5 |
+
"attention_dropout": 0.0,
|
| 6 |
+
"bos_token_id": 151643,
|
| 7 |
+
"eos_token_id": 151643,
|
| 8 |
+
"hidden_act": "silu",
|
| 9 |
+
"hidden_size": 5120,
|
| 10 |
+
"initializer_range": 0.02,
|
| 11 |
+
"intermediate_size": 27648,
|
| 12 |
+
"max_position_embeddings": 131072,
|
| 13 |
+
"max_window_layers": 64,
|
| 14 |
+
"model_type": "qwen2",
|
| 15 |
+
"num_attention_heads": 40,
|
| 16 |
+
"num_hidden_layers": 64,
|
| 17 |
+
"num_key_value_heads": 8,
|
| 18 |
+
"rms_norm_eps": 1e-05,
|
| 19 |
+
"rope_theta": 1000000.0,
|
| 20 |
+
"sliding_window": 131072,
|
| 21 |
+
"tie_word_embeddings": false,
|
| 22 |
+
"torch_dtype": "bfloat16",
|
| 23 |
+
"transformers_version": "4.43.1",
|
| 24 |
+
"use_cache": true,
|
| 25 |
+
"use_sliding_window": false,
|
| 26 |
+
"vocab_size": 152064
|
| 27 |
+
}
|
figures/benchmark.jpg
ADDED
|
generation_config.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 151646,
|
| 4 |
+
"eos_token_id": 151643,
|
| 5 |
+
"do_sample": true,
|
| 6 |
+
"temperature": 0.6,
|
| 7 |
+
"top_p": 0.95,
|
| 8 |
+
"transformers_version": "4.39.3"
|
| 9 |
+
}
|
model-00001-of-000008.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:52addd84f7e83b6f5b54edfbcd11a9dc71ced13e63967e0e551fcdd071a09cac
|
| 3 |
+
size 8792578462
|
model-00002-of-000008.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7401ea9ee01963efcae3bc43c34b17546236e30abfb356541e56df7ab2872d9a
|
| 3 |
+
size 8776906899
|
model-00003-of-000008.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:38b7e1968565c4334bae24082c262a337838d6520b590d4d0c3806df060d7a26
|
| 3 |
+
size 8776906927
|
model-00004-of-000008.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:88f4a70419dc6c41779a88416baa0f4bad155e30c23dd8e90502bd98a32c9a49
|
| 3 |
+
size 8776906927
|
model-00005-of-000008.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:45aee647ad5c930eb73896d507f0694b14218616cbe14b3f499eaab0eb5f1558
|
| 3 |
+
size 8776906927
|
model-00006-of-000008.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bc3c1a143d5b7144a6cf58a1de95981562fe27354edb7bda87433b8da869740e
|
| 3 |
+
size 8776906927
|
model-00007-of-000008.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bb06d0ea82ab4a42820683158375e979a72bf3e88ebf0eb52080f4dabd9e54b6
|
| 3 |
+
size 8776906927
|
model-00008-of-000008.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1a6b6f41ddd7d1c07d4fdb9a626f66cb9a0fb3138c7d1116fc528255c6bb2b2b
|
| 3 |
+
size 4073821536
|
model.safetensors.index.json
ADDED
|
@@ -0,0 +1,778 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"metadata": {
|
| 3 |
+
"total_size": 65527752704
|
| 4 |
+
},
|
| 5 |
+
"weight_map": {
|
| 6 |
+
"model.embed_tokens.weight": "model-00001-of-000008.safetensors",
|
| 7 |
+
"model.layers.0.self_attn.q_proj.bias": "model-00001-of-000008.safetensors",
|
| 8 |
+
"model.layers.0.self_attn.k_proj.bias": "model-00001-of-000008.safetensors",
|
| 9 |
+
"model.layers.0.self_attn.v_proj.bias": "model-00001-of-000008.safetensors",
|
| 10 |
+
"model.layers.0.self_attn.q_proj.weight": "model-00001-of-000008.safetensors",
|
| 11 |
+
"model.layers.0.self_attn.k_proj.weight": "model-00001-of-000008.safetensors",
|
| 12 |
+
"model.layers.0.self_attn.v_proj.weight": "model-00001-of-000008.safetensors",
|
| 13 |
+
"model.layers.0.self_attn.o_proj.weight": "model-00001-of-000008.safetensors",
|
| 14 |
+
"model.layers.0.mlp.gate_proj.weight": "model-00001-of-000008.safetensors",
|
| 15 |
+
"model.layers.0.mlp.up_proj.weight": "model-00001-of-000008.safetensors",
|
| 16 |
+
"model.layers.0.mlp.down_proj.weight": "model-00001-of-000008.safetensors",
|
| 17 |
+
"model.layers.0.input_layernorm.weight": "model-00001-of-000008.safetensors",
|
| 18 |
+
"model.layers.0.post_attention_layernorm.weight": "model-00001-of-000008.safetensors",
|
| 19 |
+
"model.layers.1.self_attn.q_proj.bias": "model-00001-of-000008.safetensors",
|
| 20 |
+
"model.layers.1.self_attn.k_proj.bias": "model-00001-of-000008.safetensors",
|
| 21 |
+
"model.layers.1.self_attn.v_proj.bias": "model-00001-of-000008.safetensors",
|
| 22 |
+
"model.layers.1.self_attn.q_proj.weight": "model-00001-of-000008.safetensors",
|
| 23 |
+
"model.layers.1.self_attn.k_proj.weight": "model-00001-of-000008.safetensors",
|
| 24 |
+
"model.layers.1.self_attn.v_proj.weight": "model-00001-of-000008.safetensors",
|
| 25 |
+
"model.layers.1.self_attn.o_proj.weight": "model-00001-of-000008.safetensors",
|
| 26 |
+
"model.layers.1.mlp.gate_proj.weight": "model-00001-of-000008.safetensors",
|
| 27 |
+
"model.layers.1.mlp.up_proj.weight": "model-00001-of-000008.safetensors",
|
| 28 |
+
"model.layers.1.mlp.down_proj.weight": "model-00001-of-000008.safetensors",
|
| 29 |
+
"model.layers.1.input_layernorm.weight": "model-00001-of-000008.safetensors",
|
| 30 |
+
"model.layers.1.post_attention_layernorm.weight": "model-00001-of-000008.safetensors",
|
| 31 |
+
"model.layers.2.self_attn.q_proj.bias": "model-00001-of-000008.safetensors",
|
| 32 |
+
"model.layers.2.self_attn.k_proj.bias": "model-00001-of-000008.safetensors",
|
| 33 |
+
"model.layers.2.self_attn.v_proj.bias": "model-00001-of-000008.safetensors",
|
| 34 |
+
"model.layers.2.self_attn.q_proj.weight": "model-00001-of-000008.safetensors",
|
| 35 |
+
"model.layers.2.self_attn.k_proj.weight": "model-00001-of-000008.safetensors",
|
| 36 |
+
"model.layers.2.self_attn.v_proj.weight": "model-00001-of-000008.safetensors",
|
| 37 |
+
"model.layers.2.self_attn.o_proj.weight": "model-00001-of-000008.safetensors",
|
| 38 |
+
"model.layers.2.mlp.gate_proj.weight": "model-00001-of-000008.safetensors",
|
| 39 |
+
"model.layers.2.mlp.up_proj.weight": "model-00001-of-000008.safetensors",
|
| 40 |
+
"model.layers.2.mlp.down_proj.weight": "model-00001-of-000008.safetensors",
|
| 41 |
+
"model.layers.2.input_layernorm.weight": "model-00001-of-000008.safetensors",
|
| 42 |
+
"model.layers.2.post_attention_layernorm.weight": "model-00001-of-000008.safetensors",
|
| 43 |
+
"model.layers.3.self_attn.q_proj.bias": "model-00001-of-000008.safetensors",
|
| 44 |
+
"model.layers.3.self_attn.k_proj.bias": "model-00001-of-000008.safetensors",
|
| 45 |
+
"model.layers.3.self_attn.v_proj.bias": "model-00001-of-000008.safetensors",
|
| 46 |
+
"model.layers.3.self_attn.q_proj.weight": "model-00001-of-000008.safetensors",
|
| 47 |
+
"model.layers.3.self_attn.k_proj.weight": "model-00001-of-000008.safetensors",
|
| 48 |
+
"model.layers.3.self_attn.v_proj.weight": "model-00001-of-000008.safetensors",
|
| 49 |
+
"model.layers.3.self_attn.o_proj.weight": "model-00001-of-000008.safetensors",
|
| 50 |
+
"model.layers.3.mlp.gate_proj.weight": "model-00001-of-000008.safetensors",
|
| 51 |
+
"model.layers.3.mlp.up_proj.weight": "model-00001-of-000008.safetensors",
|
| 52 |
+
"model.layers.3.mlp.down_proj.weight": "model-00001-of-000008.safetensors",
|
| 53 |
+
"model.layers.3.input_layernorm.weight": "model-00001-of-000008.safetensors",
|
| 54 |
+
"model.layers.3.post_attention_layernorm.weight": "model-00001-of-000008.safetensors",
|
| 55 |
+
"model.layers.4.self_attn.q_proj.bias": "model-00001-of-000008.safetensors",
|
| 56 |
+
"model.layers.4.self_attn.k_proj.bias": "model-00001-of-000008.safetensors",
|
| 57 |
+
"model.layers.4.self_attn.v_proj.bias": "model-00001-of-000008.safetensors",
|
| 58 |
+
"model.layers.4.self_attn.q_proj.weight": "model-00001-of-000008.safetensors",
|
| 59 |
+
"model.layers.4.self_attn.k_proj.weight": "model-00001-of-000008.safetensors",
|
| 60 |
+
"model.layers.4.self_attn.v_proj.weight": "model-00001-of-000008.safetensors",
|
| 61 |
+
"model.layers.4.self_attn.o_proj.weight": "model-00001-of-000008.safetensors",
|
| 62 |
+
"model.layers.4.mlp.gate_proj.weight": "model-00001-of-000008.safetensors",
|
| 63 |
+
"model.layers.4.mlp.up_proj.weight": "model-00001-of-000008.safetensors",
|
| 64 |
+
"model.layers.4.mlp.down_proj.weight": "model-00001-of-000008.safetensors",
|
| 65 |
+
"model.layers.4.input_layernorm.weight": "model-00001-of-000008.safetensors",
|
| 66 |
+
"model.layers.4.post_attention_layernorm.weight": "model-00001-of-000008.safetensors",
|
| 67 |
+
"model.layers.5.self_attn.q_proj.bias": "model-00001-of-000008.safetensors",
|
| 68 |
+
"model.layers.5.self_attn.k_proj.bias": "model-00001-of-000008.safetensors",
|
| 69 |
+
"model.layers.5.self_attn.v_proj.bias": "model-00001-of-000008.safetensors",
|
| 70 |
+
"model.layers.5.self_attn.q_proj.weight": "model-00001-of-000008.safetensors",
|
| 71 |
+
"model.layers.5.self_attn.k_proj.weight": "model-00001-of-000008.safetensors",
|
| 72 |
+
"model.layers.5.self_attn.v_proj.weight": "model-00001-of-000008.safetensors",
|
| 73 |
+
"model.layers.5.self_attn.o_proj.weight": "model-00001-of-000008.safetensors",
|
| 74 |
+
"model.layers.5.mlp.gate_proj.weight": "model-00001-of-000008.safetensors",
|
| 75 |
+
"model.layers.5.mlp.up_proj.weight": "model-00001-of-000008.safetensors",
|
| 76 |
+
"model.layers.5.mlp.down_proj.weight": "model-00001-of-000008.safetensors",
|
| 77 |
+
"model.layers.5.input_layernorm.weight": "model-00001-of-000008.safetensors",
|
| 78 |
+
"model.layers.5.post_attention_layernorm.weight": "model-00001-of-000008.safetensors",
