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

ggml : remove Q4_2 mode

Browse source
This commit is contained in:
Georgi Gerganov 2023-05-07 18:26:59 +03:00
parent b47bd2877f
commit 7cdc08a5d1
No known key found for this signature in database
GPG key ID: 449E073F9DC10735
7 changed files with 8 additions and 366 deletions
Download patch file Download diff file Expand all files Collapse all files

2
llama.h
View file

@ -78,7 +78,7 @@ extern "C" {
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_FTYPE_MOSTLY_Q4_2 = 5, // except 1d tensors
// LLAMA_FTYPE_MOSTLY_Q4_2 = 5, // support has been removed
// LLAMA_FTYPE_MOSTLY_Q4_3 (6) support has been removed
LLAMA_FTYPE_MOSTLY_Q8_0 = 7, // except 1d tensors
LLAMA_FTYPE_MOSTLY_Q5_0 = 8, // except 1d tensors