Add special token to PRM vocabulary if not present #2646
Conversation
This file contains 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
qgallouedec
reviewed
Jan 24, 2025
qgallouedec
reviewed
Jan 24, 2025
Comment on lines
+93
to
+102
| # Check if the step separator is in the vocabulary, if it's not, add it | ||
| if not is_token_in_vocab(tokenizer, training_args.step_token): | ||
| tokenizer.add_special_tokens({"additional_special_tokens": [training_args.step_separator]}) | ||
| model.resize_token_embeddings( | ||
| len(tokenizer), | ||
| pad_to_multiple_of=( | ||
| training_args.resize_to_multiple_of if training_args.resize_to_multiple_of is not None else None | ||
| ), | ||
| ) | ||
|
|
There was a problem hiding this comment.
WDYT of having it inside the PRM trainer?
There was a problem hiding this comment.
makes sense, will update the code
|
The docs for this PR live here. All of your documentation changes will be reflected on that endpoint. The docs are available until 30 days after the last update. |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
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Outdated suggestions cannot be applied.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.
What does this PR do?
It checks if the
step_separatortoken is present in the vocabulary of the model's tokenizer, and adds if it that's not the case. By default it uses<step_token>similar to Qwen's PRM from The Lessons of Developing Process Reward Models in Mathematical Reasoning<extra_0>.Before submitting
Pull Request section?
to it if that's the case.
documentation guidelines.
Who can review?
Anyone in the community is free to review the PR once the tests have passed. Feel free to tag
members/contributors who may be interested in your PR.