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

add Q4_2

Browse source
This commit is contained in:
qwopqwop200 2023-04-13 14:53:23 +09:00 • committed by GitHub
parent 716bd8fcfa
commit f0b14e8c69
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
1 changed files with 2 additions and 0 deletions
Download patch file Download diff file Expand all files Collapse all files

2
llama.h
View file

@ -72,6 +72,8 @@ 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_SOME_F16 = 6, // except 1d tensors
};
LLAMA_API struct llama_context_params llama_context_default_params();