|
| 79 |
+
"model.layers.6.self_attn.q_proj.bias": "model-00001-of-000008.safetensors",
|
| 80 |
+
"model.layers.6.self_attn.k_proj.bias": "model-00001-of-000008.safetensors",
|
| 81 |
+
"model.layers.6.self_attn.v_proj.bias": "model-00001-of-000008.safetensors",
|
| 82 |
+
"model.layers.6.self_attn.q_proj.weight": "model-00001-of-000008.safetensors",
|
| 83 |
+
"model.layers.6.self_attn.k_proj.weight": "model-00001-of-000008.safetensors",
|
| 84 |
+
"model.layers.6.self_attn.v_proj.weight": "model-00001-of-000008.safetensors",
|
| 85 |
+
"model.layers.6.self_attn.o_proj.weight": "model-00001-of-000008.safetensors",
|
| 86 |
+
"model.layers.6.mlp.gate_proj.weight": "model-00001-of-000008.safetensors",
|
| 87 |
+
"model.layers.6.mlp.up_proj.weight": "model-00001-of-000008.safetensors",
|
| 88 |
+
"model.layers.6.mlp.down_proj.weight": "model-00001-of-000008.safetensors",
|
| 89 |
+
"model.layers.6.input_layernorm.weight": "model-00001-of-000008.safetensors",
|
| 90 |
+
"model.layers.6.post_attention_layernorm.weight": "model-00001-of-000008.safetensors",
|
| 91 |
+
"model.layers.7.self_attn.q_proj.bias": "model-00001-of-000008.safetensors",
|
| 92 |
+
"model.layers.7.self_attn.k_proj.bias": "model-00001-of-000008.safetensors",
|
| 93 |
+
"model.layers.7.self_attn.v_proj.bias": "model-00001-of-000008.safetensors",
|
| 94 |
+
"model.layers.7.self_attn.q_proj.weight": "model-00001-of-000008.safetensors",
|
| 95 |
+
"model.layers.7.self_attn.k_proj.weight": "model-00001-of-000008.safetensors",
|
| 96 |
+
"model.layers.7.self_attn.v_proj.weight": "model-00001-of-000008.safetensors",
|
| 97 |
+
"model.layers.7.self_attn.o_proj.weight": "model-00001-of-000008.safetensors",
|
| 98 |
+
"model.layers.7.mlp.gate_proj.weight": "model-00001-of-000008.safetensors",
|
| 99 |
+
"model.layers.7.mlp.up_proj.weight": "model-00002-of-000008.safetensors",
|
| 100 |
+
"model.layers.7.mlp.down_proj.weight": "model-00002-of-000008.safetensors",
|
| 101 |
+
"model.layers.7.input_layernorm.weight": "model-00002-of-000008.safetensors",
|
| 102 |
+
"model.layers.7.post_attention_layernorm.weight": "model-00002-of-000008.safetensors",
|
| 103 |
+
"model.layers.8.self_attn.q_proj.bias": "model-00002-of-000008.safetensors",
|
| 104 |
+
"model.layers.8.self_attn.k_proj.bias": "model-00002-of-000008.safetensors",
|
| 105 |
+
"model.layers.8.self_attn.v_proj.bias": "model-00002-of-000008.safetensors",
|
| 106 |
+
"model.layers.8.self_attn.q_proj.weight": "model-00002-of-000008.safetensors",
|
| 107 |
+
"model.layers.8.self_attn.k_proj.weight": "model-00002-of-000008.safetensors",
|
| 108 |
+
"model.layers.8.self_attn.v_proj.weight": "model-00002-of-000008.safetensors",
|
| 109 |
+
"model.layers.8.self_attn.o_proj.weight": "model-00002-of-000008.safetensors",
|
| 110 |
+
"model.layers.8.mlp.gate_proj.weight": "model-00002-of-000008.safetensors",
|
| 111 |
+
"model.layers.8.mlp.up_proj.weight": "model-00002-of-000008.safetensors",
|
| 112 |
+
"model.layers.8.mlp.down_proj.weight": "model-00002-of-000008.safetensors",
|
| 113 |
+
"model.layers.8.input_layernorm.weight": "model-00002-of-000008.safetensors",
|
| 114 |
+
"model.layers.8.post_attention_layernorm.weight": "model-00002-of-000008.safetensors",
|
| 115 |
+
"model.layers.9.self_attn.q_proj.bias": "model-00002-of-000008.safetensors",
|
| 116 |
+
"model.layers.9.self_attn.k_proj.bias": "model-00002-of-000008.safetensors",
|
| 117 |
+
"model.layers.9.self_attn.v_proj.bias": "model-00002-of-000008.safetensors",
|
| 118 |
+
"model.layers.9.self_attn.q_proj.weight": "model-00002-of-000008.safetensors",
|
| 119 |
+
"model.layers.9.self_attn.k_proj.weight": "model-00002-of-000008.safetensors",
|
| 120 |
+
"model.layers.9.self_attn.v_proj.weight": "model-00002-of-000008.safetensors",
|
| 121 |
+
"model.layers.9.self_attn.o_proj.weight": "model-00002-of-000008.safetensors",
|
| 122 |
+
"model.layers.9.mlp.gate_proj.weight": "model-00002-of-000008.safetensors",
|
| 123 |
+
"model.layers.9.mlp.up_proj.weight": "model-00002-of-000008.safetensors",
|
| 124 |
+
"model.layers.9.mlp.down_proj.weight": "model-00002-of-000008.safetensors",
|
| 125 |
+
"model.layers.9.input_layernorm.weight": "model-00002-of-000008.safetensors",
|
| 126 |
+
"model.layers.9.post_attention_layernorm.weight": "model-00002-of-000008.safetensors",
|
| 127 |
+
"model.layers.10.self_attn.q_proj.bias": "model-00002-of-000008.safetensors",
|
| 128 |
+
"model.layers.10.self_attn.k_proj.bias": "model-00002-of-000008.safetensors",
|
| 129 |
+
"model.layers.10.self_attn.v_proj.bias": "model-00002-of-000008.safetensors",
|
| 130 |
+
"model.layers.10.self_attn.q_proj.weight": "model-00002-of-000008.safetensors",
|
| 131 |
+
"model.layers.10.self_attn.k_proj.weight": "model-00002-of-000008.safetensors",
|
| 132 |
+
"model.layers.10.self_attn.v_proj.weight": "model-00002-of-000008.safetensors",
|
| 133 |
+
"model.layers.10.self_attn.o_proj.weight": "model-00002-of-000008.safetensors",
|
| 134 |
+
"model.layers.10.mlp.gate_proj.weight": "model-00002-of-000008.safetensors",
|
| 135 |
+
"model.layers.10.mlp.up_proj.weight": "model-00002-of-000008.safetensors",
|
| 136 |
+
"model.layers.10.mlp.down_proj.weight": "model-00002-of-000008.safetensors",
|
| 137 |
+
"model.layers.10.input_layernorm.weight": "model-00002-of-000008.safetensors",
|
| 138 |
+
"model.layers.10.post_attention_layernorm.weight": "model-00002-of-000008.safetensors",
|
| 139 |
+
"model.layers.11.self_attn.q_proj.bias": "model-00002-of-000008.safetensors",
|
| 140 |
+
"model.layers.11.self_attn.k_proj.bias": "model-00002-of-000008.safetensors",
|
| 141 |
+
"model.layers.11.self_attn.v_proj.bias": "model-00002-of-000008.safetensors",
|
| 142 |
+
"model.layers.11.self_attn.q_proj.weight": "model-00002-of-000008.safetensors",
|
| 143 |
+
"model.layers.11.self_attn.k_proj.weight": "model-00002-of-000008.safetensors",
|
| 144 |
+
"model.layers.11.self_attn.v_proj.weight": "model-00002-of-000008.safetensors",
|
| 145 |
+
"model.layers.11.self_attn.o_proj.weight": "model-00002-of-000008.safetensors",
|
| 146 |
+
"model.layers.11.mlp.gate_proj.weight": "model-00002-of-000008.safetensors",
|
| 147 |
+
"model.layers.11.mlp.up_proj.weight": "model-00002-of-000008.safetensors",
|
| 148 |
+
"model.layers.11.mlp.down_proj.weight": "model-00002-of-000008.safetensors",
|
| 149 |
+
"model.layers.11.input_layernorm.weight": "model-00002-of-000008.safetensors",
|
| 150 |
+
"model.layers.11.post_attention_layernorm.weight": "model-00002-of-000008.safetensors",
|
| 151 |
+
"model.layers.12.self_attn.q_proj.bias": "model-00002-of-000008.safetensors",
|
| 152 |
+
"model.layers.12.self_attn.k_proj.bias": "model-00002-of-000008.safetensors",
|
| 153 |
+
"model.layers.12.self_attn.v_proj.bias": "model-00002-of-000008.safetensors",
|
| 154 |
+
"model.layers.12.self_attn.q_proj.weight": "model-00002-of-000008.safetensors",
|
| 155 |
+
"model.layers.12.self_attn.k_proj.weight": "model-00002-of-000008.safetensors",
|
| 156 |
+
"model.layers.12.self_attn.v_proj.weight": "model-00002-of-000008.safetensors",
|
| 157 |
+
"model.layers.12.self_attn.o_proj.weight": "model-00002-of-000008.safetensors",
|
| 158 |
+
"model.layers.12.mlp.gate_proj.weight": "model-00002-of-000008.safetensors",
|
| 159 |
+
"model.layers.12.mlp.up_proj.weight": "model-00002-of-000008.safetensors",
|
| 160 |
+
"model.layers.12.mlp.down_proj.weight": "model-00002-of-000008.safetensors",
|
| 161 |
+
"model.layers.12.input_layernorm.weight": "model-00002-of-000008.safetensors",
|
| 162 |
+
"model.layers.12.post_attention_layernorm.weight": "model-00002-of-000008.safetensors",
|
| 163 |
+
"model.layers.13.self_attn.q_proj.bias": "model-00002-of-000008.safetensors",
|
| 164 |
+
"model.layers.13.self_attn.k_proj.bias": "model-00002-of-000008.safetensors",
|
| 165 |
+
"model.layers.13.self_attn.v_proj.bias": "model-00002-of-000008.safetensors",
|
| 166 |
+
"model.layers.13.self_attn.q_proj.weight": "model-00002-of-000008.safetensors",
|
| 167 |
+
"model.layers.13.self_attn.k_proj.weight": "model-00002-of-000008.safetensors",
|
| 168 |
+
"model.layers.13.self_attn.v_proj.weight": "model-00002-of-000008.safetensors",
|
| 169 |
+
"model.layers.13.self_attn.o_proj.weight": "model-00002-of-000008.safetensors",
|
| 170 |
+
"model.layers.13.mlp.gate_proj.weight": "model-00002-of-000008.safetensors",
|
| 171 |
+
"model.layers.13.mlp.up_proj.weight": "model-00002-of-000008.safetensors",
|
| 172 |
+
"model.layers.13.mlp.down_proj.weight": "model-00002-of-000008.safetensors",
|
| 173 |
+
"model.layers.13.input_layernorm.weight": "model-00002-of-000008.safetensors",
|
| 174 |
+
"model.layers.13.post_attention_layernorm.weight": "model-00002-of-000008.safetensors",
|
| 175 |
+
"model.layers.14.self_attn.q_proj.bias": "model-00002-of-000008.safetensors",
|
| 176 |
+
"model.layers.14.self_attn.k_proj.bias": "model-00002-of-000008.safetensors",
|
| 177 |
+
"model.layers.14.self_attn.v_proj.bias": "model-00002-of-000008.safetensors",
|
| 178 |
+
"model.layers.14.self_attn.q_proj.weight": "model-00002-of-000008.safetensors",
|
| 179 |
+
