convert: support Mistral 3 Large MoE #17730
Open
+185
−83
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
ngxson
changed the title
Contributor
|
So far so good with this, in a couple hours will be able to test generation |
Contributor
|
seems to work and produce coherent results! |
Collaborator
Author
|
This PR still needs to be clean up before it is ready for review 😅 |
ngxson
changed the title
CISC
approved these changes
Dec 3, 2025
Comment on lines
+9941
to
+9942
| # remap hparams from Mistral MoE format to DeepseekV2 format | ||
| # we do this way to be able to reuse DeepseekV2Model set_gguf_parameters logic |
Collaborator
There was a problem hiding this comment.
Somewhat ugly but an acceptable trade-off.
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Outdated suggestions cannot be applied.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.
WIP, the code is quite ugly for now, but just want to get it to work.
Remember to convert with the
--mistral-formatargument, as the weight is not yet transformers-compatibleOutput
F16 weight is 1.35 TerabytesQ8_0 weight is 716GB and I don't have enough hw to test itEdit: thanks @bartowski1182 for testing it!
NOTE: this PR only covers the conversion to GGUF. the C++ code still missing llama 4 scaling to work, but it will be another PR