vrr/koboldcpp
2
0
Fork 0
mirror of https://github.com/LostRuins/koboldcpp.git synced 2025-09-11 09:34:37 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Merge branch 'upstream' into concedo_experimental

Browse source 
# Conflicts:
#	CMakeLists.txt
#	Makefile
#	README.md
#	common/common.cpp
#	requirements/requirements-convert-hf-to-gguf-update.txt
#	requirements/requirements-convert-hf-to-gguf.txt
#	requirements/requirements-convert.txt
#	tests/CMakeLists.txt
#	tests/test-json-schema-to-grammar.cpp
This commit is contained in:
Concedo 2024-05-09 15:13:34 +08:00
commit d084f78faa
48 changed files with 3786 additions and 1438 deletions
Download patch file Download diff file Expand all files Collapse all files

14
llama.cpp
View file

@ -4445,9 +4445,15 @@ static void llm_load_vocab(
} else if (
tokenizer_pre == "command-r") {
vocab.type_pre = LLAMA_VOCAB_PRE_TYPE_COMMAND_R;
} else if (
tokenizer_pre == "qwen2") {
vocab.type_pre = LLAMA_VOCAB_PRE_TYPE_QWEN2;
} else if (
tokenizer_pre == "olmo") {
vocab.type_pre = LLAMA_VOCAB_PRE_TYPE_OLMO;
} else if (
tokenizer_pre == "dbrx") {
vocab.type_pre = LLAMA_VOCAB_PRE_TYPE_DBRX;
} else {
throw std::runtime_error(format("unknown pre-tokenizer type: '%s'", tokenizer_pre.c_str()));
}
@ -12491,6 +12497,7 @@ struct llm_tokenizer_bpe {
case LLAMA_VOCAB_TYPE_BPE:
switch (vocab.type_pre) {
case LLAMA_VOCAB_PRE_TYPE_LLAMA3:
case LLAMA_VOCAB_PRE_TYPE_DBRX:
word_collection = unicode_regex_split(text, {
// original regex from tokenizer.json
//"(?i:'s|'t|'re|'ve|'m|'ll|'d)|[^\\r\\n\\p{L}\\p{N}]?\\p{L}+|\\p{N}{1,3}| ?[^\\s\\p{L}\\p{N}]+[\\r\\n]*|\\s*[\\r\\n]+|\\s+(?!\\S)|\\s+",
@ -12550,6 +12557,13 @@ struct llm_tokenizer_bpe {
"'s|'t|'re|'ve|'m|'ll|'d| ?\\p{L}+| ?\\p{N}+| ?[^\\s\\p{L}\\p{N}]+|\\s+(?!\\S)",
});
break;
case LLAMA_VOCAB_PRE_TYPE_QWEN2:
word_collection = unicode_regex_split(text, {
// original regex from tokenizer.json
// "(?i:'s|'t|'re|'ve|'m|'ll|'d)|[^\\r\\n\\p{L}\\p{N}]?\\p{L}+|\\p{N}| ?[^\\s\\p{L}\\p{N}]+[\\r\\n]*|\\s*[\\r\\n]+|\\s+(?!\\S)|\\s+"
"(?:'[sS]|'[tT]|'[rR][eE]|'[vV][eE]|'[mM]|'[lL][lL]|'[dD])|[^\\r\\n\\p{L}\\p{N}]?\\p{L}+|\\p{N}| ?[^\\s\\p{L}\\p{N}]+[\\r\\n]*|\\s*[\\r\\n]+|\\s+(?!\\S)|\\s+",
});
break;
default:
// default regex for BPE tokenization pre-processing
word_collection = unicode_regex_split(text, {