CS348Project/llama.cpp
5
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-10-31 08:51:55 +00:00
Code Issues Packages Projects Releases Wiki Activity

Don't crash on ftype (formerly f16) == 4 (#917)

Browse Source
This commit is contained in:
Stephan Walter
2023-04-12 15:06:16 +00:00
committed by GitHub
parent f76cb3a34d
commit e7f6997f89
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

@@ -827,7 +827,9 @@ 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();