Update tokenizer apply_chat_template with return_dict=True default #4448
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
albertvillanova
changed the title
|
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. |
qgallouedec
approved these changes
Nov 4, 2025
Member
qgallouedec
left a comment
qgallouedec
left a comment
There was a problem hiding this comment.
I was expecting more, cool!
qgallouedec
added a commit
to Harras3/trl
that referenced
this pull request
Nov 4, 2025
commit 7a9592b Author: Quentin Gallouédec <[email protected]> Date: Tue Nov 4 14:32:04 2025 -0700 🐍 Drop Python 3.9 (huggingface#4183) commit 7f15a7f Author: Harras Mansoor <[email protected]> Date: Wed Nov 5 02:06:31 2025 +0500 Removed outdated warning about batch contamination (huggingface#4423) commit 8b0a3ce Author: Albert Villanova del Moral <[email protected]> Date: Tue Nov 4 21:37:39 2025 +0100 Update tokenizer apply_chat_template with return_dict=True default (huggingface#4448) commit d9f9e2b Author: Pramodith Ballapuram <[email protected]> Date: Tue Nov 4 19:56:58 2025 +0000 Support casting to fp32 when word embeddings are tied to lm_head (huggingface#4446) commit 4e138ab Author: Sergio Paniego Blanco <[email protected]> Date: Tue Nov 4 15:15:23 2025 +0100 Upload notebook with T4 selected (huggingface#4449)
qgallouedec
added a commit
that referenced
this pull request
Nov 4, 2025
commit 4677cf2 Author: Harras Mansoor <[email protected]> Date: Wed Nov 5 04:06:13 2025 +0500 Removed Sentiment Tuning Examples (#4424) commit 7a9592b Author: Quentin Gallouédec <[email protected]> Date: Tue Nov 4 14:32:04 2025 -0700 🐍 Drop Python 3.9 (#4183) commit 7f15a7f Author: Harras Mansoor <[email protected]> Date: Wed Nov 5 02:06:31 2025 +0500 Removed outdated warning about batch contamination (#4423) commit 8b0a3ce Author: Albert Villanova del Moral <[email protected]> Date: Tue Nov 4 21:37:39 2025 +0100 Update tokenizer apply_chat_template with return_dict=True default (#4448) commit d9f9e2b Author: Pramodith Ballapuram <[email protected]> Date: Tue Nov 4 19:56:58 2025 +0000 Support casting to fp32 when word embeddings are tied to lm_head (#4446) commit 4e138ab Author: Sergio Paniego Blanco <[email protected]> Date: Tue Nov 4 15:15:23 2025 +0100 Upload notebook with T4 selected (#4449) commit 43253b2 Author: Pramodith Ballapuram <[email protected]> Date: Mon Nov 3 21:07:31 2025 +0000 Add On-Policy Distillation from thinking labs to paper index. (#4410) Co-authored-by: Quentin Gallouédec <[email protected]> commit 6f41b18 Author: Behrooz Azarkhalili <[email protected]> Date: Mon Nov 3 10:57:51 2025 -0800 fix: Remove chat template setting from non-SFT trainer scripts (#4437) Co-authored-by: Quentin Gallouédec <[email protected]> Co-authored-by: Quentin Gallouédec <[email protected]>
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.
Pass explicitly
return_dict=Truetoapply_chat_templateand get itsinput_idskey.This PR fixes the issue:
Fix #4447.
Note that
transformershas recently setreturn_dict=Trueas the default value:This PR updates the tokenization logic in the
tokenize_fnfunction oftrl/trainer/reward_trainer.pyto improve compatibility with the default output format ofapply_chat_template. Instead of assumingreturn_dict=Falseand directly returning the result, it now requests a dictionary and extracts only theinput_idsfield.Tokenization logic update:
apply_chat_templatemethod is now called withreturn_dict=True, and only theinput_idsfrom the returned dictionary are used for both thechosenandrejectedexamples.