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

Update llama.cpp - remove trailing space

Browse source
This commit is contained in:
Nexesenex 2024-03-26 09:17:09 +01:00 • committed by GitHub
parent 62c1f5b681
commit d1839362fc
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
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

@ -12486,7 +12486,7 @@ static ggml_type llama_tensor_get_type(quantize_state_internal & qs, ggml_type n
if (name.find("attn_k.weight") != std::string::npos) { if (name.find("attn_k.weight") != std::string::npos) {
if (qs.model.hparams.n_expert >= 8) new_type = GGML_TYPE_IQ4_XS; if (qs.model.hparams.n_expert >= 8) new_type = GGML_TYPE_IQ4_XS;
else if (qs.model.hparams.n_expert >= 4) new_type = GGML_TYPE_IQ3_S; else if (qs.model.hparams.n_expert >= 4) new_type = GGML_TYPE_IQ3_S;
else if (qs.model.hparams.n_expert >= 2) new_type = GGML_TYPE_IQ3_XXS; else if (qs.model.hparams.n_expert >= 2) new_type = GGML_TYPE_IQ3_XXS;
else if (qs.model.hparams.n_gqa() >= 8) new_type = GGML_TYPE_IQ2_S; else if (qs.model.hparams.n_gqa() >= 8) new_type = GGML_TYPE_IQ2_S;
else if (qs.model.hparams.n_gqa() >= 4) new_type = GGML_TYPE_IQ2_XS; else if (qs.model.hparams.n_gqa() >= 4) new_type = GGML_TYPE_IQ2_XS;
else if (qs.model.hparams.n_gqa() >= 2) new_type = GGML_TYPE_IQ2_XXS; else if (qs.model.hparams.n_gqa() >= 2) new_type = GGML_TYPE_IQ2_XXS;