Fix conversion mapping for Qwen3VL-MoE#43953
Closed
zucchini-nlp wants to merge 1 commit intohuggingface:mainfrom
Closed
Fix conversion mapping for Qwen3VL-MoE#43953zucchini-nlp wants to merge 1 commit intohuggingface:mainfrom
zucchini-nlp wants to merge 1 commit intohuggingface:mainfrom
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. |
Member
|
Nop, this is not the right conversion. Weights are already merged into the final experts, but need transposition, see #43913! |
Member
|
Though if all weights ONLY need the transpose, that PR would be much simpler actually - gonna check |
Member
Author
Ah right, didn't see that. Indeed, we shouldn't need to merge. In that case no conversion is needed ig |
Member
|
They still need to be transposed 🥲 Finally fixed it in #44037 |
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Fixes #43931, no transpose needed after standardizing the model impl to inherit from Qwen3-MoE