"model.layers.14.self_attn.k_proj.weight": "model-00002-of-000008.safetensors",
|
| 180 |
+
"model.layers.14.self_attn.v_proj.weight": "model-00002-of-000008.safetensors",
|
| 181 |
+
"model.layers.14.self_attn.o_proj.weight": "model-00002-of-000008.safetensors",
|
| 182 |
+
"model.layers.14.mlp.gate_proj.weight": "model-00002-of-000008.safetensors",
|
| 183 |
+
"model.layers.14.mlp.up_proj.weight": "model-00002-of-000008.safetensors",
|
| 184 |
+
"model.layers.14.mlp.down_proj.weight": "model-00002-of-000008.safetensors",
|
| 185 |
+
"model.layers.14.input_layernorm.weight": "model-00002-of-000008.safetensors",
|
| 186 |
+
"model.layers.14.post_attention_layernorm.weight": "model-00002-of-000008.safetensors",
|
| 187 |
+
"model.layers.15.self_attn.q_proj.bias": "model-00002-of-000008.safetensors",
|
| 188 |
+
"model.layers.15.self_attn.k_proj.bias": "model-00002-of-000008.safetensors",
|
| 189 |
+
"model.layers.15.self_attn.v_proj.bias": "model-00002-of-000008.safetensors",
|
| 190 |
+
"model.layers.15.self_attn.q_proj.weight": "model-00002-of-000008.safetensors",
|
| 191 |
+
"model.layers.15.self_attn.k_proj.weight": "model-00002-of-000008.safetensors",
|
| 192 |
+
"model.layers.15.self_attn.v_proj.weight": "model-00002-of-000008.safetensors",
|
| 193 |
+
"model.layers.15.self_attn.o_proj.weight": "model-00002-of-000008.safetensors",
|
| 194 |
+
"model.layers.15.mlp.gate_proj.weight": "model-00002-of-000008.safetensors",
|
| 195 |
+
"model.layers.15.mlp.up_proj.weight": "model-00002-of-000008.safetensors",
|
| 196 |
+
"model.layers.15.mlp.down_proj.weight": "model-00002-of-000008.safetensors",
|
| 197 |
+
"model.layers.15.input_layernorm.weight": "model-00002-of-000008.safetensors",
|
| 198 |
+
"model.layers.15.post_attention_layernorm.weight": "model-00002-of-000008.safetensors",
|
| 199 |
+
"model.layers.16.self_attn.q_proj.bias": "model-00002-of-000008.safetensors",
|
| 200 |
+
"model.layers.16.self_attn.k_proj.bias": "model-00002-of-000008.safetensors",
|
| 201 |
+
"model.layers.16.self_attn.v_proj.bias": "model-00002-of-000008.safetensors",
|
| 202 |
+
"model.layers.16.self_attn.q_proj.weight": "model-00002-of-000008.safetensors",
|
| 203 |
+
"model.layers.16.self_attn.k_proj.weight": "model-00002-of-000008.safetensors",
|
| 204 |
+
"model.layers.16.self_attn.v_proj.weight": "model-00002-of-000008.safetensors",
|
| 205 |
+
"model.layers.16.self_attn.o_proj.weight": "model-00002-of-000008.safetensors",
|
| 206 |
+
"model.layers.16.mlp.gate_proj.weight": "model-00002-of-000008.safetensors",
|
| 207 |
+
"model.layers.16.mlp.up_proj.weight": "model-00003-of-000008.safetensors",
|
| 208 |
+
"model.layers.16.mlp.down_proj.weight": "model-00003-of-000008.safetensors",
|
| 209 |
+
"model.layers.16.input_layernorm.weight": "model-00003-of-000008.safetensors",
|
| 210 |
+
"model.layers.16.post_attention_layernorm.weight": "model-00003-of-000008.safetensors",
|
| 211 |
+
"model.layers.17.self_attn.q_proj.bias": "model-00003-of-000008.safetensors",
|
| 212 |
+
"model.layers.17.self_attn.k_proj.bias": "model-00003-of-000008.safetensors",
|
| 213 |
+
"model.layers.17.self_attn.v_proj.bias": "model-00003-of-000008.safetensors",
|
| 214 |
+
"model.layers.17.self_attn.q_proj.weight": "model-00003-of-000008.safetensors",
|
| 215 |
+
"model.layers.17.self_attn.k_proj.weight": "model-00003-of-000008.safetensors",
|
| 216 |
+
"model.layers.17.self_attn.v_proj.weight": "model-00003-of-000008.safetensors",
|
| 217 |
+
"model.layers.17.self_attn.o_proj.weight": "model-00003-of-000008.safetensors",
|
| 218 |
+
"model.layers.17.mlp.gate_proj.weight": "model-00003-of-000008.safetensors",
|
| 219 |
+
"model.layers.17.mlp.up_proj.weight": "model-00003-of-000008.safetensors",
|
| 220 |
+
"model.layers.17.mlp.down_proj.weight": "model-00003-of-000008.safetensors",
|
| 221 |
+
"model.layers.17.input_layernorm.weight": "model-00003-of-000008.safetensors",
|
| 222 |
+
"model.layers.17.post_attention_layernorm.weight": "model-00003-of-000008.safetensors",
|
| 223 |
+
"model.layers.18.self_attn.q_proj.bias": "model-00003-of-000008.safetensors",
|
| 224 |
+
"model.layers.18.self_attn.k_proj.bias": "model-00003-of-000008.safetensors",
|
| 225 |
+
"model.layers.18.self_attn.v_proj.bias": "model-00003-of-000008.safetensors",
|
| 226 |
+
"model.layers.18.self_attn.q_proj.weight": "model-00003-of-000008.safetensors",
|
| 227 |
+
"model.layers.18.self_attn.k_proj.weight": "model-00003-of-000008.safetensors",
|
| 228 |
+
"model.layers.18.self_attn.v_proj.weight": "model-00003-of-000008.safetensors",
|
| 229 |
+
"model.layers.18.self_attn.o_proj.weight": "model-00003-of-000008.safetensors",
|
| 230 |
+
"model.layers.18.mlp.gate_proj.weight": "model-00003-of-000008.safetensors",
|
| 231 |
+
"model.layers.18.mlp.up_proj.weight": "model-00003-of-000008.safetensors",
|
| 232 |
+
"model.layers.18.mlp.down_proj.weight": "model-00003-of-000008.safetensors",
|
| 233 |
+
"model.layers.18.input_layernorm.weight": "model-00003-of-000008.safetensors",
|
| 234 |
+
"model.layers.18.post_attention_layernorm.weight": "model-00003-of-000008.safetensors",
|
| 235 |
+
"model.layers.19.self_attn.q_proj.bias": "model-00003-of-000008.safetensors",
|
| 236 |
+
"model.layers.19.self_attn.k_proj.bias": "model-00003-of-000008.safetensors",
|
| 237 |
+
"model.layers.19.self_attn.v_proj.bias": "model-00003-of-000008.safetensors",
|
| 238 |
+
"model.layers.19.self_attn.q_proj.weight": "model-00003-of-000008.safetensors",
|
| 239 |
+
"model.layers.19.self_attn.k_proj.weight": "model-00003-of-000008.safetensors",
|
| 240 |
+
"model.layers.19.self_attn.v_proj.weight": "model-00003-of-000008.safetensors",
|
| 241 |
+
"model.layers.19.self_attn.o_proj.weight": "model-00003-of-000008.safetensors",
|
| 242 |
+
"model.layers.19.mlp.gate_proj.weight": "model-00003-of-000008.safetensors",
|
| 243 |
+
"model.layers.19.mlp.up_proj.weight": "model-00003-of-000008.safetensors",
|
| 244 |
+
"model.layers.19.mlp.down_proj.weight": "model-00003-of-000008.safetensors",
|
| 245 |
+
"model.layers.19.input_layernorm.weight": "model-00003-of-000008.safetensors",
|
| 246 |
+
"model.layers.19.post_attention_layernorm.weight": "model-00003-of-000008.safetensors",
|
| 247 |
+
"model.layers.20.self_attn.q_proj.bias": "model-00003-of-000008.safetensors",
|
| 248 |
+
"model.layers.20.self_attn.k_proj.bias": "model-00003-of-000008.safetensors",
|
| 249 |
+
"model.layers.20.self_attn.v_proj.bias": "model-00003-of-000008.safetensors",
|
| 250 |
+
"model.layers.20.self_attn.q_proj.weight": "model-00003-of-000008.safetensors",
|
| 251 |
+
"model.layers.20.self_attn.k_proj.weight": "model-00003-of-000008.safetensors",
|
| 252 |
+
"model.layers.20.self_attn.v_proj.weight": "model-00003-of-000008.safetensors",
|
| 253 |
+
"model.layers.20.self_attn.o_proj.weight": "model-00003-of-000008.safetensors",
|
| 254 |
+
"model.layers.20.mlp.gate_proj.weight": "model-00003-of-000008.safetensors",
|
| 255 |
+
"model.layers.20.mlp.up_proj.weight": "model-00003-of-000008.safetensors",
|
| 256 |
+
"model.layers.20.mlp.down_proj.weight": "model-00003-of-000008.safetensors",
|
| 257 |
+
"model.layers.20.input_layernorm.weight": "model-00003-of-000008.safetensors",
|
| 258 |
+
"model.layers.20.post_attention_layernorm.weight": "model-00003-of-000008.safetensors",
|
| 259 |
+
"model.layers.21.self_attn.q_proj.bias": "model-00003-of-000008.safetensors",
|
| 260 |
+
"model.layers.21.self_attn.k_proj.bias": "model-00003-of-000008.safetensors",
|
| 261 |
+
"model.layers.21.self_attn.v_proj.bias": "model-00003-of-000008.safetensors",
|
| 262 |
+
"model.layers.21.self_attn.q_proj.weight": "model-00003-of-000008.safetensors",
|
| 263 |
+
"model.layers.21.self_attn.k_proj.weight": "model-00003-of-000008.safetensors",
|
| 264 |
+
"model.layers.21.self_attn.v_proj.weight": "model-00003-of-000008.safetensors",
|
| 265 |
+
"model.layers.21.self_attn.o_proj.weight": "model-00003-of-000008.safetensors",
|
| 266 |
+
"model.layers.21.mlp.gate_proj.weight": "model-00003-of-000008.safetensors",
|
| 267 |
+
"model.layers.21.mlp.up_proj.weight": "model-00003-of-000008.safetensors",
|
| 268 |
+
"model.layers.21.mlp.down_proj.weight": "model-00003-of-000008.safetensors",
|
| 269 |
+
"model.layers.21.input_layernorm.weight": "model-00003-of-000008.safetensors",
|
| 270 |
+
"model.layers.21.post_attention_layernorm.weight": "model-00003-of-000008.safetensors",
|
| 271 |
+
"model.layers.22.self_attn.q_proj.bias": "model-00003-of-000008.safetensors",
|
| 272 |
+
"model.layers.22.self_attn.k_proj.bias": "model-00003-of-000008.safetensors",
|
| 273 |
+
"model.layers.22.self_attn.v_proj.bias": "model-00003-of-000008.safetensors",
|
| 274 |
+
"model.layers.22.self_attn.q_proj.weight": "model-00003-of-000008.safetensors",
|
| 275 |
+
"model.layers.22.self_attn.k_proj.weight": "model-00003-of-000008.safetensors",
|
| 276 |
+
"model.layers.22.self_attn.v_proj.weight": "model-00003-of-000008.safetensors",
|
| 277 |
+
"model.layers.22.self_attn.o_proj.weight": "model-00003-of-000008.safetensors",
|
| 278 |
+
"model.layers.22.mlp.gate_proj.weight": "model-00003-of-000008.safetensors",
