Fixed get_rel_pos & add_rel_pos_inplace operator#3
Merged
sfallah merged 9 commits intosfallah:sf/deepseek-ocrfrom Nov 22, 2025
Merged
Fixed get_rel_pos & add_rel_pos_inplace operator#3sfallah merged 9 commits intosfallah:sf/deepseek-ocrfrom
sfallah merged 9 commits intosfallah:sf/deepseek-ocrfrom
Conversation
…ut in deepseek2 model
|
Hi! I’ve been quietly following this fork from the shadows for a while, and you’re doing an amazing job 😊 Thank you so much! |
Collaborator
Author
|
Halfway, I guess? We've implemented the LM component and are tackling/debugging the vision model. Should be done soon!! |
Owner
|
@Juste-Leo2 |
Collaborator
Author
|
@sfallah I reviewed the code, fixed some minor bugs and just made it more readable/reusable. Nice!! |
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Make sure to read the contributing guidelines before submitting a PR
Fixed get_rel_pos and have tested it aligns with the original implementation. #2
I gotta go to bed (2:00 am here) and will take a look at add_rel_pos_inplace as soon as I get up.