Add text-generation tag and link to Github
#2
by
nielsr
HF staff
- opened
README.md
CHANGED
@@ -9,6 +9,7 @@ tags:
|
|
9 |
- deepseek
|
10 |
- unsloth
|
11 |
- transformers
|
|
|
12 |
---
|
13 |
|
14 |
## ***See [our collection](https://huggingface.co/collections/unsloth/deepseek-v3-all-versions-677cf5cfd7df8b7815fc723c) for versions of Deepseek V3 including GGUF, bf16 and original formats.***
|
@@ -23,6 +24,8 @@ We have a free Google Colab Tesla T4 notebook for Llama 3.1 (8B) here: https://c
|
|
23 |
# unsloth/DeepSeek-V3-bf16
|
24 |
For more details on the model, please go to Deepseek's original [model card](https://huggingface.co/deepseek-ai/DeepSeek-V3)
|
25 |
|
|
|
|
|
26 |
## ✨ Finetune for Free
|
27 |
|
28 |
All notebooks are **beginner friendly**! Add your dataset, click "Run All", and you'll get a 2x faster finetuned model which can be exported to GGUF, vLLM or uploaded to Hugging Face.
|
@@ -91,12 +94,12 @@ Throughout the entire training process, we did not experience any irrecoverable
|
|
91 |
|
92 |
| **Model** | **#Total Params** | **#Activated Params** | **Context Length** | **Download** |
|
93 |
| :------------: | :------------: | :------------: | :------------: | :------------: |
|
94 |
-
| DeepSeek-V3-Base | 671B | 37B | 128K | [🤗
|
95 |
-
| DeepSeek-V3 | 671B | 37B | 128K | [🤗
|
96 |
|
97 |
</div>
|
98 |
|
99 |
-
**NOTE: The total size of DeepSeek-V3 models on
|
100 |
|
101 |
To ensure optimal performance and flexibility, we have partnered with open-source communities and hardware vendors to provide multiple ways to run the model locally. For step-by-step guidance, check out Section 6: [How_to Run_Locally](#6-how-to-run-locally).
|
102 |
|
@@ -193,15 +196,10 @@ Evaluation results on the ``Needle In A Haystack`` (NIAH) tests. DeepSeek-V3 pe
|
|
193 |
|
194 |
Note: All models are evaluated in a configuration that limits the output length to 8K. Benchmarks containing fewer than 1000 samples are tested multiple times using varying temperature settings to derive robust final results. DeepSeek-V3 stands as the best-performing open-source model, and also exhibits competitive performance against frontier closed-source models.
|
195 |
|
196 |
-
</div>
|
197 |
-
|
198 |
-
|
199 |
#### Open Ended Generation Evaluation
|
200 |
|
201 |
<div align="center">
|
202 |
|
203 |
-
|
204 |
-
|
205 |
| Model | Arena-Hard | AlpacaEval 2.0 |
|
206 |
|-------|------------|----------------|
|
207 |
| DeepSeek-V2.5-0905 | 76.2 | 50.5 |
|
@@ -321,14 +319,4 @@ This code repository is licensed under [the MIT License](LICENSE-CODE). The use
|
|
321 |
```
|
322 |
@misc{deepseekai2024deepseekv3technicalreport,
|
323 |
title={DeepSeek-V3 Technical Report},
|
324 |
-
author={DeepSeek-AI and Aixin Liu and Bei Feng and Bing Xue and Bingxuan Wang and Bochao Wu and Chengda Lu and Chenggang Zhao and Chengqi Deng and Chenyu Zhang and Chong Ruan and Damai Dai and Daya Guo and Dejian Yang and Deli Chen and Dongjie Ji and Erhang Li and Fangyun Lin and Fucong Dai and Fuli Luo and Guangbo Hao and Guanting Chen and Guowei Li and H. Zhang and Han Bao and Hanwei Xu and Haocheng Wang and Haowei Zhang and Honghui Ding and Huajian Xin and Huazuo Gao and Hui Li and Hui Qu and J. L. Cai and Jian Liang and Jianzhong Guo and Jiaqi Ni and Jiashi Li and Jiawei Wang and Jin Chen and Jingchang Chen and Jingyang Yuan and Junjie Qiu and Junlong Li and Junxiao Song and Kai Dong and Kai Hu and Kaige Gao and Kang Guan and