root/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggerganov/llama.cpp.git synced 2024-12-26 03:14:35 +00:00
Code Issues Actions 7 Packages Projects Releases Wiki Activity

llama : handle unknown utf8 bytes (#7588)

Browse Source
This commit is contained in:
Georgi Gerganov 2024-05-28 13:55:35 +03:00 committed by GitHub
parent 271ff3fc44
commit 8b99e2aa66
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 10 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

11
llama.cpp
View File

@ -17940,7 +17940,16 @@ static std::string llama_decode_text(const std::string & text) {
const auto cpts = unicode_cpts_from_utf8(text); const auto cpts = unicode_cpts_from_utf8(text);
for (const auto cpt : cpts) { for (const auto cpt : cpts) {
decoded_text += unicode_utf8_to_byte(unicode_cpt_to_utf8(cpt)); const auto utf8 = unicode_cpt_to_utf8(cpt);
try {
decoded_text += unicode_utf8_to_byte(utf8);
} catch (const std::out_of_range & e) {
decoded_text += "[UNK_BYTE_0x";
for (const auto c : utf8) {
decoded_text += format("%02x", (uint8_t) c);
}
decoded_text += text + "]";
}
} }
return decoded_text; return decoded_text;