Add xdrope for HunyuanOCR (even though does not seem to improve results) - #281
Merged
Conversation
…code are broken the position_ids are not computed properly and batch not supported
There was a problem hiding this comment.
Pull request overview
Copilot reviewed 9 out of 10 changed files in this pull request and generated 5 comments.
💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
This PR adds support for "xdrope" which hunyuanOCR supposedly uses.
In fact their xdrope is close to mRope used by Qwen VL (we need to revisit when implementing this one)
The big issue is that hunyuanOCR xdrope is broken in both vLLM and HF as of the time of this PR.
batching is not supported in their code
pos_h/pos_w are not properly computed
AND they forgot to build the block diagonal mask when handling multiple images.
This PR fixes all of this BUT I just hope training was done accurately.
Anyway outputs are quite good with and without xdrope.