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:
#	.gitignore
#	README.md
#	docs/backend/BLIS.md
#	docs/backend/SYCL.md
#	docs/development/llama-star/idea-arch.key
#	docs/development/llama-star/idea-arch.pdf
#	docs/development/token_generation_performance_tips.md
#	src/llama.cpp
#	tests/test-tokenizer-0.cpp
#	tests/test-tokenizer-1-bpe.cpp
#	tests/test-tokenizer-1-spm.cpp
#	tests/test-tokenizer-random.py
This commit is contained in:
Concedo 2024-07-06 19:39:24 +08:00
commit 8e5fd6f509
28 changed files with 352 additions and 2091 deletions
Download patch file Download diff file Expand all files Collapse all files

18
src/unicode.cpp
View file

@ -242,8 +242,7 @@ static std::vector<size_t> unicode_regex_split_custom_gpt2(const std::string & t
};
auto _get_flags = [&] (const size_t pos) -> codepoint_flags {
static const codepoint_flags undef(codepoint_flags::UNDEFINED);
return (offset_ini <= pos && pos < offset_end) ? unicode_cpt_flags(cpts[pos]) : undef;
return (offset_ini <= pos && pos < offset_end) ? unicode_cpt_flags(cpts[pos]) : codepoint_flags{};
};
size_t _prev_end = offset_ini;
@ -305,9 +304,9 @@ static std::vector<size_t> unicode_regex_split_custom_gpt2(const std::string & t
continue;
}
// regex: <space>?[^\s\p{L}\p{N}]+
if (!(flags2.is_whitespace || flags2.is_letter || flags2.is_number || flags2.is_undefined)) {
if (!(flags2.is_whitespace | flags2.is_letter | flags2.is_number) && flags2.as_uint()) {
pos += (cpt == ' ');
while (!(flags2.is_whitespace || flags2.is_letter || flags2.is_number || flags2.is_undefined)) {
while (!(flags2.is_whitespace | flags2.is_letter | flags2.is_number) && flags2.as_uint()) {
flags2 = _get_flags(++pos);
}
_add_token(pos);
@ -361,8 +360,7 @@ static std::vector<size_t> unicode_regex_split_custom_llama3(const std::string &
};
auto _get_flags = [&] (const size_t pos) -> codepoint_flags {
static const codepoint_flags undef(codepoint_flags::UNDEFINED);
return (offset_ini <= pos && pos < offset_end) ? unicode_cpt_flags(cpts[pos]) : undef;
return (offset_ini <= pos && pos < offset_end) ? unicode_cpt_flags(cpts[pos]) : codepoint_flags{};
};
size_t _prev_end = offset_ini;
@ -404,8 +402,8 @@ static std::vector<size_t> unicode_regex_split_custom_llama3(const std::string &
}
}
// regex: [^\r\n\p{L}\p{N}]?\p{L}+ //####FIXME: the first \p{L} is correct?
if (!(cpt == '\r' || cpt == '\n' || /*flags.is_letter |*/ flags.is_number)) {
// regex: [^\r\n\p{L}\p{N}]?\p{L}+
if (!(cpt == '\r' || cpt == '\n' || flags.is_number)) {
if (flags.is_letter || _get_flags(pos+1).is_letter) { // one or more letters
pos++;
while (_get_flags(pos).is_letter) {
@ -431,9 +429,9 @@ static std::vector<size_t> unicode_regex_split_custom_llama3(const std::string &
// regex: <space>?[^\s\p{L}\p{N}]+[\r\n]*
auto flags2 = (cpt == ' ' ? _get_flags(pos+1) : flags);
if (!(flags2.is_whitespace || flags2.is_letter || flags2.is_number || flags2.is_undefined)) {
if (!(flags2.is_whitespace | flags2.is_letter | flags2.is_number) && flags.as_uint()) {
pos += (cpt == ' ');
while (!(flags2.is_whitespace || flags2.is_letter || flags2.is_number || flags2.is_undefined)) {
while (!(flags2.is_whitespace | flags2.is_letter | flags2.is_number) && flags2.as_uint()) {
flags2 = _get_flags(++pos);
}
uint32_t cpt2 = _get_cpt(pos);