Files
ollama-for-amd/llama/patches/0005-fix-deepseek-deseret-regex.patch
Daniel Hiltgen 49a9c9ba6a GGML update to ec98e2002 (#13451)
* Revert "add support for NVIDIA Nemotron 3 Nano"

This reverts commit e7d2ae9d69421012e9a8765c06a3fdf0e45b12f3.

* GGML update to 380b4c984

Remove MaskBatchPadding as GGML_KQ_MASK_PAD is no longer present (no
padding required)

* update to c45f89d55

* ec98e2002

solar pro needed more adjusting - needs verification

* review comments
2025-12-17 13:13:55 -08:00

73 lines
3.3 KiB
Diff
Raw Permalink Blame History

This file contains ambiguous Unicode characters
This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.
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 63250cdf1..dd86a1745 100644
--- a/src/llama-vocab.cpp
+++ b/src/llama-vocab.cpp
@@ -299,7 +299,7 @@ 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--ℝℤΩℨK--ℴℹℼ-ℿⅅ-ⅉⅎↃↄⰀ-ⱻⱾ-ⳤⳫ-ⳮⳲⳳꙀ-ꙭꚀ-ꚛꜢ-ꝯꝱ-ꞇꞋ-ꞎꭰ-ꮿff-stﬓ-ﬗA--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--ℝℤΩℨK--ℴℹℼ-ℿⅅ-ⅉⅎↃↄⰀ-ⱻⱾ-ⳤⳫ-ⳮⳲⳳꙀ-ꙭꚀ-ꚛꜢ-ꝯꝱ-ꞇꞋ-ꞎꭰ-ꮿff-stﬓ-ﬗA--\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 bb44edfad..13ced055f 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
@@ -218,6 +238,7 @@ 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) {