vbatts/llama.cpp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

Fixed copy/paste mistake

Browse source
This commit is contained in:
Iwan Kawrakow 2023-06-19 11:39:47 +03:00
parent 510b537d42
commit 986a56e2b2
1 changed files with 1 additions and 1 deletions
Download patch file Download diff file Expand all files Collapse all files

2
llama.cpp
View file

@ -2506,7 +2506,7 @@ static void llama_model_quantize_internal(const std::string & fname_inp, const s
if (tensor.name == "output.weight") { if (tensor.name == "output.weight") {
int nx = tensor.ne.at(0); int nx = tensor.ne.at(0);
int ny = tensor.ne.at(1); int ny = tensor.ne.at(1);
if (nx % QK_K == 0 || ny % QK_K == 0) { if (nx % QK_K == 0 && ny % QK_K == 0) {
new_type = GGML_TYPE_Q6_K; new_type = GGML_TYPE_Q6_K;
} }
} else if (tensor.name.find("attention.wv.weight") != std::string::npos) { } else if (tensor.name.find("attention.wv.weight") != std::string::npos) {