Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

point 1 download from hugginface is not clear #33

Open
mirecta opened this issue Sep 27, 2024 · 1 comment
Open

point 1 download from hugginface is not clear #33

mirecta opened this issue Sep 27, 2024 · 1 comment

Comments

@mirecta
Copy link

mirecta commented Sep 27, 2024

Download the Llama-3.1-8B-Omni model from 🤗Huggingface.
after click to link i will go to the page which looks similar to this but its not clear what exactly i must download an where i must save it . So i freeze at this step

@SteinsHead
Copy link

SteinsHead commented Sep 28, 2024

I recently ran this project, so I should be able to help you with this problem.
Start by selecting a directory to hold the model, such as models/. Then run the following two commands in sequence in the models directory to download all the model files you need. When you run the run.sh script, change the model-path option to save the model for you. And don't forget to install git-lfs locally

GIT_LFS_SKIP_SMUDGE=1 git clone https://huggingface.co/ICTNLP/Llama-3.1-8B-Omni
cd Llama-3.1-8B-Omni/
git lfs pull --include="*.safetensors"

These two commands should also be used when you download other models

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

2 participants