[bugfix] Fix DataCollatorForChatML unexpected generation prompt #2450
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
|
thanks @NIL-zhuang great catch! |
kashif
approved these changes
Dec 11, 2024
|
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. |
|
Do we test this collator somewhere? |
|
we do test it.. but more for the labels rather than the content of the ids... let me see if i can add a failing test |
kashif
reviewed
Dec 11, 2024
kashif
reviewed
Dec 11, 2024
kashif
reviewed
Dec 11, 2024
|
@qgallouedec added failng tests |
kashif
reviewed
Dec 11, 2024
kashif
reviewed
Dec 11, 2024
kashif
approved these changes
Dec 11, 2024
kashif
reviewed
Dec 11, 2024
kashif
approved these changes
Dec 11, 2024
yaricom
pushed a commit
to yaricom/trl
that referenced
this pull request
Dec 11, 2024
…ingface#2450) * [bugfix] Fix DataCollatorForChatML unexpected generation prompt * Update utils.py * Update test_utils.py * Update tests/test_utils.py * Update tests/test_utils.py * Update tests/test_utils.py * Update tests/test_utils.py * Update test_utils.py * Update tests/test_utils.py * Update tests/test_utils.py --------- Co-authored-by: Kashif Rasul <kashif.rasul@gmail.com>
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Outdated suggestions cannot be applied.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?
Fixes #2449
Fix DataCollatorForChatML unexpected generation prompt
DataCollatorForChatML will add generation prompt like
<|start_header_id|>assistant<|end_header_id|>after model response, which is not suitable for instruction tuning, as is referred in #2449Before submitting
Pull Request section?
to it if that's the case. DataCollatorForChatML unexpected generation prompt #2449
documentation guidelines. Will do it afterwards if necessary.
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.