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

feat: Update llama.cpp

Browse source
This commit is contained in:
Andrei Betlen 2024-02-26 11:40:58 -05:00
parent a57d5dff86
commit 9558ce7878
1 changed files with 6 additions and 2 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

8
llama_cpp/llama_cpp.py
View file

@ -256,12 +256,14 @@ LLAMA_TOKEN_TYPE_BYTE = 6
# 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_IQ2_XS = 20, // except 1d tensors
# LLAMA_FTYPE_MOSTLY_Q2_K_S = 21, // except 1d tensors # LLAMA_FTYPE_MOSTLY_Q2_K_S = 21, // except 1d tensors
# LLAMA_FTYPE_MOSTLY_Q3_K_XS = 22, // except 1d tensors # LLAMA_FTYPE_MOSTLY_IQ3_XS = 22, // except 1d tensors
# LLAMA_FTYPE_MOSTLY_IQ3_XXS = 23, // except 1d tensors # LLAMA_FTYPE_MOSTLY_IQ3_XXS = 23, // except 1d tensors
# LLAMA_FTYPE_MOSTLY_IQ1_S = 24, // except 1d tensors # LLAMA_FTYPE_MOSTLY_IQ1_S = 24, // except 1d tensors
# LLAMA_FTYPE_MOSTLY_IQ4_NL = 25, // except 1d tensors # LLAMA_FTYPE_MOSTLY_IQ4_NL = 25, // except 1d tensors
# LLAMA_FTYPE_MOSTLY_IQ3_S = 26, // except 1d tensors # LLAMA_FTYPE_MOSTLY_IQ3_S = 26, // except 1d tensors
# LLAMA_FTYPE_MOSTLY_IQ3_M = 27, // except 1d tensors # LLAMA_FTYPE_MOSTLY_IQ3_M = 27, // except 1d tensors
# LLAMA_FTYPE_MOSTLY_IQ2_S = 28, // except 1d tensors
# LLAMA_FTYPE_MOSTLY_IQ2_M = 29, // except 1d tensors
# LLAMA_FTYPE_GUESSED = 1024, // not specified in the model file # LLAMA_FTYPE_GUESSED = 1024, // not specified in the model file
# }; # };
@ -285,12 +287,14 @@ LLAMA_FTYPE_MOSTLY_Q6_K = 18
LLAMA_FTYPE_MOSTLY_IQ2_XXS = 19 LLAMA_FTYPE_MOSTLY_IQ2_XXS = 19
LLAMA_FTYPE_MOSTLY_IQ2_XS = 20 LLAMA_FTYPE_MOSTLY_IQ2_XS = 20
LLAMA_FTYPE_MOSTLY_Q2_K_S = 21 LLAMA_FTYPE_MOSTLY_Q2_K_S = 21
LLAMA_FTYPE_MOSTLY_Q3_K_XS = 22 LLAMA_FTYPE_MOSTLY_IQ3_XS = 22
LLAMA_FTYPE_MOSTLY_IQ3_XXS = 23 LLAMA_FTYPE_MOSTLY_IQ3_XXS = 23
LLAMA_FTYPE_MOSTLY_IQ1_S = 24 LLAMA_FTYPE_MOSTLY_IQ1_S = 24
LLAMA_FTYPE_MOSTLY_IQ4_NL = 25 LLAMA_FTYPE_MOSTLY_IQ4_NL = 25
LLAMA_FTYPE_MOSTLY_IQ3_S = 26 LLAMA_FTYPE_MOSTLY_IQ3_S = 26
LLAMA_FTYPE_MOSTLY_IQ3_M = 27 LLAMA_FTYPE_MOSTLY_IQ3_M = 27
LLAMA_FTYPE_MOSTLY_IQ2_S = 28
LLAMA_FTYPE_MOSTLY_IQ2_M = 29
LLAMA_FTYPE_GUESSED = 1024 LLAMA_FTYPE_GUESSED = 1024
# enum llama_rope_scaling_type { # enum llama_rope_scaling_type {