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

Add an auto-download script that supports 7B, 13B & 30B models #14

Merged
merged 2 commits into from
Mar 22, 2023

Conversation

nsarrazin
Copy link
Member

This PR ads an autodownload script that fetches the model weights from huggingface. This simplifies the initial setup of Serge to just :

git clone git@github.com:nsarrazin/serge.git && cd serge

cp .env.sample .env

docker compose up -d
docker compose exec api python3 /usr/src/app/utils/download.py tokenizer 7B

This also adds support for the 30B theoretically, although I haven't tried it.

This PR closes #2, #13

@nsarrazin nsarrazin merged commit 48bc3dc into main Mar 22, 2023
@nsarrazin nsarrazin deleted the feature/add_support_for_all_models branch March 23, 2023 05:16
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

Successfully merging this pull request may close these issues.

Replace hardcoded tweaks to llama.cpp with a more permanent solution
1 participant