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 2023-04-12 14:29:00 -04:00 • committed by Don Mahurin
parent d595f330e2
commit 3693449c07
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

@ -114,6 +114,7 @@ LLAMA_FTYPE_ALL_F32 = ctypes.c_int(0)
LLAMA_FTYPE_MOSTLY_F16 = ctypes.c_int(1) # except 1d tensors LLAMA_FTYPE_MOSTLY_F16 = ctypes.c_int(1) # except 1d tensors
LLAMA_FTYPE_MOSTLY_Q4_0 = ctypes.c_int(2) # except 1d tensors LLAMA_FTYPE_MOSTLY_Q4_0 = ctypes.c_int(2) # except 1d tensors
LLAMA_FTYPE_MOSTLY_Q4_1 = ctypes.c_int(3) # except 1d tensors LLAMA_FTYPE_MOSTLY_Q4_1 = ctypes.c_int(3) # except 1d tensors
LLAMA_FTYPE_MOSTLY_Q4_1_SOME_F16 = ctypes.c_int(4) # tok_embeddings.weight and output.weight are F16
# Functions # Functions