|
| 279 |
+
"model.layers.22.mlp.up_proj.weight": "model-00003-of-000008.safetensors",
|
| 280 |
+
"model.layers.22.mlp.down_proj.weight": "model-00003-of-000008.safetensors",
|
| 281 |
+
"model.layers.22.input_layernorm.weight": "model-00003-of-000008.safetensors",
|
| 282 |
+
"model.layers.22.post_attention_layernorm.weight": "model-00003-of-000008.safetensors",
|
| 283 |
+
"model.layers.23.self_attn.q_proj.bias": "model-00003-of-000008.safetensors",
|
| 284 |
+
"model.layers.23.self_attn.k_proj.bias": "model-00003-of-000008.safetensors",
|
| 285 |
+
"model.layers.23.self_attn.v_proj.bias": "model-00003-of-000008.safetensors",
|
| 286 |
+
"model.layers.23.self_attn.q_proj.weight": "model-00003-of-000008.safetensors",
|
| 287 |
+
"model.layers.23.self_attn.k_proj.weight": "model-00003-of-000008.safetensors",
|
| 288 |
+
"model.layers.23.self_attn.v_proj.weight": "model-00003-of-000008.safetensors",
|
| 289 |
+
"model.layers.23.self_attn.o_proj.weight": "model-00003-of-000008.safetensors",
|
| 290 |
+
"model.layers.23.mlp.gate_proj.weight": "model-00003-of-000008.safetensors",
|
| 291 |
+
"model.layers.23.mlp.up_proj.weight": "model-00003-of-000008.safetensors",
|
| 292 |
+
"model.layers.23.mlp.down_proj.weight": "model-00003-of-000008.safetensors",
|
| 293 |
+
"model.layers.23.input_layernorm.weight": "model-00003-of-000008.safetensors",
|
| 294 |
+
"model.layers.23.post_attention_layernorm.weight": "model-00003-of-000008.safetensors",
|
| 295 |
+
"model.layers.24.self_attn.q_proj.bias": "model-00003-of-000008.safetensors",
|
| 296 |
+
"model.layers.24.self_attn.k_proj.bias": "model-00003-of-000008.safetensors",
|
| 297 |
+
"model.layers.24.self_attn.v_proj.bias": "model-00003-of-000008.safetensors",
|
| 298 |
+
"model.layers.24.self_attn.q_proj.weight": "model-00003-of-000008.safetensors",
|
| 299 |
+
"model.layers.24.self_attn.k_proj.weight": "model-00003-of-000008.safetensors",
|
| 300 |
+
"model.layers.24.self_attn.v_proj.weight": "model-00003-of-000008.safetensors",
|
| 301 |
+
"model.layers.24.self_attn.o_proj.weight": "model-00003-of-000008.safetensors",
|
| 302 |
+
"model.layers.24.mlp.gate_proj.weight": "model-00003-of-000008.safetensors",
|
| 303 |
+
"model.layers.24.mlp.up_proj.weight": "model-00003-of-000008.safetensors",
|
| 304 |
+
"model.layers.24.mlp.down_proj.weight": "model-00003-of-000008.safetensors",
|
| 305 |
+
"model.layers.24.input_layernorm.weight": "model-00003-of-000008.safetensors",
|
| 306 |
+
"model.layers.24.post_attention_layernorm.weight": "model-00003-of-000008.safetensors",
|
| 307 |
+
"model.layers.25.self_attn.q_proj.bias": "model-00003-of-000008.safetensors",
|
| 308 |
+
"model.layers.25.self_attn.k_proj.bias": "model-00003-of-000008.safetensors",
|
| 309 |
+
"model.layers.25.self_attn.v_proj.bias": "model-00003-of-000008.safetensors",
|
| 310 |
+
"model.layers.25.self_attn.q_proj.weight": "model-00003-of-000008.safetensors",
|
| 311 |
+
"model.layers.25.self_attn.k_proj.weight": "model-00003-of-000008.safetensors",
|
| 312 |
+
"model.layers.25.self_attn.v_proj.weight": "model-00003-of-000008.safetensors",
|
| 313 |
+
"model.layers.25.self_attn.o_proj.weight": "model-00003-of-000008.safetensors",
|
| 314 |
+
"model.layers.25.mlp.gate_proj.weight": "model-00003-of-000008.safetensors",
|
| 315 |
+
"model.layers.25.mlp.up_proj.weight": "model-00004-of-000008.safetensors",
|
| 316 |
+
"model.layers.25.mlp.down_proj.weight": "model-00004-of-000008.safetensors",
|
| 317 |
+
"model.layers.25.input_layernorm.weight": "model-00004-of-000008.safetensors",
|
| 318 |
+
"model.layers.25.post_attention_layernorm.weight": "model-00004-of-000008.safetensors",
|
| 319 |
+
"model.layers.26.self_attn.q_proj.bias": "model-00004-of-000008.safetensors",
|
| 320 |
+
"model.layers.26.self_attn.k_proj.bias": "model-00004-of-000008.safetensors",
|
| 321 |
+
"model.layers.26.self_attn.v_proj.bias": "model-00004-of-000008.safetensors",
|
| 322 |
+
"model.layers.26.self_attn.q_proj.weight": "model-00004-of-000008.safetensors",
|
| 323 |
+
"model.layers.26.self_attn.k_proj.weight": "model-00004-of-000008.safetensors",
|
| 324 |
+
"model.layers.26.self_attn.v_proj.weight": "model-00004-of-000008.safetensors",
|
| 325 |
+
"model.layers.26.self_attn.o_proj.weight": "model-00004-of-000008.safetensors",
|
| 326 |
+
"model.layers.26.mlp.gate_proj.weight": "model-00004-of-000008.safetensors",
|
| 327 |
+
"model.layers.26.mlp.up_proj.weight": "model-00004-of-000008.safetensors",
|
| 328 |
+
"model.layers.26.mlp.down_proj.weight": "model-00004-of-000008.safetensors",
|
| 329 |
+
"model.layers.26.input_layernorm.weight": "model-00004-of-000008.safetensors",
|
| 330 |
+
"model.layers.26.post_attention_layernorm.weight": "model-00004-of-000008.safetensors",
|
| 331 |
+
"model.layers.27.self_attn.q_proj.bias": "model-00004-of-000008.safetensors",
|
| 332 |
+
"model.layers.27.self_attn.k_proj.bias": "model-00004-of-000008.safetensors",
|
| 333 |
+
"model.layers.27.self_attn.v_proj.bias": "model-00004-of-000008.safetensors",
|
| 334 |
+
"model.layers.27.self_attn.q_proj.weight": "model-00004-of-000008.safetensors",
|
| 335 |
+
"model.layers.27.self_attn.k_proj.weight": "model-00004-of-000008.safetensors",
|
| 336 |
+
"model.layers.27.self_attn.v_proj.weight": "model-00004-of-000008.safetensors",
|
| 337 |
+
"model.layers.27.self_attn.o_proj.weight": "model-00004-of-000008.safetensors",
|
| 338 |
+
"model.layers.27.mlp.gate_proj.weight": "model-00004-of-000008.safetensors",
|
| 339 |
+
"model.layers.27.mlp.up_proj.weight": "model-00004-of-000008.safetensors",
|
| 340 |
+
"model.layers.27.mlp.down_proj.weight": "model-00004-of-000008.safetensors",
|
| 341 |
+
"model.layers.27.input_layernorm.weight": "model-00004-of-000008.safetensors",
|
| 342 |
+
"model.layers.27.post_attention_layernorm.weight": "model-00004-of-000008.safetensors",
|
| 343 |
+
"model.layers.28.self_attn.q_proj.bias": "model-00004-of-000008.safetensors",
|
| 344 |
+
"model.layers.28.self_attn.k_proj.bias": "model-00004-of-000008.safetensors",
|
| 345 |
+
"model.layers.28.self_attn.v_proj.bias": "model-00004-of-000008.safetensors",
|
| 346 |
+
"model.layers.28.self_attn.q_proj.weight": "model-00004-of-000008.safetensors",
|
| 347 |
+
"model.layers.28.self_attn.k_proj.weight": "model-00004-of-000008.safetensors",
|
| 348 |
+
"model.layers.28.self_attn.v_proj.weight": "model-00004-of-000008.safetensors",
|
| 349 |
+
"model.layers.28.self_attn.o_proj.weight": "model-00004-of-000008.safetensors",
|
| 350 |
+
"model.layers.28.mlp.gate_proj.weight": "model-00004-of-000008.safetensors",
|
| 351 |
+
"model.layers.28.mlp.up_proj.weight": "model-00004-of-000008.safetensors",
|
| 352 |
+
"model.layers.28.mlp.down_proj.weight": "model-00004-of-000008.safetensors",
|
| 353 |
+
"model.layers.28.input_layernorm.weight": "model-00004-of-000008.safetensors",
|
| 354 |
+
"model.layers.28.post_attention_layernorm.weight": "model-00004-of-000008.safetensors",
|
| 355 |
+
"model.layers.29.self_attn.q_proj.bias": "model-00004-of-000008.safetensors",
|
| 356 |
+
"model.layers.29.self_attn.k_proj.bias": "model-00004-of-000008.safetensors",
|
| 357 |
+
"model.layers.29.self_attn.v_proj.bias": "model-00004-of-000008.safetensors",
|
| 358 |
+
"model.layers.29.self_attn.q_proj.weight": "model-00004-of-000008.safetensors",
|
| 359 |
+
"model.layers.29.self_attn.k_proj.weight": "model-00004-of-000008.safetensors",
|
| 360 |
+
"model.layers.29.self_attn.v_proj.weight": "model-00004-of-000008.safetensors",
|
| 361 |
+
"model.layers.29.self_attn.o_proj.weight": "model-00004-of-000008.safetensors",
|
| 362 |
+
"model.layers.29.mlp.gate_proj.weight": "model-00004-of-000008.safetensors",
|
| 363 |
+
"model.layers.29.mlp.up_proj.weight": "model-00004-of-000008.safetensors",
|
| 364 |
+
"model.layers.29.mlp.down_proj.weight": "model-00004-of-000008.safetensors",
|
| 365 |
+
"model.layers.29.input_layernorm.weight": "model-00004-of-000008.safetensors",
|
| 366 |
+
"model.layers.29.post_attention_layernorm.weight": "model-00004-of-000008.safetensors",
|
| 367 |
+
"model.layers.30.self_attn.q_proj.bias": "model-00004-of-000008.safetensors",
|
| 368 |
+
"model.layers.30.self_attn.k_proj.bias": "model-00004-of-000008.safetensors",
|
| 369 |
+
"model.layers.30.self_attn.v_proj.bias": "model-00004-of-000008.safetensors",
|
| 370 |
+
"model.layers.30.self_attn.q_proj.weight": "model-00004-of-000008.safetensors",
|
| 371 |
+
"model.layers.30.self_attn.k_proj.weight": "model-00004-of-000008.safetensors",
|
| 372 |
+
"model.layers.30.self_attn.v_proj.weight": "model-00004-of-000008.safetensors",
|
| 373 |
+
"model.layers.30.self_attn.o_proj.weight": "model-00004-of-000008.safetensors",
|
| 374 |
+
"model.layers.30.mlp.gate_proj.weight": "model-00004-of-000008.safetensors",
|
| 375 |
+
"model.layers.30.mlp.up_proj.weight": "model-00004-of-000008.safetensors",
|
| 376 |
+
"model.layers.30.mlp.down_proj.weight": "model-00004-of-000008.safetensors",
|
| 377 |
+
"model.layers.30.input_layernorm.weight": "model-00004-of-000008.safetensors",
|
| 378 |
+
"model.layers.30.post_attention_layernorm.weight": "model-00004-of-000008.safetensors",
