deepseek-ai / DeepSeek-V2

DeepSeek-V2: A Strong, Economical, and Efficient Mixture-of-Experts Language Model
MIT License
3.6k stars 153 forks source link

hi, could you provide a code like llama3? #53

Open lambda7xx opened 5 months ago

lambda7xx commented 5 months ago

hi, Dear DeepSeek team:

if your team could provide a implementation like https://github.com/meta-llama/llama3/tree/main/llama, it will be great. Llama3 is very helpful to learn.

SupercarryNg commented 4 months ago

Maybe you are looking for https://huggingface.co/deepseek-ai/DeepSeek-V2-Lite/blob/main/modeling_deepseek.py

lambda7xx commented 4 months ago

Maybe you are looking for https://huggingface.co/deepseek-ai/DeepSeek-V2-Lite/blob/main/modeling_deepseek.py

I think if the deepseek team can maintain a repo like llama, it will be great. In llama repo, it has a model implementation and a example to run the model(https://github.com/meta-llama/llama3/blob/main/example_text_completion.py).