Kexin Huang and Kuai Yu and Lean Wang and Lecong Zhang and Lei Xu and Leyi Xia and Liang Zhao and Litong Wang and Liyue Zhang and Meng Li and Miaojun Wang and Mingchuan Zhang and Minghua Zhang and Minghui Tang and Mingming Li and Ning Tian and Panpan Huang and Peiyi Wang and Peng Zhang and Qiancheng Wang and Qihao Zhu and Qinyu Chen and Qiushi Du and R. J. Chen and R. L. Jin and Ruiqi Ge and Ruisong Zhang and Ruizhe Pan and Runji Wang and Runxin Xu and Ruoyu Zhang and Ruyi Chen and S. S. Li and Shanghao Lu and Shangyan Zhou and Shanhuang Chen and Shaoqing Wu and Shengfeng Ye and Shengfeng Ye and Shirong Ma and Shiyu Wang and Shuang Zhou and Shuiping Yu and Shunfeng Zhou and Shuting Pan and T. Wang and Tao Yun and Tian Pei and Tianyu Sun and W. L. Xiao and Wangding Zeng and Wanjia Zhao and Wei An and Wen Liu and Wenfeng Liang and Wenjun Gao and Wenqin Yu and Wentao Zhang and X. Q. Li and Xiangyue Jin and Xianzu Wang and Xiao Bi and Xiaodong Liu and Xiaohan Wang and Xiaojin Shen and Xiaokang Chen and Xiaokang Zhang and Xiaosha Chen and Xiaotao Nie and Xiaowen Sun and Xiaoxiang Wang and Xin Cheng and Xin Liu and Xin Xie and Xingchao Liu and Xingkai Yu and Xinnan Song and Xinxia Shan and Xinyi Zhou and Xinyu Yang and Xinyuan Li and Xuecheng Su and Xuheng Lin and Y. K. Li and Y. Q. Wang and Y. X. Wei and Y. X. Zhu and Yang Zhang and Yanhong
|
325 |
-
year={2024},
|
326 |
-
eprint={2412.19437},
|
327 |
-
archivePrefix={arXiv},
|
328 |
-
primaryClass={cs.CL},
|
329 |
-
url={https://arxiv.org/abs/2412.19437},
|
330 |
-
}
|
331 |
-
```
|
332 |
-
|
333 |
-
## 9. Contact
|
334 |
-
If you have any questions, please raise an issue or contact us at [[email protected]]([email protected]).
|
|
|
9 |
- deepseek
|
10 |
- unsloth
|
11 |
- transformers
|
12 |
+
pipeline_tag: text-generation
|
13 |
---
|
14 |
|
15 |
## ***See [our collection](https://huggingface.co/collections/unsloth/deepseek-v3-all-versions-677cf5cfd7df8b7815fc723c) for versions of Deepseek V3 including GGUF, bf16 and original formats.***
|
|
|
24 |
# unsloth/DeepSeek-V3-bf16
|
25 |
For more details on the model, please go to Deepseek's original [model card](https://huggingface.co/deepseek-ai/DeepSeek-V3)
|
26 |
|
27 |
+
Github repository: https://github.com/deepseek-ai/DeepSeek-V3
|
28 |
+
|
29 |
## ✨ Finetune for Free
|
30 |
|
31 |
All notebooks are **beginner friendly**! Add your dataset, click "Run All", and you'll get a 2x faster finetuned model which can be exported to GGUF, vLLM or uploaded to Hugging Face.
|
|
|
94 |
|
95 |
| **Model** | **#Total Params** | **#Activated Params** | **Context Length** | **Download** |
|
96 |
| :------------: | :------------: | :------------: | :------------: | :------------: |
|
97 |
+
| DeepSeek-V3-Base | 671B | 37B | 128K | [🤗 Hugging Face](https://huggingface.co/deepseek-ai/DeepSeek-V3-Base) |
|
98 |
+
| DeepSeek-V3 | 671B | 37B | 128K | [🤗 Hugging Face](https://huggingface.co/deepseek-ai/DeepSeek-V3) |
|
99 |
|
100 |
</div>
|
101 |
|
102 |
+
**NOTE: The total size of DeepSeek-V3 models on Hugging Face is 685B, which includes 671B of the Main Model weights and 14B of the Multi-Token Prediction (MTP) Module weights.**
|
103 |
|
104 |
To ensure optimal performance and flexibility, we have partnered with open-source communities and hardware vendors to provide multiple ways to run the model locally. For step-by-step guidance, check out Section 6: [How_to Run_Locally](#6-how-to-run-locally).
