Add tiny Qwen3-4B-Instruct-2507#5586
Merged
Merged
Conversation
|
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. |
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
#5470 (comment) flagged that Qwen3-4B-Instruct-2507 uses a different chat template than other Qwen3 model.
This PR adds a tiny version of Qwen3 using this other template. Next PR -> #5574
Note
Low Risk
Low risk: this only adds a new tiny test model variant and wires it into existing parameterized test matrices, without changing runtime library behavior.
Overview
Adds a new tiny model fixture for
Qwen/Qwen3-4B-Instruct-2507(published astrl-internal-testing/tiny-Qwen3ForCausalLM-Instruct-2507) so unit tests can cover Qwen3’s alternate non-thinking chat template.Updates the relevant parameterized test lists (chat template/tool-calling, data utils chat-template application, and chunked LM head coverage) to include the new tiny model ID.
Reviewed by Cursor Bugbot for commit 7b162f9. Bugbot is set up for automated code reviews on this repo. Configure here.