]> git.djapps.eu Git - pkg/ggml/sources/llama.cpp/commit
model: mistral small 4 support (#20649)
authorXuan-Son Nguyen <redacted>
Mon, 16 Mar 2026 23:31:14 +0000 (00:31 +0100)
committerGitHub <redacted>
Mon, 16 Mar 2026 23:31:14 +0000 (00:31 +0100)
commitd34ff7eb5ba289bd61f659c8f3f48c983c3ce4f8
treed0a7d376bc1ae01c9b776865fd8df31172c47972
parent45172df4d6843a903ad7dcb84c83388094f896bb
model: mistral small 4 support (#20649)

* model: mistral small 4 support

* fix test

* fix test (2)

* Apply suggestions from code review

Co-authored-by: Sigbjørn Skjæret <redacted>
* Update convert_hf_to_gguf.py

Co-authored-by: Sigbjørn Skjæret <redacted>
* change newline

---------

Co-authored-by: Sigbjørn Skjæret <redacted>
convert_hf_to_gguf.py
gguf-py/gguf/constants.py
src/llama-arch.cpp
src/llama-arch.h
src/llama-model.cpp
tests/test-llama-archs.cpp