Merge pull request #82 from ml-explore/llamav2

llama v2 with sharded weights
This commit is contained in:
Awni Hannun
2023-12-12 17:08:24 -08:00
committed by GitHub
9 changed files with 201 additions and 133 deletions

View File

@@ -14,7 +14,7 @@ For example with Homebrew:
brew install git-lfs
```
Download the models from HuggingFace:
Download the models from Hugging Face:
```
git clone https://huggingface.co/someone13574/mixtral-8x7b-32kseqlen
@@ -46,7 +46,7 @@ rm mixtral-8x7b-32kseqlen/*.pth*
As easy as:
```
python mixtral.py --model_path mixtral mixtral-8x7b-32kseqlen/
python mixtral.py --model_path mixtral-8x7b-32kseqlen/
```
[^mixtral]: Refer to Mistral's [blog post](https://mistral.ai/news/mixtral-of-experts/) for more details.