|
| 379 |
+
"model.layers.31.self_attn.q_proj.bias": "model-00004-of-000008.safetensors",
|
| 380 |
+
"model.layers.31.self_attn.k_proj.bias": "model-00004-of-000008.safetensors",
|
| 381 |
+
"model.layers.31.self_attn.v_proj.bias": "model-00004-of-000008.safetensors",
|
| 382 |
+
"model.layers.31.self_attn.q_proj.weight": "model-00004-of-000008.safetensors",
|
| 383 |
+
"model.layers.31.self_attn.k_proj.weight": "model-00004-of-000008.safetensors",
|
| 384 |
+
"model.layers.31.self_attn.v_proj.weight": "model-00004-of-000008.safetensors",
|
| 385 |
+
"model.layers.31.self_attn.o_proj.weight": "model-00004-of-000008.safetensors",
|
| 386 |
+
"model.layers.31.mlp.gate_proj.weight": "model-00004-of-000008.safetensors",
|
| 387 |
+
"model.layers.31.mlp.up_proj.weight": "model-00004-of-000008.safetensors",
|
| 388 |
+
"model.layers.31.mlp.down_proj.weight": "model-00004-of-000008.safetensors",
|
| 389 |
+
"model.layers.31.input_layernorm.weight": "model-00004-of-000008.safetensors",
|
| 390 |
+
"model.layers.31.post_attention_layernorm.weight": "model-00004-of-000008.safetensors",
|
| 391 |
+
"model.layers.32.self_attn.q_proj.bias": "model-00004-of-000008.safetensors",
|
| 392 |
+
"model.layers.32.self_attn.k_proj.bias": "model-00004-of-000008.safetensors",
|
| 393 |
+
"model.layers.32.self_attn.v_proj.bias": "model-00004-of-000008.safetensors",
|
| 394 |
+
"model.layers.32.self_attn.q_proj.weight": "model-00004-of-000008.safetensors",
|
| 395 |
+
"model.layers.32.self_attn.k_proj.weight": "model-00004-of-000008.safetensors",
|
| 396 |
+
"model.layers.32.self_attn.v_proj.weight": "model-00004-of-000008.safetensors",
|
| 397 |
+
"model.layers.32.self_attn.o_proj.weight": "model-00004-of-000008.safetensors",
|
| 398 |
+
"model.layers.32.mlp.gate_proj.weight": "model-00004-of-000008.safetensors",
|
| 399 |
+
"model.layers.32.mlp.up_proj.weight": "model-00004-of-000008.safetensors",
|
| 400 |
+
"model.layers.32.mlp.down_proj.weight": "model-00004-of-000008.safetensors",
|
| 401 |
+
"model.layers.32.input_layernorm.weight": "model-00004-of-000008.safetensors",
|
| 402 |
+
"model.layers.32.post_attention_layernorm.weight": "model-00004-of-000008.safetensors",
|
| 403 |
+
"model.layers.33.self_attn.q_proj.bias": "model-00004-of-000008.safetensors",
|
| 404 |
+
"model.layers.33.self_attn.k_proj.bias": "model-00004-of-000008.safetensors",
|
| 405 |
+
"model.layers.33.self_attn.v_proj.bias": "model-00004-of-000008.safetensors",
|
| 406 |
+
"model.layers.33.self_attn.q_proj.weight": "model-00004-of-000008.safetensors",
|
| 407 |
+
"model.layers.33.self_attn.k_proj.weight": "model-00004-of-000008.safetensors",
|
| 408 |
+
"model.layers.33.self_attn.v_proj.weight": "model-00004-of-000008.safetensors",
|
| 409 |
+
"model.layers.33.self_attn.o_proj.weight": "model-00004-of-000008.safetensors",
|
| 410 |
+
"model.layers.33.mlp.gate_proj.weight": "model-00004-of-000008.safetensors",
|
| 411 |
+
"model.layers.33.mlp.up_proj.weight": "model-00004-of-000008.safetensors",
|
| 412 |
+
"model.layers.33.mlp.down_proj.weight": "model-00004-of-000008.safetensors",
|
| 413 |
+
"model.layers.33.input_layernorm.weight": "model-00004-of-000008.safetensors",
|
| 414 |
+
"model.layers.33.post_attention_layernorm.weight": "model-00004-of-000008.safetensors",
|
| 415 |
+
"model.layers.34.self_attn.q_proj.bias": "model-00004-of-000008.safetensors",
|
| 416 |
+
"model.layers.34.self_attn.k_proj.bias": "model-00004-of-000008.safetensors",
|
| 417 |
+
"model.layers.34.self_attn.v_proj.bias": "model-00004-of-000008.safetensors",
|
| 418 |
+
"model.layers.34.self_attn.q_proj.weight": "model-00004-of-000008.safetensors",
|
| 419 |
+
"model.layers.34.self_attn.k_proj.weight": "model-00004-of-000008.safetensors",
|
| 420 |
+
"model.layers.34.self_attn.v_proj.weight": "model-00004-of-000008.safetensors",
|
| 421 |
+
"model.layers.34.self_attn.o_proj.weight": "model-00004-of-000008.safetensors",
|
| 422 |
+
"model.layers.34.mlp.gate_proj.weight": "model-00004-of-000008.safetensors",
|
| 423 |
+
"model.layers.34.mlp.up_proj.weight": "model-00005-of-000008.safetensors",
|
| 424 |
+
"model.layers.34.mlp.down_proj.weight": "model-00005-of-000008.safetensors",
|
| 425 |
+
"model.layers.34.input_layernorm.weight": "model-00005-of-000008.safetensors",
|
| 426 |
+
"model.layers.34.post_attention_layernorm.weight": "model-00005-of-000008.safetensors",
|
| 427 |
+
"model.layers.35.self_attn.q_proj.bias": "model-00005-of-000008.safetensors",
|
| 428 |
+
"model.layers.35.self_attn.k_proj.bias": "model-00005-of-000008.safetensors",
|
| 429 |
+
"model.layers.35.self_attn.v_proj.bias": "model-00005-of-000008.safetensors",
|
| 430 |
+
"model.layers.35.self_attn.q_proj.weight": "model-00005-of-000008.safetensors",
|
| 431 |
+
"model.layers.35.self_attn.k_proj.weight": "model-00005-of-000008.safetensors",
|
| 432 |
+
"model.layers.35.self_attn.v_proj.weight": "model-00005-of-000008.safetensors",
|
| 433 |
+
"model.layers.35.self_attn.o_proj.weight": "model-00005-of-000008.safetensors",
|
| 434 |
+
"model.layers.35.mlp.gate_proj.weight": "model-00005-of-000008.safetensors",
|
| 435 |
+
"model.layers.35.mlp.up_proj.weight": "model-00005-of-000008.safetensors",
|
| 436 |
+
"model.layers.35.mlp.down_proj.weight": "model-00005-of-000008.safetensors",
|
| 437 |
+
"model.layers.35.input_layernorm.weight": "model-00005-of-000008.safetensors",
|
| 438 |
+
"model.layers.35.post_attention_layernorm.weight": "model-00005-of-000008.safetensors",
|
| 439 |
+
"model.layers.36.self_attn.q_proj.bias": "model-00005-of-000008.safetensors",
|
| 440 |
+
"model.layers.36.self_attn.k_proj.bias": "model-00005-of-000008.safetensors",
|
| 441 |
+
"model.layers.36.self_attn.v_proj.bias": "model-00005-of-000008.safetensors",
|
| 442 |
+
"model.layers.36.self_attn.q_proj.weight": "model-00005-of-000008.safetensors",
|
| 443 |
+
"model.layers.36.self_attn.k_proj.weight": "model-00005-of-000008.safetensors",
|
| 444 |
+
"model.layers.36.self_attn.v_proj.weight": "model-00005-of-000008.safetensors",
|
| 445 |
+
"model.layers.36.self_attn.o_proj.weight": "model-00005-of-000008.safetensors",
|
| 446 |
+
"model.layers.36.mlp.gate_proj.weight": "model-00005-of-000008.safetensors",
|
| 447 |
+
"model.layers.36.mlp.up_proj.weight": "model-00005-of-000008.safetensors",
|
| 448 |
+
"model.layers.36.mlp.down_proj.weight": "model-00005-of-000008.safetensors",
|
| 449 |
+
"model.layers.36.input_layernorm.weight": "model-00005-of-000008.safetensors",
|
| 450 |
+
"model.layers.36.post_attention_layernorm.weight": "model-00005-of-000008.safetensors",
|
| 451 |
+
"model.layers.37.self_attn.q_proj.bias": "model-00005-of-000008.safetensors",
|
| 452 |
+
"model.layers.37.self_attn.k_proj.bias": "model-00005-of-000008.safetensors",
|
| 453 |
+
"model.layers.37.self_attn.v_proj.bias": "model-00005-of-000008.safetensors",
|
| 454 |
+
"model.layers.37.self_attn.q_proj.weight": "model-00005-of-000008.safetensors",
|
| 455 |
+
"model.layers.37.self_attn.k_proj.weight": "model-00005-of-000008.safetensors",
|
| 456 |
+
"model.layers.37.self_attn.v_proj.weight": "model-00005-of-000008.safetensors",
|
| 457 |
+
"model.layers.37.self_attn.o_proj.weight": "model-00005-of-000008.safetensors",
|
| 458 |
+
"model.layers.37.mlp.gate_proj.weight": "model-00005-of-000008.safetensors",
|
| 459 |
+
"model.layers.37.mlp.up_proj.weight": "model-00005-of-000008.safetensors",
|
| 460 |
+
"model.layers.37.mlp.down_proj.weight": "model-00005-of-000008.safetensors",
|
| 461 |
+
"model.layers.37.input_layernorm.weight": "model-00005-of-000008.safetensors",
|
| 462 |
+
"model.layers.37.post_attention_layernorm.weight": "model-00005-of-000008.safetensors",
|
| 463 |
+
"model.layers.38.self_attn.q_proj.bias": "model-00005-of-000008.safetensors",
|
| 464 |
+
"model.layers.38.self_attn.k_proj.bias": "model-00005-of-000008.safetensors",
|
| 465 |
+
"model.layers.38.self_attn.v_proj.bias": "model-00005-of-000008.safetensors",
|
| 466 |
+
"model.layers.38.self_attn.q_proj.weight": "model-00005-of-000008.safetensors",
|
| 467 |
+
"model.layers.38.self_attn.k_proj.weight": "model-00005-of-000008.safetensors",
|
| 468 |
+
"model.layers.38.self_attn.v_proj.weight": "model-00005-of-000008.safetensors",
|
| 469 |
+
"model.layers.38.self_attn.o_proj.weight": "model-00005-of-000008.safetensors",
|
| 470 |
+
"model.layers.38.mlp.gate_proj.weight": "model-00005-of-000008.safetensors",
|
| 471 |
+
"model.layers.38.mlp.up_proj.weight": "model-00005-of-000008.safetensors",
|
| 472 |
+
"model.layers.38.mlp.down_proj.weight": "model-00005-of-000008.safetensors",
|
| 473 |
+
"model.layers.38.input_layernorm.weight": "model-00005-of-000008.safetensors",
|
| 474 |
+
"model.layers.38.post_attention_layernorm.weight": "model-00005-of-000008.safetensors",
|
| 475 |
+
"model.layers.39.self_attn.q_proj.bias": "model-00005-of-000008.safetensors",
|
| 476 |
+
"model.layers.39.self_attn.k_proj.bias": "model-00005-of-000008.safetensors",
|
| 477 |
+
"model.layers.39.self_attn.v_proj.bias": "model-00005-of-000008.safetensors",
|
| 478 |
+
