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

Update llama.cpp

Browse source
This commit is contained in:
Andrei Betlen 2024-01-11 22:51:12 -05:00
parent f0159663d9
commit bb610b9428
2 changed files with 6 additions and 1 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

5
llama_cpp/llama_cpp.py
View file

@ -180,6 +180,8 @@ LLAMA_TOKEN_TYPE_BYTE = 6
# LLAMA_FTYPE_MOSTLY_Q5_K_M = 17, // except 1d tensors # LLAMA_FTYPE_MOSTLY_Q5_K_M = 17, // except 1d tensors
# LLAMA_FTYPE_MOSTLY_Q6_K = 18, // except 1d tensors # LLAMA_FTYPE_MOSTLY_Q6_K = 18, // except 1d tensors
# LLAMA_FTYPE_MOSTLY_IQ2_XXS = 19, // except 1d tensors # LLAMA_FTYPE_MOSTLY_IQ2_XXS = 19, // except 1d tensors
# LLAMA_FTYPE_MOSTLY_IQ2_XS = 20, // except 1d tensors
# LLAMA_FTYPE_MOSTLY_Q2_K_S = 21, // except 1d tensors
# LLAMA_FTYPE_GUESSED = 1024, // not specified in the model file # LLAMA_FTYPE_GUESSED = 1024, // not specified in the model file
# }; # };
@ -200,6 +202,9 @@ LLAMA_FTYPE_MOSTLY_Q4_K_M = 15
LLAMA_FTYPE_MOSTLY_Q5_K_S = 16 LLAMA_FTYPE_MOSTLY_Q5_K_S = 16
LLAMA_FTYPE_MOSTLY_Q5_K_M = 17 LLAMA_FTYPE_MOSTLY_Q5_K_M = 17
LLAMA_FTYPE_MOSTLY_Q6_K = 18 LLAMA_FTYPE_MOSTLY_Q6_K = 18
LLAMA_FTYPE_MOSTLY_IQ2_XXS = 19
LLAMA_FTYPE_MOSTLY_IQ2_XS = 20
LLAMA_FTYPE_MOSTLY_Q2_K_S = 21
LLAMA_FTYPE_GUESSED = 1024 LLAMA_FTYPE_GUESSED = 1024
# enum llama_rope_scaling_type { # enum llama_rope_scaling_type {

2
vendor/llama.cpp vendored

@ -1 +1 @@
Subproject commit 6efb8eb30e7025b168f3fda3ff83b9b386428ad6 Subproject commit 1d118386fea031f01550f8cd47a5c86296e5333f