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

Fix mistake

Browse source
This commit is contained in:
Nexesenex 2024-08-19 16:02:00 +02:00
parent caeb839ae3
commit a7f91643bb
1 changed files with 1 additions and 1 deletions
Download patch file Download diff file Expand all files Collapse all files

2
src/llama.cpp
View file

@ -16202,7 +16202,7 @@ static ggml_type llama_tensor_get_type(quantize_state_internal & qs, ggml_type n
if (qs.model.hparams.n_expert >= 4) new_type = GGML_TYPE_Q4_K;
else {
if (ftype == LLAMA_FTYPE_MOSTLY_IQ1_XS || ftype == LLAMA_FTYPE_MOSTLY_IQ1_S ||
ftype == LLAMA_FTYPE_MOSTLY_IQ1_M || LLAMA_FTYPE_MOSTLY_IQ1_XL) new_type = GGML_TYPE_IQ2_XXS;
ftype == LLAMA_FTYPE_MOSTLY_IQ1_M || ftype == LLAMA_FTYPE_MOSTLY_IQ1_XL) new_type = GGML_TYPE_IQ2_XXS;
else if (ftype == LLAMA_FTYPE_MOSTLY_IQ2_S) new_type = GGML_TYPE_IQ2_S;
else if (ftype == LLAMA_FTYPE_MOSTLY_IQ2_M) new_type = GGML_TYPE_IQ3_XXS;
}