|
105 |
|
|
|
196 |
|
197 |
Note: All models are evaluated in a configuration that limits the output length to 8K. Benchmarks containing fewer than 1000 samples are tested multiple times using varying temperature settings to derive robust final results. DeepSeek-V3 stands as the best-performing open-source model, and also exhibits competitive performance against frontier closed-source models.
|
198 |
|
|
|
|
|
|
|
199 |
#### Open Ended Generation Evaluation
|
200 |
|
201 |
<div align="center">
|
202 |
|
|
|
|
|
203 |
| Model | Arena-Hard | AlpacaEval 2.0 |
|
204 |
|-------|------------|----------------|
|
205 |
| DeepSeek-V2.5-0905 | 76.2 | 50.5 |
|
|
|
319 |
```
|
320 |
@misc{deepseekai2024deepseekv3technicalreport,
|
321 |
title={DeepSeek-V3 Technical Report},
|
322 |
+
author={DeepSeek-AI and Aixin Liu and Bei Feng and Bing Xue and Bingxuan Wang and Bochao Wu and Chengda Lu and Chenggang Zhao and Chengqi Deng and Chenyu Zhang and Chong Ruan and Damai Dai and Daya Guo and Dejian Yang and Deli Chen and Dongjie Ji and Erhang Li and Fangyun Lin and Fucong Dai and Fuli Luo and Guangbo Hao and Guanting Chen and Guowei Li and H. Zhang and Han Bao and Hanwei Xu and Haocheng Wang and Haowei Zhang and Honghui Ding and Huajian Xin and Huazuo Gao and Hui Li and Hui Qu and J. L. Cai and Jian Liang and Jianzhong Guo and Jiaqi Ni and Jiashi Li and Jiawei Wang and Jin Chen and Jingchang Chen and Jingyang Yuan and Junjie Qiu and Junlong Li and Junxiao Song and Kai Dong and Kai Hu and Kaige Gao and Kang Guan and Kexin Huang and Kuai Yu and Lean Wang and Lecong Zhang and Lei Xu and Leyi Xia and Liang Zhao and Litong Wang and Liyue Zhang and Meng Li and Miaojun Wang and Mingchuan Zhang and Minghua Zhang and Minghui Tang and Mingming Li and Ning Tian and Panpan Huang and Peiyi Wang and Peng Zhang and Qiancheng Wang and Qihao Zhu and Qinyu Chen and Qiushi Du and R. J. Chen and R. L. Jin and Ruiqi Ge and Ruisong Zhang and Ruizhe Pan and Runji Wang and Runxin Xu and Ruoyu Zhang and Ruyi Chen and S. S. Li and Shanghao Lu and Shangyan Zhou and Shanhuang Chen and Shaoqing Wu and Shengfeng Ye and Shengfeng Ye and Shirong Ma and Shiyu Wang and Shuang Zhou and Shuiping Yu and Shunfeng Zhou and Shuting Pan and T. Wang and Tao Yun and Tian Pei and Tianyu Sun and W. L. Xiao and Wangding Zeng and Wanjia Zhao and Wei An and Wen Liu and Wenfeng Liang and Wenjun Gao and Wenqin Yu and Wentao Zhang and X. Q. Li and Xiangyue Jin and Xianzu Wang and Xiao Bi and Xiaodong Liu and Xiaohan Wang and Xiaojin Shen and Xiaokang Chen and Xiaokang Zhang and Xiaosha Chen and Xiaotao Nie and Xiaowen Sun and Xiaoxiang Wang and Xin Cheng and Xin Liu and Xin Xie and Xingchao Liu and Xingkai Yu and Xinnan Song and Xinxia Shan and Xinyi Zhou and Xinyu Yang and Xinyuan Li and Xuecheng Su and Xuheng Lin and Y. K. Li and Y. Q. Wang and Y. X. Wei and Y. X. Zhu and Yang Zhang and Yanhong
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|