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

Merge branch 'master' into concedo

Browse source
This commit is contained in:
Concedo 2023-04-12 23:25:45 +08:00
commit f4257a8eef
2 changed files with 4 additions and 1 deletions
Download patch file Download diff file Expand all files Collapse all files

4
llama.cpp
View file

@ -834,7 +834,9 @@ static const char *llama_ftype_name(enum llama_ftype ftype) {
case LLAMA_FTYPE_MOSTLY_F16: return "mostly F16";
case LLAMA_FTYPE_MOSTLY_Q4_0: return "mostly Q4_0";
case LLAMA_FTYPE_MOSTLY_Q4_1: return "mostly Q4_1";
default: LLAMA_ASSERT(false);
case LLAMA_FTYPE_MOSTLY_Q4_1_SOME_F16:
return "mostly Q4_1, some F16";
default: return "unknown, may not work";
}
}

1
llama.h
View file

@ -71,6 +71,7 @@ extern "C" {
LLAMA_FTYPE_MOSTLY_F16 = 1, // except 1d tensors
LLAMA_FTYPE_MOSTLY_Q4_0 = 2, // except 1d tensors
LLAMA_FTYPE_MOSTLY_Q4_1 = 3, // except 1d tensors
LLAMA_FTYPE_MOSTLY_Q4_1_SOME_F16 = 4, // tok_embeddings.weight and output.weight are F16
};
LLAMA_API struct llama_context_params llama_context_default_params();