Skip to content

llama : fix bpe tokenize from byte #2889

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 1 commit into from
Sep 3, 2023
Merged

llama : fix bpe tokenize from byte #2889

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
10 changes: 8 additions & 2 deletions llama.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -3319,9 +3319,15 @@ struct llm_tokenizer_bpe {
std::string byte_str(1, *j);
auto token_multibyte = vocab.token_to_id.find(byte_str);
if (token_multibyte == vocab.token_to_id.end()) {
fprintf(stderr,"ERROR: byte not found in vocab: '%s'\n", byte_str.c_str());
try {
llama_token token_byte = llama_byte_to_token(vocab, *j);
output.push_back(token_byte);
} catch (const std::out_of_range & err) {
fprintf(stderr,"ERROR: byte not found in vocab: '%s'\n", byte_str.c_str());
}
} else {
output.push_back((*token_multibyte).second);
}
output.push_back((*token_multibyte).second);
}
} else {
output.push_back((*token).second);
Expand Down