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

feat: Update llama.cpp

Browse source
This commit is contained in:
Andrei Betlen 2024-03-28 12:06:46 -04:00
parent 901fe02461
commit 125b2358c9
2 changed files with 8 additions and 4 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

10
llama_cpp/llama_cpp.py
View file

@ -199,14 +199,18 @@ llama_seq_id = ctypes.c_int32
# enum llama_vocab_type {
# LLAMA_VOCAB_TYPE_NONE = 0, // For models without vocab
# LLAMA_VOCAB_TYPE_SPM = 1, // SentencePiece
# LLAMA_VOCAB_TYPE_BPE = 2, // Byte Pair Encoding
# LLAMA_VOCAB_TYPE_WPM = 3, // WordPiece
# LLAMA_VOCAB_TYPE_SPM = 1, // LLaMA tokenizer based on byte-level BPE with byte fallback
# LLAMA_VOCAB_TYPE_BPE = 2, // GPT-2 tokenizer based on byte-level BPE
# LLAMA_VOCAB_TYPE_WPM = 3, // BERT tokenizer based on WordPiece
# };
LLAMA_VOCAB_TYPE_NONE = 0
"""For models without vocab"""
LLAMA_VOCAB_TYPE_SPM = 1
"""LLaMA tokenizer based on byte-level BPE with byte fallback"""
LLAMA_VOCAB_TYPE_BPE = 2
"""GPT-2 tokenizer based on byte-level BPE"""
LLAMA_VOCAB_TYPE_WPM = 3
"""BERT tokenizer based on WordPiece"""
# // note: these values should be synchronized with ggml_rope

2
vendor/llama.cpp vendored

@ -1 +1 @@
Subproject commit 32c8486e1f0297393cb22ac0a0d26a6b17ad4d54
Subproject commit 5106ef482c65ac60ac14da9a68c7b37bca4c6993