"model.layers.39.self_attn.q_proj.weight": "model-00005-of-000008.safetensors",
|
| 479 |
+
"model.layers.39.self_attn.k_proj.weight": "model-00005-of-000008.safetensors",
|
| 480 |
+
"model.layers.39.self_attn.v_proj.weight": "model-00005-of-000008.safetensors",
|
| 481 |
+
"model.layers.39.self_attn.o_proj.weight": "model-00005-of-000008.safetensors",
|
| 482 |
+
"model.layers.39.mlp.gate_proj.weight": "model-00005-of-000008.safetensors",
|
| 483 |
+
"model.layers.39.mlp.up_proj.weight": "model-00005-of-000008.safetensors",
|
| 484 |
+
"model.layers.39.mlp.down_proj.weight": "model-00005-of-000008.safetensors",
|
| 485 |
+
"model.layers.39.input_layernorm.weight": "model-00005-of-000008.safetensors",
|
| 486 |
+
"model.layers.39.post_attention_layernorm.weight": "model-00005-of-000008.safetensors",
|
| 487 |
+
"model.layers.40.self_attn.q_proj.bias": "model-00005-of-000008.safetensors",
|
| 488 |
+
"model.layers.40.self_attn.k_proj.bias": "model-00005-of-000008.safetensors",
|
| 489 |
+
"model.layers.40.self_attn.v_proj.bias": "model-00005-of-000008.safetensors",
|
| 490 |
+
"model.layers.40.self_attn.q_proj.weight": "model-00005-of-000008.safetensors",
|
| 491 |
+
"model.layers.40.self_attn.k_proj.weight": "model-00005-of-000008.safetensors",
|
| 492 |
+
"model.layers.40.self_attn.v_proj.weight": "model-00005-of-000008.safetensors",
|
| 493 |
+
"model.layers.40.self_attn.o_proj.weight": "model-00005-of-000008.safetensors",
|
| 494 |
+
"model.layers.40.mlp.gate_proj.weight": "model-00005-of-000008.safetensors",
|
| 495 |
+
"model.layers.40.mlp.up_proj.weight": "model-00005-of-000008.safetensors",
|
| 496 |
+
"model.layers.40.mlp.down_proj.weight": "model-00005-of-000008.safetensors",
|
| 497 |
+
"model.layers.40.input_layernorm.weight": "model-00005-of-000008.safetensors",
|
| 498 |
+
"model.layers.40.post_attention_layernorm.weight": "model-00005-of-000008.safetensors",
|
| 499 |
+
"model.layers.41.self_attn.q_proj.bias": "model-00005-of-000008.safetensors",
|
| 500 |
+
"model.layers.41.self_attn.k_proj.bias": "model-00005-of-000008.safetensors",
|
| 501 |
+
"model.layers.41.self_attn.v_proj.bias": "model-00005-of-000008.safetensors",
|
| 502 |
+
"model.layers.41.self_attn.q_proj.weight": "model-00005-of-000008.safetensors",
|
| 503 |
+
"model.layers.41.self_attn.k_proj.weight": "model-00005-of-000008.safetensors",
|
| 504 |
+
"model.layers.41.self_attn.v_proj.weight": "model-00005-of-000008.safetensors",
|
| 505 |
+
"model.layers.41.self_attn.o_proj.weight": "model-00005-of-000008.safetensors",
|
| 506 |
+
"model.layers.41.mlp.gate_proj.weight": "model-00005-of-000008.safetensors",
|
| 507 |
+
"model.layers.41.mlp.up_proj.weight": "model-00005-of-000008.safetensors",
|
| 508 |
+
"model.layers.41.mlp.down_proj.weight": "model-00005-of-000008.safetensors",
|
| 509 |
+
"model.layers.41.input_layernorm.weight": "model-00005-of-000008.safetensors",
|
| 510 |
+
"model.layers.41.post_attention_layernorm.weight": "model-00005-of-000008.safetensors",
|
| 511 |
+
"model.layers.42.self_attn.q_proj.bias": "model-00005-of-000008.safetensors",
|
| 512 |
+
"model.layers.42.self_attn.k_proj.bias": "model-00005-of-000008.safetensors",
|
| 513 |
+
"model.layers.42.self_attn.v_proj.bias": "model-00005-of-000008.safetensors",
|
| 514 |
+
"model.layers.42.self_attn.q_proj.weight": "model-00005-of-000008.safetensors",
|
| 515 |
+
"model.layers.42.self_attn.k_proj.weight": "model-00005-of-000008.safetensors",
|
| 516 |
+
"model.layers.42.self_attn.v_proj.weight": "model-00005-of-000008.safetensors",
|
| 517 |
+
"model.layers.42.self_attn.o_proj.weight": "model-00005-of-000008.safetensors",
|
| 518 |
+
"model.layers.42.mlp.gate_proj.weight": "model-00005-of-000008.safetensors",
|
| 519 |
+
"model.layers.42.mlp.up_proj.weight": "model-00005-of-000008.safetensors",
|
| 520 |
+
"model.layers.42.mlp.down_proj.weight": "model-00005-of-000008.safetensors",
|
| 521 |
+
"model.layers.42.input_layernorm.weight": "model-00005-of-000008.safetensors",
|
| 522 |
+
"model.layers.42.post_attention_layernorm.weight": "model-00005-of-000008.safetensors",
|
| 523 |
+
"model.layers.43.self_attn.q_proj.bias": "model-00005-of-000008.safetensors",
|
| 524 |
+
"model.layers.43.self_attn.k_proj.bias": "model-00005-of-000008.safetensors",
|
| 525 |
+
"model.layers.43.self_attn.v_proj.bias": "model-00005-of-000008.safetensors",
|
| 526 |
+
"model.layers.43.self_attn.q_proj.weight": "model-00005-of-000008.safetensors",
|
| 527 |
+
"model.layers.43.self_attn.k_proj.weight": "model-00005-of-000008.safetensors",
|
| 528 |
+
"model.layers.43.self_attn.v_proj.weight": "model-00005-of-000008.safetensors",
|
| 529 |
+
"model.layers.43.self_attn.o_proj.weight": "model-00005-of-000008.safetensors",
|
| 530 |
+
"model.layers.43.mlp.gate_proj.weight": "model-00005-of-000008.safetensors",
|
| 531 |
+
"model.layers.43.mlp.up_proj.weight": "model-00006-of-000008.safetensors",
|
| 532 |
+
"model.layers.43.mlp.down_proj.weight": "model-00006-of-000008.safetensors",
|
| 533 |
+
"model.layers.43.input_layernorm.weight": "model-00006-of-000008.safetensors",
|
| 534 |
+
"model.layers.43.post_attention_layernorm.weight": "model-00006-of-000008.safetensors",
|
| 535 |
+
"model.layers.44.self_attn.q_proj.bias": "model-00006-of-000008.safetensors",
|
| 536 |
+
"model.layers.44.self_attn.k_proj.bias": "model-00006-of-000008.safetensors",
|
| 537 |
+
"model.layers.44.self_attn.v_proj.bias": "model-00006-of-000008.safetensors",
|
| 538 |
+
"model.layers.44.self_attn.q_proj.weight": "model-00006-of-000008.safetensors",
|
| 539 |
+
"model.layers.44.self_attn.k_proj.weight": "model-00006-of-000008.safetensors",
|
| 540 |
+
"model.layers.44.self_attn.v_proj.weight": "model-00006-of-000008.safetensors",
|
| 541 |
+
"model.layers.44.self_attn.o_proj.weight": "model-00006-of-000008.safetensors",
|
| 542 |
+
"model.layers.44.mlp.gate_proj.weight": "model-00006-of-000008.safetensors",
|
| 543 |
+
"model.layers.44.mlp.up_proj.weight": "model-00006-of-000008.safetensors",
|
| 544 |
+
"model.layers.44.mlp.down_proj.weight": "model-00006-of-000008.safetensors",
|
| 545 |
+
"model.layers.44.input_layernorm.weight": "model-00006-of-000008.safetensors",
|
| 546 |
+
"model.layers.44.post_attention_layernorm.weight": "model-00006-of-000008.safetensors",
|
| 547 |
+
"model.layers.45.self_attn.q_proj.bias": "model-00006-of-000008.safetensors",
|
| 548 |
+
"model.layers.45.self_attn.k_proj.bias": "model-00006-of-000008.safetensors",
|
| 549 |
+
"model.layers.45.self_attn.v_proj.bias": "model-00006-of-000008.safetensors",
|
| 550 |
+
"model.layers.45.self_attn.q_proj.weight": "model-00006-of-000008.safetensors",
|
| 551 |
+
"model.layers.45.self_attn.k_proj.weight": "model-00006-of-000008.safetensors",
|
| 552 |
+
"model.layers.45.self_attn.v_proj.weight": "model-00006-of-000008.safetensors",
|
| 553 |
+
"model.layers.45.self_attn.o_proj.weight": "model-00006-of-000008.safetensors",
|
| 554 |
+
"model.layers.45.mlp.gate_proj.weight": "model-00006-of-000008.safetensors",
|
| 555 |
+
"model.layers.45.mlp.up_proj.weight": "model-00006-of-000008.safetensors",
|
| 556 |
+
"model.layers.45.mlp.down_proj.weight": "model-00006-of-000008.safetensors",
|
| 557 |
+
"model.layers.45.input_layernorm.weight": "model-00006-of-000008.safetensors",
|
| 558 |
+
"model.layers.45.post_attention_layernorm.weight": "model-00006-of-000008.safetensors",
|
| 559 |
+
"model.layers.46.self_attn.q_proj.bias": "model-00006-of-000008.safetensors",
|
| 560 |
+
"model.layers.46.self_attn.k_proj.bias": "model-00006-of-000008.safetensors",
|
| 561 |
+
"model.layers.46.self_attn.v_proj.bias": "model-00006-of-000008.safetensors",
|
| 562 |
+
"model.layers.46.self_attn.q_proj.weight": "model-00006-of-000008.safetensors",
|
| 563 |
+
"model.layers.46.self_attn.k_proj.weight": "model-00006-of-000008.safetensors",
|
| 564 |
+
"model.layers.46.self_attn.v_proj.weight": "model-00006-of-000008.safetensors",
|
| 565 |
+
"model.layers.46.self_attn.o_proj.weight": "model-00006-of-000008.safetensors",
|
| 566 |
+
"model.layers.46.mlp.gate_proj.weight": "model-00006-of-000008.safetensors",
|
| 567 |
+
"model.layers.46.mlp.up_proj.weight": "model-00006-of-000008.safetensors",
|
| 568 |
+
"model.layers.46.mlp.down_proj.weight": "model-00006-of-000008.safetensors",
|
| 569 |
+
"model.layers.46.input_layernorm.weight": "model-00006-of-000008.safetensors",
|
| 570 |
+
"model.layers.46.post_attention_layernorm.weight": "model-00006-of-000008.safetensors",
|
| 571 |
+
"model.layers.47.self_attn.q_proj.bias": "model-00006-of-000008.safetensors",
|
| 572 |
+
"model.layers.47.self_attn.k_proj.bias": "model-00006-of-000008.safetensors",
|
| 573 |
+
"model.layers.47.self_attn.v_proj.bias": "model-00006-of-000008.safetensors",
|
| 574 |
+
"model.layers.47.self_attn.q_proj.weight": "model-00006-of-000008.safetensors",
|
| 575 |
+
"model.layers.47.self_attn.k_proj.weight": "model-00006-of-000008.safetensors",
|
| 576 |
+
"model.layers.47.self_attn.v_proj.weight": "model-00006-of-000008.safetensors",
|
| 577 |
+
"model.layers.47.self_attn.o_proj.weight": "model-00006-of-000008.safetensors",
|
| 578 |
+
