vbatts/llama.cpp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

Fix unicode whitespaces (deepseek-llm)

Browse source
This commit is contained in:
jaime-m-p 2024-06-14 20:00:15 +02:00
parent 07530a8dce
commit 4ff15d4fda
1 changed files with 8 additions and 1 deletions
Download patch file Download diff file Expand all files Collapse all files

9
unicode.cpp
View file

@ -772,9 +772,16 @@ std::vector<std::string> unicode_regex_split(const std::string & text, const std
bpe_offsets = unicode_regex_split_stl(text_collapsed, regex_expr_collapsed, bpe_offsets);
} else {
// no unicode category used, we can use std::wregex directly
const std::wstring wtext = unicode_wstring_from_utf8(text);
const std::wstring wregex_expr = unicode_wstring_from_utf8(regex_expr);
// std::wregex \s does not mach non-ASCII whitespaces, using 0x0B as fallback
std::wstring wtext(cpts.begin(), cpts.end());
for (size_t i = 0; i < wtext.size(); ++i) {
if (wtext[i] > 0x7F && unicode_cpt_flags(wtext[i]).is_whitespace) {
wtext[i] = 0x0B;
}
}
//printf("text: %s\n", text.c_str());
//printf("regex_expr: %s\n", regex_expr.c_str());
bpe_offsets = unicode_regex_split_stl(wtext, wregex_expr, bpe_offsets);