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.

Sign up for GitHub

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

Jump to bottom

fix(code-interpreter): use llama for preprocessing #22

Merged
merged 1 commit into from
Oct 25, 2024
Merged

fix(code-interpreter): use llama for preprocessing #22

merged 1 commit into from
Oct 25, 2024

Conversation

JanPokorny
Copy link
Contributor

No description provided.

@JanPokorny JanPokorny requested a review from jezekra1 October 22, 2024 16:14
@JanPokorny JanPokorny force-pushed the janpokorny/fix-code-interpreter-use-llama-for-preprocessing branch from 380b731 to 673587b Compare October 22, 2024 16:14
@JanPokorny JanPokorny force-pushed the janpokorny/fix-code-interpreter-use-llama-for-preprocessing branch from 673587b to 599d1f2 Compare October 23, 2024 12:16
@JanPokorny JanPokorny marked this pull request as draft October 23, 2024 12:37
@JanPokorny
Copy link
Contributor Author

image
It does this in certain cases, I have to improve the prompt.

@JanPokorny JanPokorny force-pushed the janpokorny/fix-code-interpreter-use-llama-for-preprocessing branch from 599d1f2 to 4ce31a7 Compare October 23, 2024 13:13
@JanPokorny JanPokorny marked this pull request as ready for review October 23, 2024 13:13
@jezekra1
Copy link
Contributor

Can we make this configurable through env variable so that you can switch between llama and granite?

Also, does it make sense for llama to fix code written by llama?

@JanPokorny
Copy link
Contributor Author

@jezekra1

  1. Potentially, but why? Easier rollback if this one shows issues? There are known issues with Granite (like mangling certain filenames) so I don't think we want to have it as an option.
  2. Yes, LLM output can often improved by just feeding it in again and saying "fix your mistakes", so I don't see the issue with this being the same LLM

@JanPokorny JanPokorny force-pushed the janpokorny/fix-code-interpreter-use-llama-for-preprocessing branch from 4ce31a7 to d59bf7e Compare October 24, 2024 08:11
@JanPokorny JanPokorny requested a review from a team as a code owner October 24, 2024 08:11
@JanPokorny JanPokorny merged commit b709b3b into main Oct 25, 2024
6 checks passed
@JanPokorny JanPokorny deleted the janpokorny/fix-code-interpreter-use-llama-for-preprocessing branch October 25, 2024 09:40
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Reviewers

@xjacka xjacka xjacka approved these changes

@jezekra1 jezekra1 Awaiting requested review from jezekra1

Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

Successfully merging this pull request may close these issues.
3 participants
@JanPokorny @jezekra1 @xjacka