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

Update llama_cpp.py

Browse source
This commit is contained in:
Matt Hoffner 2023-05-01 20:40:06 -07:00 committed by GitHub
parent e9e0654aed
commit f97ff3c5bb
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
1 changed files with 3 additions and 3 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

6
llama_cpp/llama_cpp.py
View file

@ -136,9 +136,9 @@ 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_MOSTYL_Q4_3 = ctypes.c_int(6) # except 1d tensors
LLAMA_FTYPE_MOSTYL_Q8_0 = ctypes.c_int(7) # except 1d tensors
LLAMA_FTYPE_MOSTYL_Q5_0 = ctypes.c_int(8) # except 1d tensors
LLAMA_FTYPE_MOSTYL_Q5_1 = ctypes.c_int(9) # except 1d tensors
LLAMA_FTYPE_MOSTLY_Q8_0 = ctypes.c_int(7) # except 1d tensors
LLAMA_FTYPE_MOSTLY_Q5_0 = ctypes.c_int(8) # except 1d tensors
LLAMA_FTYPE_MOSTLY_Q5_1 = ctypes.c_int(9) # except 1d tensors
# Functions