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

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
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
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