deepseekmirror/DeepSeek-V2
1
0
Fork 0
mirror of https://github.com/deepseek-ai/DeepSeek-V2.git synced 2025-05-03 08:59:03 -04:00
Code Issues Actions Packages Projects Releases Wiki Activity

docs: update README.md

Browse Source 
HuggingFace -> Hugging Face
This commit is contained in:
Ikko Eltociear Ashimine 2024-05-10 01:18:32 +09:00 committed by GitHub
parent cbd18b1e47
commit dfffc674f5
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 6 additions and 6 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

8
README.md
View File

@ -83,7 +83,7 @@ We pretrained DeepSeek-V2 on a diverse and high-quality corpus comprising 8.1 tr
</div> </div>
Due to the constraints of HuggingFace, the open-source code currently experiences slower performance than our internal codebase when running on GPUs with Huggingface. To facilitate the efficient execution of our model, we offer a dedicated vllm solution that optimizes performance for running our model effectively. Due to the constraints of Hugging Face, the open-source code currently experiences slower performance than our internal codebase when running on GPUs with Hugging Face. To facilitate the efficient execution of our model, we offer a dedicated vllm solution that optimizes performance for running our model effectively.
## 3. Evaluation Results ## 3. Evaluation Results
### Base Model ### Base Model
@ -186,8 +186,8 @@ We also provide OpenAI-Compatible API at DeepSeek Platform: [platform.deepseek.c
## 7. How to run locally ## 7. How to run locally
**To utilize DeepSeek-V2 in BF16 format for inference, 80GB*8 GPUs are required.** **To utilize DeepSeek-V2 in BF16 format for inference, 80GB*8 GPUs are required.**
### Inference with Huggingface's Transformers ### Inference with Hugging Face's Transformers
You can directly employ [Huggingface's Transformers](https://github.com/huggingface/transformers) for model inference. You can directly employ [Hugging Face's Transformers](https://github.com/huggingface/transformers) for model inference.
#### Text Completion #### Text Completion
```python ```python
@ -235,7 +235,7 @@ result = tokenizer.decode(outputs[0][input_tensor.shape[1]:], skip_special_token
print(result) print(result)
``` ```
The complete chat template can be found within `tokenizer_config.json` located in the huggingface model repository. The complete chat template can be found within `tokenizer_config.json` located in the Hugging Face model repository.
An example of chat template is as belows: An example of chat template is as belows: