Conversation
Downstream tasks will now be able to specify questions to train with rather than being forced to use the ones here.
|
❗ The branch name In order to correctly link this PR to an issue, the branch name should be prefixed with the relevant issue number. Please recreate this PR using required branch name structure (e.g. |
dearden
added this pull request to stack #8
September 10, 2026 09:58
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
Removes hardcoded questions from PASTEL, so now they have to be given to the model.
This means that you don't have to update pastel repo every time you want to try new questions.
Pull request checklist
/reviewmy PR, and reviewed any LLM generated code myself