root/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggerganov/llama.cpp.git synced 2024-12-24 10:24:35 +00:00
Code Issues Actions 5 Packages Projects Releases Wiki Activity

Fix token count accounting

Browse Source
This commit is contained in:
Matvey Soloviev 2023-03-13 00:35:51 +01:00
parent c80e2a8f2a
commit 460c482540
1 changed files with 2 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
main.cpp
View File

@ -976,6 +976,8 @@ int main(int argc, char ** argv) {
std::vector<gpt_vocab::id> line_inp = ::llama_tokenize(vocab, buf, false);
embd_inp.insert(embd_inp.end(), line_inp.begin(), line_inp.end());
remaining_tokens -= line_inp.size();
input_noecho = true; // do not echo this again
}