FIX Prefix tuning with Qwen3 issue #2883
Merged
Conversation
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
|
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. |
Doesn't happen in from source install of transfomers ...
BenjaminBossan
commented
Oct 31, 2025
| ) | ||
|
|
||
| if peft_config.is_prompt_learning: | ||
| peft_config = _prepare_prompt_learning_config(peft_config, model_config) |
Member
Author
There was a problem hiding this comment.
While debugging this issue, I noticed that _prepare_prompt_learning_config is being called twice, here and in peft_model.py:
Line 1019 in d43b315
This is not a huge deal, as the results should be the same and because the function is quick. Still, let's remove the redundant call here.
Member
Author
|
@githubnemo I wanted to ask Cyril or Raushan if the fix is reasonable, but they're both OoO right now. |
githubnemo
approved these changes
Nov 5, 2025
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Outdated suggestions cannot be applied.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.
Resolves #2881.
Use
model_config["head_dim"]instead ofpeft_config.token_dim // peft_config.num_attention_headsif it exists.