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 2024-05-08 08:42:22 -04:00
parent 9ce5cb376a
commit 2a39b99575
2 changed files with 10 additions and 3 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

11
llama_cpp/llama_cpp.py
View file

@ -296,7 +296,9 @@ LLAMA_VOCAB_TYPE_WPM = 3
# LLAMA_VOCAB_PRE_TYPE_GPT2 = 7,
# LLAMA_VOCAB_PRE_TYPE_REFACT = 8,
# LLAMA_VOCAB_PRE_TYPE_COMMAND_R = 9,
# LLAMA_VOCAB_PRE_TYPE_OLMO = 10,
# LLAMA_VOCAB_PRE_TYPE_QWEN2 = 10,
# LLAMA_VOCAB_PRE_TYPE_OLMO = 11,
# LLAMA_VOCAB_PRE_TYPE_DBRX = 12,
# };
LLAMA_VOCAB_PRE_TYPE_DEFAULT = 0
LLAMA_VOCAB_PRE_TYPE_LLAMA3 = 1
@ -308,7 +310,9 @@ LLAMA_VOCAB_PRE_TYPE_STARCODER = 6
LLAMA_VOCAB_PRE_TYPE_GPT2 = 7
LLAMA_VOCAB_PRE_TYPE_REFACT = 8
LLAMA_VOCAB_PRE_TYPE_COMMAND_R = 9
LLAMA_VOCAB_PRE_TYPE_OLMO = 10
LLAMA_VOCAB_PRE_TYPE_QWEN2 = 10
LLAMA_VOCAB_PRE_TYPE_OLMO = 11
LLAMA_VOCAB_PRE_TYPE_DBRX = 12
# // note: these values should be synchronized with ggml_rope
@ -377,6 +381,7 @@ LLAMA_TOKEN_TYPE_BYTE = 6
# LLAMA_FTYPE_MOSTLY_IQ2_M = 29, // except 1d tensors
# LLAMA_FTYPE_MOSTLY_IQ4_XS = 30, // except 1d tensors
# LLAMA_FTYPE_MOSTLY_IQ1_M = 31, // except 1d tensors
# LLAMA_FTYPE_MOSTLY_BF16 = 32, // except 1d tensors
# LLAMA_FTYPE_GUESSED = 1024, // not specified in the model file
# };
@ -409,6 +414,8 @@ LLAMA_FTYPE_MOSTLY_IQ3_M = 27
LLAMA_FTYPE_MOSTLY_IQ2_S = 28
LLAMA_FTYPE_MOSTLY_IQ2_M = 29
LLAMA_FTYPE_MOSTLY_IQ4_XS = 30
LLAMA_FTYPE_MOSTLY_IQ1_M = 31
LLAMA_FTYPE_MOSTLY_BF16 = 32
LLAMA_FTYPE_GUESSED = 1024
# enum llama_rope_scaling_type {

2
vendor/llama.cpp vendored

@ -1 +1 @@
Subproject commit c0e6fbf8c380718102bd25fcb8d2e55f8f9480d1
Subproject commit 911b3900dded9a1cfe0f0e41b82c7a29baf3a217