tqcq/llama.cpp
0
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-07-01 13:05:52 +00:00
Code Issues Packages Projects Releases Wiki Activity

unicode : improve naming style (#10838)

Browse Source 
* unicode : improve naming style

ggml-ci

* cont [no ci]
This commit is contained in:
Georgi Gerganov
2024-12-16 12:31:45 +02:00
committed by GitHub
parent 644fd71b44
commit 08ea539df2
3 changed files with 61 additions and 62 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
src/llama-vocab.cpp
View File

@ -738,7 +738,7 @@ struct llm_tokenizer_wpm_session {
std::vector<std::string> words(1, "");
for (const uint32_t cpt : cpts_nfd) {
const auto flags = unicode_cpt_flags(cpt);
const auto flags = unicode_cpt_flags_from_cpt(cpt);
if (flags.is_whitespace) {
if (words.back().size()) { // finish previous word if any