]> git.djapps.eu Git - pkg/ggml/sources/llama.cpp/commit
overview / pkg / ggml / sources / llama.cpp / commit
summary | shortlog | log | commit | commitdiff | tree
(parent: f77a8ff)
llama : correction of the attn.v.weight quantization for IQ3_XS (#6209)
authorNexesenex <redacted>
Fri, 22 Mar 2024 13:32:02 +0000 (14:32 +0100)
committerGitHub <redacted>
Fri, 22 Mar 2024 13:32:02 +0000 (15:32 +0200)
commite80f06d2a194be62ab5b1cd7ef7c7a5b241dd4fb
treeecd5d09b0c627826dd50d419f8cec057c4805d11tree
parentf77a8ffd3bbde77b7819823b0c006fd8c2d5cae4commit | diff
llama : correction of the attn.v.weight quantization for IQ3_XS (#6209)

IQ3_XS was not mentioned, IQ3_S and IQ3_M were present twice.

That PR corrects this in the manner which was probably intended initially.
llama.cpp diff | blob | history
Packaging of ggml-org/llama.cpp