]> git.djapps.eu Git - pkg/ggml/sources/llama.cpp/commit
overview / pkg / ggml / sources / llama.cpp / commit
summary | shortlog | log | commit | commitdiff | tree
(parent: db44417)
convert : Mistral format yarn apply_scale support (#22612)
authorJulien Denize <redacted>
Sun, 3 May 2026 19:51:21 +0000 (21:51 +0200)
committerGitHub <redacted>
Sun, 3 May 2026 19:51:21 +0000 (21:51 +0200)
commit048a490f763708b84f186078559c0929ed3fcd9c
tree86e02cbc66061eac3ebec5ded2e9ec573066aa37tree
parentdb44417b027cff147f7de85e7da22bc6a3a804fbcommit | diff
convert :  Mistral format yarn apply_scale support (#22612)

* [BUGFIX] Mistral format apply_scale support.

* Update convert_hf_to_gguf.py

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

---------

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