From dfffc674f512d48c4479c5418e2637027d0c4bff Mon Sep 17 00:00:00 2001 From: Ikko Eltociear Ashimine Date: Fri, 10 May 2024 01:18:32 +0900 Subject: [PATCH] docs: update README.md HuggingFace -> Hugging Face --- README.md | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) diff --git a/README.md b/README.md index 6049440..2723903 100644 --- a/README.md +++ b/README.md @@ -78,12 +78,12 @@ We pretrained DeepSeek-V2 on a diverse and high-quality corpus comprising 8.1 tr | **Model** | **Context Length** | **Download** | | :------------: | :------------: | :------------: | -| DeepSeek-V2 | 128k | [🤗 HuggingFace](https://huggingface.co/deepseek-ai/DeepSeek-V2) | -| DeepSeek-V2-Chat (RL) | 128k | [🤗 HuggingFace](https://huggingface.co/deepseek-ai/DeepSeek-V2-Chat) | +| DeepSeek-V2 | 128k | [🤗 Hugging Face](https://huggingface.co/deepseek-ai/DeepSeek-V2) | +| DeepSeek-V2-Chat (RL) | 128k | [🤗 Hugging Face](https://huggingface.co/deepseek-ai/DeepSeek-V2-Chat) | -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 ### Base Model @@ -186,8 +186,8 @@ We also provide OpenAI-Compatible API at DeepSeek Platform: [platform.deepseek.c ## 7. How to run locally **To utilize DeepSeek-V2 in BF16 format for inference, 80GB*8 GPUs are required.** -### Inference with Huggingface's Transformers -You can directly employ [Huggingface's Transformers](https://github.com/huggingface/transformers) for model inference. +### Inference with Hugging Face's Transformers +You can directly employ [Hugging Face's Transformers](https://github.com/huggingface/transformers) for model inference. #### Text Completion ```python @@ -235,7 +235,7 @@ result = tokenizer.decode(outputs[0][input_tensor.shape[1]:], skip_special_token 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: