]> git.djapps.eu Git - pkg/ggml/sources/llama.cpp/commit
overview / pkg / ggml / sources / llama.cpp / commit
summary | shortlog | log | commit | commitdiff | tree
(parent: 847eedb)
gemma : use more bits for the token_embd.weight tensor (#5650)
authorGeorgi Gerganov <redacted>
Thu, 22 Feb 2024 21:23:46 +0000 (23:23 +0200)
committerGitHub <redacted>
Thu, 22 Feb 2024 21:23:46 +0000 (23:23 +0200)
commit96633eeca1265ed03e57230de54032041c58f9cd
treef3e0370d7f304666030968a4f0fb8a36f693b605tree
parent847eedbdb2d1ebf14ef56eb507d4b4b975510908commit | diff
gemma : use more bits for the token_embd.weight tensor (#5650)

* gemma : use Q8_0 for the token_embd.weight tensor

* llama : quantize token_embd.weight using output type
llama.cpp diff | blob | history
Packaging of ggml-org/llama.cpp