"model.layers.47.mlp.gate_proj.weight": "model-00006-of-000008.safetensors",
|
| 579 |
+
"model.layers.47.mlp.up_proj.weight": "model-00006-of-000008.safetensors",
|
| 580 |
+
"model.layers.47.mlp.down_proj.weight": "model-00006-of-000008.safetensors",
|
| 581 |
+
"model.layers.47.input_layernorm.weight": "model-00006-of-000008.safetensors",
|
| 582 |
+
"model.layers.47.post_attention_layernorm.weight": "model-00006-of-000008.safetensors",
|
| 583 |
+
"model.layers.48.self_attn.q_proj.bias": "model-00006-of-000008.safetensors",
|
| 584 |
+
"model.layers.48.self_attn.k_proj.bias": "model-00006-of-000008.safetensors",
|
| 585 |
+
"model.layers.48.self_attn.v_proj.bias": "model-00006-of-000008.safetensors",
|
| 586 |
+
"model.layers.48.self_attn.q_proj.weight": "model-00006-of-000008.safetensors",
|
| 587 |
+
"model.layers.48.self_attn.k_proj.weight": "model-00006-of-000008.safetensors",
|
| 588 |
+
"model.layers.48.self_attn.v_proj.weight": "model-00006-of-000008.safetensors",
|
| 589 |
+
"model.layers.48.self_attn.o_proj.weight": "model-00006-of-000008.safetensors",
|
| 590 |
+
"model.layers.48.mlp.gate_proj.weight": "model-00006-of-000008.safetensors",
|
| 591 |
+
"model.layers.48.mlp.up_proj.weight": "model-00006-of-000008.safetensors",
|
| 592 |
+
"model.layers.48.mlp.down_proj.weight": "model-00006-of-000008.safetensors",
|
| 593 |
+
"model.layers.48.input_layernorm.weight": "model-00006-of-000008.safetensors",
|
| 594 |
+
"model.layers.48.post_attention_layernorm.weight": "model-00006-of-000008.safetensors",
|
| 595 |
+
"model.layers.49.self_attn.q_proj.bias": "model-00006-of-000008.safetensors",
|
| 596 |
+
"model.layers.49.self_attn.k_proj.bias": "model-00006-of-000008.safetensors",
|
| 597 |
+
"model.layers.49.self_attn.v_proj.bias": "model-00006-of-000008.safetensors",
|
| 598 |
+
"model.layers.49.self_attn.q_proj.weight": "model-00006-of-000008.safetensors",
|
| 599 |
+
"model.layers.49.self_attn.k_proj.weight": "model-00006-of-000008.safetensors",
|
| 600 |
+
"model.layers.49.self_attn.v_proj.weight": "model-00006-of-000008.safetensors",
|
| 601 |
+
"model.layers.49.self_attn.o_proj.weight": "model-00006-of-000008.safetensors",
|
| 602 |
+
"model.layers.49.mlp.gate_proj.weight": "model-00006-of-000008.safetensors",
|
| 603 |
+
"model.layers.49.mlp.up_proj.weight": "model-00006-of-000008.safetensors",
|
| 604 |
+
"model.layers.49.mlp.down_proj.weight": "model-00006-of-000008.safetensors",
|
| 605 |
+
"model.layers.49.input_layernorm.weight": "model-00006-of-000008.safetensors",
|
| 606 |
+
"model.layers.49.post_attention_layernorm.weight": "model-00006-of-000008.safetensors",
|
| 607 |
+
"model.layers.50.self_attn.q_proj.bias": "model-00006-of-000008.safetensors",
|
| 608 |
+
"model.layers.50.self_attn.k_proj.bias": "model-00006-of-000008.safetensors",
|
| 609 |
+
"model.layers.50.self_attn.v_proj.bias": "model-00006-of-000008.safetensors",
|
| 610 |
+
"model.layers.50.self_attn.q_proj.weight": "model-00006-of-000008.safetensors",
|
| 611 |
+
"model.layers.50.self_attn.k_proj.weight": "model-00006-of-000008.safetensors",
|
| 612 |
+
"model.layers.50.self_attn.v_proj.weight": "model-00006-of-000008.safetensors",
|
| 613 |
+
"model.layers.50.self_attn.o_proj.weight": "model-00006-of-000008.safetensors",
|
| 614 |
+
"model.layers.50.mlp.gate_proj.weight": "model-00006-of-000008.safetensors",
|
| 615 |
+
"model.layers.50.mlp.up_proj.weight": "model-00006-of-000008.safetensors",
|
| 616 |
+
"model.layers.50.mlp.down_proj.weight": "model-00006-of-000008.safetensors",
|
| 617 |
+
"model.layers.50.input_layernorm.weight": "model-00006-of-000008.safetensors",
|
| 618 |
+
"model.layers.50.post_attention_layernorm.weight": "model-00006-of-000008.safetensors",
|
| 619 |
+
"model.layers.51.self_attn.q_proj.bias": "model-00006-of-000008.safetensors",
|
| 620 |
+
"model.layers.51.self_attn.k_proj.bias": "model-00006-of-000008.safetensors",
|
| 621 |
+
"model.layers.51.self_attn.v_proj.bias": "model-00006-of-000008.safetensors",
|
| 622 |
+
"model.layers.51.self_attn.q_proj.weight": "model-00006-of-000008.safetensors",
|
| 623 |
+
"model.layers.51.self_attn.k_proj.weight": "model-00006-of-000008.safetensors",
|
| 624 |
+
"model.layers.51.self_attn.v_proj.weight": "model-00006-of-000008.safetensors",
|
| 625 |
+
"model.layers.51.self_attn.o_proj.weight": "model-00006-of-000008.safetensors",
|
| 626 |
+
"model.layers.51.mlp.gate_proj.weight": "model-00006-of-000008.safetensors",
|
| 627 |
+
"model.layers.51.mlp.up_proj.weight": "model-00006-of-000008.safetensors",
|
| 628 |
+
"model.layers.51.mlp.down_proj.weight": "model-00006-of-000008.safetensors",
|
| 629 |
+
"model.layers.51.input_layernorm.weight": "model-00006-of-000008.safetensors",
|
| 630 |
+
"model.layers.51.post_attention_layernorm.weight": "model-00006-of-000008.safetensors",
|
| 631 |
+
"model.layers.52.self_attn.q_proj.bias": "model-00006-of-000008.safetensors",
|
| 632 |
+
"model.layers.52.self_attn.k_proj.bias": "model-00006-of-000008.safetensors",
|
| 633 |
+
"model.layers.52.self_attn.v_proj.bias": "model-00006-of-000008.safetensors",
|
| 634 |
+
"model.layers.52.self_attn.q_proj.weight": "model-00006-of-000008.safetensors",
|
| 635 |
+
"model.layers.52.self_attn.k_proj.weight": "model-00006-of-000008.safetensors",
|
| 636 |
+
"model.layers.52.self_attn.v_proj.weight": "model-00006-of-000008.safetensors",
|
| 637 |
+
"model.layers.52.self_attn.o_proj.weight": "model-00006-of-000008.safetensors",
|
| 638 |
+
"model.layers.52.mlp.gate_proj.weight": "model-00006-of-000008.safetensors",
|
| 639 |
+
"model.layers.52.mlp.up_proj.weight": "model-00007-of-000008.safetensors",
|
| 640 |
+
"model.layers.52.mlp.down_proj.weight": "model-00007-of-000008.safetensors",
|
| 641 |
+
"model.layers.52.input_layernorm.weight": "model-00007-of-000008.safetensors",
|
| 642 |
+
"model.layers.52.post_attention_layernorm.weight": "model-00007-of-000008.safetensors",
|
| 643 |
+
"model.layers.53.self_attn.q_proj.bias": "model-00007-of-000008.safetensors",
|
| 644 |
+
"model.layers.53.self_attn.k_proj.bias": "model-00007-of-000008.safetensors",
|
| 645 |
+
"model.layers.53.self_attn.v_proj.bias": "model-00007-of-000008.safetensors",
|
| 646 |
+
"model.layers.53.self_attn.q_proj.weight": "model-00007-of-000008.safetensors",
|
| 647 |
+
"model.layers.53.self_attn.k_proj.weight": "model-00007-of-000008.safetensors",
|
| 648 |
+
"model.layers.53.self_attn.v_proj.weight": "model-00007-of-000008.safetensors",
|
| 649 |
+
"model.layers.53.self_attn.o_proj.weight": "model-00007-of-000008.safetensors",
|
| 650 |
+
"model.layers.53.mlp.gate_proj.weight": "model-00007-of-000008.safetensors",
|
| 651 |
+
"model.layers.53.mlp.up_proj.weight": "model-00007-of-000008.safetensors",
|
| 652 |
+
"model.layers.53.mlp.down_proj.weight": "model-00007-of-000008.safetensors",
|
| 653 |
+
"model.layers.53.input_layernorm.weight": "model-00007-of-000008.safetensors",
|
| 654 |
+
"model.layers.53.post_attention_layernorm.weight": "model-00007-of-000008.safetensors",
|
| 655 |
+
"model.layers.54.self_attn.q_proj.bias": "model-00007-of-000008.safetensors",
|
| 656 |
+
"model.layers.54.self_attn.k_proj.bias": "model-00007-of-000008.safetensors",
|
| 657 |
+
"model.layers.54.self_attn.v_proj.bias": "model-00007-of-000008.safetensors",
|
| 658 |
+
"model.layers.54.self_attn.q_proj.weight": "model-00007-of-000008.safetensors",
|
| 659 |
+
"model.layers.54.self_attn.k_proj.weight": "model-00007-of-000008.safetensors",
|
| 660 |
+
"model.layers.54.self_attn.v_proj.weight": "model-00007-of-000008.safetensors",
|
| 661 |
+
"model.layers.54.self_attn.o_proj.weight": "model-00007-of-000008.safetensors",
|
| 662 |
+
"model.layers.54.mlp.gate_proj.weight": "model-00007-of-000008.safetensors",
|
| 663 |
+
"model.layers.54.mlp.up_proj.weight": "model-00007-of-000008.safetensors",
|
| 664 |
+
"model.layers.54.mlp.down_proj.weight": "model-00007-of-000008.safetensors",
|
| 665 |
+
"model.layers.54.input_layernorm.weight": "model-00007-of-000008.safetensors",
|
| 666 |
+
"model.layers.54.post_attention_layernorm.weight": "model-00007-of-000008.safetensors",
|
| 667 |
+
"model.layers.55.self_attn.q_proj.bias": "model-00007-of-000008.safetensors",
|
| 668 |
+
"model.layers.55.self_attn.k_proj.bias": "model-00007-of-000008.safetensors",
|
| 669 |
+
"model.layers.55.self_attn.v_proj.bias": "model-00007-of-000008.safetensors",
|
| 670 |
+
"model.layers.55.self_attn.q_proj.weight": "model-00007-of-000008.safetensors",
|
| 671 |
+
"model.layers.55.self_attn.k_proj.weight": "model-00007-of-000008.safetensors",
|
| 672 |
+
"model.layers.55.self_attn.v_proj.weight": "model-00007-of-000008.safetensors",
|
| 673 |
+
"model.layers.55.self_attn.o_proj.weight": "model-00007-of-000008.safetensors",
|
| 674 |
+
"model.layers.55.mlp.gate_proj.weight": "model-00007-of-000008.safetensors",
|
| 675 |
+
"model.layers.55.mlp.up_proj.weight": "model-00007-of-000008.safetensors",
|
| 676 |
+
"model.layers.55.mlp.down_proj.weight": "model-00007-of-000008.safetensors",
|
| 677 |
+
"model.layers.55.input_layernorm.weight": "model-00007-of-000008.safetensors",
|
| 678 |
+
