Skip to content

fix deepseek deseret regex #10062

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Closed
wants to merge 1 commit into from
Closed

fix deepseek deseret regex #10062

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 1 addition & 1 deletion src/llama-vocab.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -389,7 +389,7 @@ struct llm_tokenizer_bpe : llm_tokenizer {
case LLAMA_VOCAB_PRE_TYPE_DEEPSEEK_LLM:
regex_exprs = {
"[\r\n]",
"\\s?[A-Za-zµÀ-ÖØ-öø-ƺƼ-ƿDŽ-ʓʕ-ʯͰ-ͳͶͷͻ-ͽͿΆΈ-ΊΌΎ-ΡΣ-ϵϷ-ҁҊ-ԯԱ-ՖႠ-ჅᎠ-Ᏽᏸ-ᏽᲐ-ᲺᲽ-Ჿᴀ-ᴫᵫ-ᵷᵹ-ᶚḀ-ἕἘ-Ἕἠ-ὅὈ-Ὅὐ-ὗὙὛὝὟ-ώᾀ-ᾴᾶ-ᾼιῂ-ῄῆ-ῌῐ-ΐῖ-Ίῠ-Ῥῲ-ῴῶ-ῼℂℇℊ-ℓℕℙ-ℝℤΩℨK-ℭℯ-ℴℹℼ-ℿⅅ-ⅉⅎↃↄⰀ-ⱻⱾ-ⳤⳫ-ⳮⳲⳳꙀ-ꙭꚀ-ꚛꜢ-ꝯꝱ-ꞇꞋ-ꞎꭰ-ꮿff-stﬓ-ﬗＡ-Ｚａ-ｚ𐐀-𐑏𐒰-𐓓𐓘-𐓻𐲀-𐲲𐳀-𐳲𑢠-𑣟𞤀-𞥃]+",
"\\s?[A-Za-zµÀ-ÖØ-öø-ƺƼ-ƿDŽ-ʓʕ-ʯͰ-ͳͶͷͻ-ͽͿΆΈ-ΊΌΎ-ΡΣ-ϵϷ-ҁҊ-ԯԱ-ՖႠ-ჅᎠ-Ᏽᏸ-ᏽᲐ-ᲺᲽ-Ჿᴀ-ᴫᵫ-ᵷᵹ-ᶚḀ-ἕἘ-Ἕἠ-ὅὈ-Ὅὐ-ὗὙὛὝὟ-ώᾀ-ᾴᾶ-ᾼιῂ-ῄῆ-ῌῐ-ΐῖ-Ίῠ-Ῥῲ-ῴῶ-ῼℂℇℊ-ℓℕℙ-ℝℤΩℨK-ℭℯ-ℴℹℼ-ℿⅅ-ⅉⅎↃↄⰀ-ⱻⱾ-ⳤⳫ-ⳮⳲⳳꙀ-ꙭꚀ-ꚛꜢ-ꝯꝱ-ꞇꞋ-ꞎꭰ-ꮿff-stﬓ-ﬗＡ-Ｚａ-ｚ\U00010400-\U0001044f𐒰-𐓓𐓘-𐓻𐲀-𐲲𐳀-𐳲𑢠-𑣟𞤀-𞥃]+",
"\\s?[!-/:-~！-／：-～‘-‟　-。]+",
"\\s+$",
"[一-龥ࠀ-一가-퟿]+",
Expand Down
21 changes: 21 additions & 0 deletions src/unicode.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2,6 +2,11 @@
#define _SILENCE_CXX17_CODECVT_HEADER_DEPRECATION_WARNING
#endif

#if defined(_WIN32)
#define WIN32_LEAN_AND_MEAN
#include <windows.h>
#endif

#include "unicode.h"
#include "unicode-data.h"

Expand Down Expand Up @@ -201,8 +206,24 @@ static std::unordered_map<std::string, uint8_t> unicode_utf8_to_byte_map() {
}

static inline std::wstring unicode_wstring_from_utf8(const std::string & s) {
#ifdef _WIN32
int wlen = MultiByteToWideChar(CP_UTF8, 0, s.c_str(), -1, NULL, 0);
if (!wlen) {
throw std::invalid_argument("failed to convert regex");
}
wchar_t * wbuf = (wchar_t *) malloc(wlen * sizeof(wchar_t));
wlen = MultiByteToWideChar(CP_UTF8, 0, s.c_str(), -1, wbuf, wlen);
if (!wlen) {
free(wbuf);
throw std::invalid_argument("failed to convert regex");
}
std::wstring ret = std::wstring(wbuf);
free(wbuf);
return ret;
#else
std::wstring_convert<std::codecvt_utf8<wchar_t>> conv;
return conv.from_bytes(s);
#endif
}

static std::vector<std::string> unicode_byte_encoding_process(const std::vector<std::string> & bpe_words) {
Expand Down
Loading