Update llama.cpp

This commit is contained in:
Andrei Betlen
2023-04-25 19:03:41 -04:00
parent 3cab3ef4cb
commit cbd26fdcc1
2 changed files with 2 additions and 1 deletions

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_MOSTYL_Q4_3 = ctypes.c_int(6) # except 1d tensors
LLAMA_FTYPE_MOSTYL_Q8_0 = ctypes.c_int(7) # except 1d tensors
# Functions