"model.layers.55.post_attention_layernorm.weight": "model-00007-of-000008.safetensors",
|
| 679 |
+
"model.layers.56.self_attn.q_proj.bias": "model-00007-of-000008.safetensors",
|
| 680 |
+
"model.layers.56.self_attn.k_proj.bias": "model-00007-of-000008.safetensors",
|
| 681 |
+
"model.layers.56.self_attn.v_proj.bias": "model-00007-of-000008.safetensors",
|
| 682 |
+
"model.layers.56.self_attn.q_proj.weight": "model-00007-of-000008.safetensors",
|
| 683 |
+
"model.layers.56.self_attn.k_proj.weight": "model-00007-of-000008.safetensors",
|
| 684 |
+
"model.layers.56.self_attn.v_proj.weight": "model-00007-of-000008.safetensors",
|
| 685 |
+
"model.layers.56.self_attn.o_proj.weight": "model-00007-of-000008.safetensors",
|
| 686 |
+
"model.layers.56.mlp.gate_proj.weight": "model-00007-of-000008.safetensors",
|
| 687 |
+
"model.layers.56.mlp.up_proj.weight": "model-00007-of-000008.safetensors",
|
| 688 |
+
"model.layers.56.mlp.down_proj.weight": "model-00007-of-000008.safetensors",
|
| 689 |
+
"model.layers.56.input_layernorm.weight": "model-00007-of-000008.safetensors",
|
| 690 |
+
"model.layers.56.post_attention_layernorm.weight": "model-00007-of-000008.safetensors",
|
| 691 |
+
"model.layers.57.self_attn.q_proj.bias": "model-00007-of-000008.safetensors",
|
| 692 |
+
"model.layers.57.self_attn.k_proj.bias": "model-00007-of-000008.safetensors",
|
| 693 |
+
"model.layers.57.self_attn.v_proj.bias": "model-00007-of-000008.safetensors",
|
| 694 |
+
"model.layers.57.self_attn.q_proj.weight": "model-00007-of-000008.safetensors",
|
| 695 |
+
"model.layers.57.self_attn.k_proj.weight": "model-00007-of-000008.safetensors",
|
| 696 |
+
"model.layers.57.self_attn.v_proj.weight": "model-00007-of-000008.safetensors",
|
| 697 |
+
"model.layers.57.self_attn.o_proj.weight": "model-00007-of-000008.safetensors",
|
| 698 |
+
"model.layers.57.mlp.gate_proj.weight": "model-00007-of-000008.safetensors",
|
| 699 |
+
"model.layers.57.mlp.up_proj.weight": "model-00007-of-000008.safetensors",
|
| 700 |
+
"model.layers.57.mlp.down_proj.weight": "model-00007-of-000008.safetensors",
|
| 701 |
+
"model.layers.57.input_layernorm.weight": "model-00007-of-000008.safetensors",
|
| 702 |
+
"model.layers.57.post_attention_layernorm.weight": "model-00007-of-000008.safetensors",
|
| 703 |
+
"model.layers.58.self_attn.q_proj.bias": "model-00007-of-000008.safetensors",
|
| 704 |
+
"model.layers.58.self_attn.k_proj.bias": "model-00007-of-000008.safetensors",
|
| 705 |
+
"model.layers.58.self_attn.v_proj.bias": "model-00007-of-000008.safetensors",
|
| 706 |
+
"model.layers.58.self_attn.q_proj.weight": "model-00007-of-000008.safetensors",
|
| 707 |
+
"model.layers.58.self_attn.k_proj.weight": "model-00007-of-000008.safetensors",
|
| 708 |
+
"model.layers.58.self_attn.v_proj.weight": "model-00007-of-000008.safetensors",
|
| 709 |
+
"model.layers.58.self_attn.o_proj.weight": "model-00007-of-000008.safetensors",
|
| 710 |
+
"model.layers.58.mlp.gate_proj.weight": "model-00007-of-000008.safetensors",
|
| 711 |
+
"model.layers.58.mlp.up_proj.weight": "model-00007-of-000008.safetensors",
|
| 712 |
+
"model.layers.58.mlp.down_proj.weight": "model-00007-of-000008.safetensors",
|
| 713 |
+
"model.layers.58.input_layernorm.weight": "model-00007-of-000008.safetensors",
|
| 714 |
+
"model.layers.58.post_attention_layernorm.weight": "model-00007-of-000008.safetensors",
|
| 715 |
+
"model.layers.59.self_attn.q_proj.bias": "model-00007-of-000008.safetensors",
|
| 716 |
+
"model.layers.59.self_attn.k_proj.bias": "model-00007-of-000008.safetensors",
|
| 717 |
+
"model.layers.59.self_attn.v_proj.bias": "model-00007-of-000008.safetensors",
|
| 718 |
+
"model.layers.59.self_attn.q_proj.weight": "model-00007-of-000008.safetensors",
|
| 719 |
+
"model.layers.59.self_attn.k_proj.weight": "model-00007-of-000008.safetensors",
|
| 720 |
+
"model.layers.59.self_attn.v_proj.weight": "model-00007-of-000008.safetensors",
|
| 721 |
+
"model.layers.59.self_attn.o_proj.weight": "model-00007-of-000008.safetensors",
|
| 722 |
+
"model.layers.59.mlp.gate_proj.weight": "model-00007-of-000008.safetensors",
|
| 723 |
+
"model.layers.59.mlp.up_proj.weight": "model-00007-of-000008.safetensors",
|
| 724 |
+
"model.layers.59.mlp.down_proj.weight": "model-00007-of-000008.safetensors",
|
| 725 |
+
"model.layers.59.input_layernorm.weight": "model-00007-of-000008.safetensors",
|
| 726 |
+
"model.layers.59.post_attention_layernorm.weight": "model-00007-of-000008.safetensors",
|
| 727 |
+
"model.layers.60.self_attn.q_proj.bias": "model-00007-of-000008.safetensors",
|
| 728 |
+
"model.layers.60.self_attn.k_proj.bias": "model-00007-of-000008.safetensors",
|
| 729 |
+
"model.layers.60.self_attn.v_proj.bias": "model-00007-of-000008.safetensors",
|
| 730 |
+
"model.layers.60.self_attn.q_proj.weight": "model-00007-of-000008.safetensors",
|
| 731 |
+
"model.layers.60.self_attn.k_proj.weight": "model-00007-of-000008.safetensors",
|
| 732 |
+
"model.layers.60.self_attn.v_proj.weight": "model-00007-of-000008.safetensors",
|
| 733 |
+
"model.layers.60.self_attn.o_proj.weight": "model-00007-of-000008.safetensors",
|
| 734 |
+
"model.layers.60.mlp.gate_proj.weight": "model-00007-of-000008.safetensors",
|
| 735 |
+
"model.layers.60.mlp.up_proj.weight": "model-00007-of-000008.safetensors",
|
| 736 |
+
"model.layers.60.mlp.down_proj.weight": "model-00007-of-000008.safetensors",
|
| 737 |
+
"model.layers.60.input_layernorm.weight": "model-00007-of-000008.safetensors",
|
| 738 |
+
"model.layers.60.post_attention_layernorm.weight": "model-00007-of-000008.safetensors",
|
| 739 |
+
"model.layers.61.self_attn.q_proj.bias": "model-00007-of-000008.safetensors",
|
| 740 |
+
"model.layers.61.self_attn.k_proj.bias": "model-00007-of-000008.safetensors",
|
| 741 |
+
"model.layers.61.self_attn.v_proj.bias": "model-00007-of-000008.safetensors",
|
| 742 |
+
"model.layers.61.self_attn.q_proj.weight": "model-00007-of-000008.safetensors",
|
| 743 |
+
"model.layers.61.self_attn.k_proj.weight": "model-00007-of-000008.safetensors",
|
| 744 |
+
"model.layers.61.self_attn.v_proj.weight": "model-00007-of-000008.safetensors",
|
| 745 |
+
"model.layers.61.self_attn.o_proj.weight": "model-00007-of-000008.safetensors",
|
| 746 |
+
"model.layers.61.mlp.gate_proj.weight": "model-00007-of-000008.safetensors",
|
| 747 |
+
"model.layers.61.mlp.up_proj.weight": "model-00008-of-000008.safetensors",
|
| 748 |
+
"model.layers.61.mlp.down_proj.weight": "model-00008-of-000008.safetensors",
|
| 749 |
+
"model.layers.61.input_layernorm.weight": "model-00008-of-000008.safetensors",
|
| 750 |
+
"model.layers.61.post_attention_layernorm.weight": "model-00008-of-000008.safetensors",
|
| 751 |
+
"model.layers.62.self_attn.q_proj.bias": "model-00008-of-000008.safetensors",
|
| 752 |
+
"model.layers.62.self_attn.k_proj.bias": "model-00008-of-000008.safetensors",
|
| 753 |
+
"model.layers.62.self_attn.v_proj.bias": "model-00008-of-000008.safetensors",
|
| 754 |
+
"model.layers.62.self_attn.q_proj.weight": "model-00008-of-000008.safetensors",
|
| 755 |
+
"model.layers.62.self_attn.k_proj.weight": "model-00008-of-000008.safetensors",
|
| 756 |
+
"model.layers.62.self_attn.v_proj.weight": "model-00008-of-000008.safetensors",
|
| 757 |
+
"model.layers.62.self_attn.o_proj.weight": "model-00008-of-000008.safetensors",
|
| 758 |
+
"model.layers.62.mlp.gate_proj.weight": "model-00008-of-000008.safetensors",
|
| 759 |
+
"model.layers.62.mlp.up_proj.weight": "model-00008-of-000008.safetensors",
|
| 760 |
+
"model.layers.62.mlp.down_proj.weight": "model-00008-of-000008.safetensors",
|
| 761 |
+
"model.layers.62.input_layernorm.weight": "model-00008-of-000008.safetensors",
|
| 762 |
+
"model.layers.62.post_attention_layernorm.weight": "model-00008-of-000008.safetensors",
|
| 763 |
+
"model.layers.63.self_attn.q_proj.bias": "model-00008-of-000008.safetensors",
|
| 764 |
+
"model.layers.63.self_attn.k_proj.bias": "model-00008-of-000008.safetensors",
|
| 765 |
+
"model.layers.63.self_attn.v_proj.bias": "model-00008-of-000008.safetensors",
|
| 766 |
+
"model.layers.63.self_attn.q_proj.weight": "model-00008-of-000008.safetensors",
|
| 767 |
+
"model.layers.63.self_attn.k_proj.weight": "model-00008-of-000008.safetensors",
|
| 768 |
+
"model.layers.63.self_attn.v_proj.weight": "model-00008-of-000008.safetensors",
|
| 769 |
+
"model.layers.63.self_attn.o_proj.weight": "model-00008-of-000008.safetensors",
|
| 770 |
+
"model.layers.63.mlp.gate_proj.weight": "model-00008-of-000008.safetensors",
|
| 771 |
+
"model.layers.63.mlp.up_proj.weight": "model-00008-of-000008.safetensors",
|
| 772 |
+
"model.layers.63.mlp.down_proj.weight": "model-00008-of-000008.safetensors",
|
| 773 |
+
"model.layers.63.input_layernorm.weight": "model-00008-of-000008.safetensors",
|
| 774 |
+
"model.layers.63.post_attention_layernorm.weight": "model-00008-of-000008.safetensors",
|
| 775 |
+
"model.norm.weight": "model-00008-of-000008.safetensors",
|
| 776 |
+
"lm_head.weight": "model-00008-of-000008.safetensors"
|
| 777 |
+
}
|
| 778 |
+
}
|
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｜><think>\\n'}}{% endif %}"
|
| 35 |
+
}
|