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 CodeLlama-70b-Instruct-hf #752

Merged
merged 11 commits into from
Jan 30, 2024
Merged

Add CodeLlama-70b-Instruct-hf #752

merged 11 commits into from
Jan 30, 2024

Conversation

nsarrazin
Copy link
Collaborator

This PR adds CodeLlama-70b-Instruct-hf to HuggingChat. I had to make sure we were properly stripping the end tokens, but here we go, it should work!

@nsarrazin nsarrazin added the models This issue is related to model performance/reliability label Jan 30, 2024
@gary149 gary149 requested review from gary149 and mishig25 January 30, 2024 09:02
Copy link
Collaborator

@mishig25 mishig25 left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

lgtm!

@nsarrazin nsarrazin merged commit a8ca669 into main Jan 30, 2024
3 checks passed
@nsarrazin nsarrazin deleted the model/codellama_70b branch January 30, 2024 10:39
ice91 pushed a commit to ice91/chat-ui that referenced this pull request Oct 30, 2024
* Add CodeLlama-70b-Instruct-hf

* add comment to reduce

* Added missing newlines to prompt format for codellama 70b

* remove extra space

* stop tokens

* Remove source newline

* fix preprompt

* fix prompt one last time

* add news

* shorter text

* fix link & remove old tokens

---------

Co-authored-by: Mishig Davaadorj <dmishig@gmail.com>
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
models This issue is related to model performance/reliability
Projects
None yet
Development

Successfully merging this pull request may close these issues.

2 participants