]> git.djapps.eu Git - pkg/ggml/sources/llama.cpp/commit
overview / pkg / ggml / sources / llama.cpp / commit
summary | shortlog | log | commit | commitdiff | tree
(parent: 446595b)
llama : fix kq_scale for the attention layers of PLaMo2 (#14892)
authorShunta Saito <redacted>
Sun, 27 Jul 2025 07:38:44 +0000 (16:38 +0900)
committerGitHub <redacted>
Sun, 27 Jul 2025 07:38:44 +0000 (09:38 +0200)
commit1dc9614e0673e794d2e2bf88ba04f7d57b63a57b
tree5c0239f10ff2ed23a051ccba3019c86ab20681c4tree
parent446595b9b3a113d9ba10506922c3a156cca9d477commit | diff
llama : fix kq_scale for the attention layers of PLaMo2 (#14892)

* Fix dimensions for expand

* Change dimensions to copy states to cache

* Fix the default value for plamo2 conversion

* Fix scale given to build_attn

* Update src/llama-model.cpp

Co-authored-by: Sigbjørn Skjæret <redacted>
* Update src/llama-model.cpp

Co-authored-by: Sigbjørn Skjæret <redacted>
* Update src/llama-model.cpp

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

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