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

llama : valign + remove unused ftype (#8502)

Browse source
This commit is contained in:
Georgi Gerganov 2024-07-16 10:00:30 +03:00 • committed by GitHub
parent 7acfd4e8d5
commit 0efec57787
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
3 changed files with 72 additions and 76 deletions
Download patch file Download diff file Expand all files Collapse all files

2
include/llama.h
View file

@ -133,7 +133,7 @@ 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_FTYPE_MOSTLY_Q4_1_SOME_F16 = 4, // tok_embeddings.weight and output.weight are F16
// 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