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

Update llama.cpp

Browse source
This commit is contained in:
Andrei Betlen 2023-04-25 19:03:41 -04:00 • committed by Don Mahurin
parent 80c18cb665
commit 656190750d
1 changed files with 1 additions and 0 deletions
Download patch file Download diff file Expand all files Collapse all files

1
examples/llama_cpp.py
View file

@ -119,6 +119,7 @@ LLAMA_FTYPE_MOSTLY_Q4_1_SOME_F16 = ctypes.c_int(
) # tok_embeddings.weight and output.weight are F16
LLAMA_FTYPE_MOSTLY_Q4_2 = ctypes.c_int(5) # except 1d tensors
LLAMA_FTYPE_MOSTLY_Q4_3 = ctypes.c_int(6) # except 1d tensors
LLAMA_FTYPE_MOSTLY_Q8_0 = ctypes.c_int(7) # except 1d tensors
# Functions