Repository navigation
mimo : support dflash (convert + feature extraction) - #29650
Merged
Merged
Conversation
CISC
approved these changes
Sep 29, 2026
| prefix = "model" if not self.is_mistral_format else "consolidated" | ||
| part_names: list[str] = ModelBase.get_model_part_names(self.dir_model, prefix, ".safetensors") | ||
| is_safetensors: bool = len(part_names) > 0 | ||
| is_safetensors: bool = len(part_names) > 0 or (not self.is_mistral_format and (self.dir_model / "model.safetensors.index.json").is_file()) |
Member
There was a problem hiding this comment.
We should come up with something more clever, but I like this for now.
Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@huggingface.co>
pierreguillot
pushed a commit
to Ircam-Partiels/llama.cpp
that referenced
this pull request
Oct 1, 2026
* convert : update to support dflash * cont : fix Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@huggingface.co> --------- Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@huggingface.co>
frostyautumnleaf
pushed a commit
to frostyautumnleaf/llama.cpp
that referenced
this pull request
Oct 5, 2026
* convert : update to support dflash * cont : fix Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@huggingface.co> --------- Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@huggingface.co>
edwardyoon
pushed a commit
to edwardyoon/focus-llama
that referenced
this pull request
Oct 7, 2026
* convert : update to support dflash * cont : fix Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@huggingface.co> --------- Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@huggingface.co> (cherry picked from commit 22bdcc4)
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
2 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.
Overview
Add support for MiMo v2.6 DFlash. Based on notes from https://huggingface.co/TrevorJS/MiMo-V2.6-Flash-RL-GGUF + help from @am17an.
Currently works with CUDA, but the Metal backend produces NaN - to be investigated.Edit: the Metal issues are unrelated -> will be fixed in follow-up PRModels: https://huggingface.co/ggml-org/MiMo-V2.6-Flash-MOPD-GGUF
Requirements