]> git.djapps.eu Git - pkg/ggml/sources/llama.cpp/commit
overview / pkg / ggml / sources / llama.cpp / commit
summary | shortlog | log | commit | commitdiff | tree
(parent: c6c5e85)
convert: support Mistral 3 Large MoE (#17730)
authorXuan-Son Nguyen <redacted>
Sat, 6 Dec 2025 09:49:33 +0000 (10:49 +0100)
committerGitHub <redacted>
Sat, 6 Dec 2025 09:49:33 +0000 (10:49 +0100)
commitdbc15a79672e72e0b9c1832adddf3334f5c9229c
treefc12470c20df3844afafcf8074eb21cd41c3ee68tree
parentc6c5e859798163c2e41d848d1157438467a2a34acommit | diff
convert: support Mistral 3 Large MoE (#17730)

* convert: support Mistral 3 Large MoE

* filter out vision tensors, add missing keys

* handle vocab

* add temperature_length

* fix mscale_all_dim

* clean up

* Apply suggestions from code review

Co-authored-by: Sigbjørn Skjæret <redacted>
* fix

* Update gguf-py/gguf/tensor_mapping.py

Co-authored-by: Sigbjørn Skjæret <redacted>
---------

Co-authored-by: Sigbjørn Skjæret <redacted>
convert_hf_to_gguf.py diff | blob | history
gguf-py/gguf/tensor_mapping.py diff | blob | history
Packaging of ggml-org/llama.cpp