|
|
From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
|
|
|
From: jmorganca <jmorganca@gmail.com>
|
|
|
Date: Tue, 8 Apr 2025 19:43:06 -0700
|
|
|
Subject: [PATCH] fix deepseek deseret regex
|
|
|
|
|
|
on some systems, deepseek's regex would throw an error
|
|
|
on windows due to the deseret characters in the matching
|
|
|
regex
|
|
|
---
|
|
|
src/llama-vocab.cpp | 2 +-
|
|
|
src/unicode.cpp | 21 +++++++++++++++++++++
|
|
|
2 files changed, 22 insertions(+), 1 deletion(-)
|
|
|
|
|
|
diff --git a/src/llama-vocab.cpp b/src/llama-vocab.cpp
|
|
|
index 806c1b3d..10f34d33 100644
|
|
|
--- a/src/llama-vocab.cpp
|
|
|
+++ b/src/llama-vocab.cpp
|
|
|
@@ -298,7 +298,7 @@ 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-]+",
|
|
|
diff --git a/src/unicode.cpp b/src/unicode.cpp
|
|
|
index e63bb4ab..73cb2b1a 100644
|
|
|
--- a/src/unicode.cpp
|
|
|
+++ b/src/unicode.cpp
|
|
|
@@ -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"
|
|
|
|
|
|
@@ -200,6 +205,21 @@ 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
|
|
|
#if defined(__clang__)
|
|
|
// disable C++17 deprecation warning for std::codecvt_utf8
|
|
|
# pragma clang diagnostic push
|
|
|
@@ -213,6 +233,7 @@ static inline std::wstring unicode_wstring_from_utf8(const std::string & s) {
|
|
|
#endif
|
|
|
|
|
|
return conv.from_bytes(s);
|
|
|
+#endif
|
|
|
}
|
|
|
|
|
|
static std::vector<std::string> unicode_byte_encoding_process(const std::vector<std::string> & bpe_words) {
|
