convert : fix duplicate key DeepSeek-R1 conversion error #14103
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
ericcurtin
approved these changes
Jun 10, 2025
There was a problem hiding this comment.
Pull Request Overview
This PR adds a guard to avoid writing duplicate key/value lengths when head_dim from AutoConfig is incorrect for DeepSeekV3.
- Adds a conditional check comparing
qk_rope_head_dimtohead_dimbefore callingadd_key_lengthandadd_value_length - Documents the workaround with a comment pointing to the relevant Transformers config file
Comments suppressed due to low confidence (1)
convert_hf_to_gguf.py:558
- Introduce a dedicated test for the DeepSeekV3 conversion path to cover this workaround and ensure future changes to
head_dimhandling don’t regress.
if (head_dim := self.hparams.get("head_dim")) is not None:
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Outdated suggestions cannot be applied.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.
Since DeepSeekV3 support was merged into
transformersAutoConfigstarted returning an incorrecthead_dimvalue.Fixes #14093