feat: support mm_token_type_ids and 3D RoPE alignment for Qwen2/3-VL …#437
Open
Wangxiaoxiaoa wants to merge 1 commit intoalibaba:mainfrom
Open
feat: support mm_token_type_ids and 3D RoPE alignment for Qwen2/3-VL …#437Wangxiaoxiaoa wants to merge 1 commit intoalibaba:mainfrom
Wangxiaoxiaoa wants to merge 1 commit intoalibaba:mainfrom
Conversation
|
|
Wangxiaoxiaoa
force-pushed
the
feat/qwen_vl_support
branch
from
dec9235 to
c8122a3
Compare
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
2 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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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
This PR introduces the missing support for
mm_token_type_idsand binds the necessary 3D RoPE position generation methods for Qwen2-VL and Qwen3-VL models.Changes:
1. Added logic in
DataCollatorWithPaddingForMMto properly padmm_token_type_idsbased on the tokenizer'spadding_side.2. Added dynamic binding for
get_vision_position_idsand generation logic for multimodal token types inmodel_providers.pyto ensure correct 3D positional embeddings calculation during forward pass.Fixes #436
Type of change