Enable RL training from base model #44
Closed
Conversation
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
Collaborator
|
I'd recommend deleting the newly defined |
pan-x-c
reviewed
May 23, 2025
| messages.append({"role": "assistant", "content": self.reply_prefix}) | ||
| return messages | ||
|
|
||
| def format_prompt(self): |
Collaborator
There was a problem hiding this comment.
Add a new workflow named BaseModelWorkflow may be better.
pan-x-c
reviewed
May 23, 2025
| # for unpaired preference dataset | ||
| label_key: str = "" | ||
|
|
||
| use_base_format: bool = False |
Collaborator
There was a problem hiding this comment.
Using a new workflow type can do the same thing. Don't add a new field here.
Collaborator
Author
|
The corresponding changes will the addressed in another PR. Close this PR for now. |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
3 participants
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Outdated suggestions cannot be applied.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.
Description
The workflow don't support training from base model since we are using self.model.chat instead of self.model.generate; This PR should enable training from base model.
Checklist
Please check the following items before code is ready to be reviewed.