8000 supporting more diverse tokenizers by eric8607242 · Pull Request #2420 · ggml-org/llama.cpp · GitHub
[go: up one dir, main page]
Skip to content

supporting more diverse tokenizers #2420

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 2 commits into from
Jul 28, 2023
Merged

supporting more diverse tokenizers #2420

Changes from 1 commit
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
efb5dac
supporting more diverse tokenizers
eric8607242 Jul 27, 2023
a8ee520
Update llama.cpp
ggerganov Jul 28, 2023
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
Prev Previous commit
Update llama.cpp
  • Loading branch information
@ggerganov
ggerganov authored Jul 28, 2023
commit a8ee520eb8e9f59288949b3ceea77066301b02ef
2 changes: 2 additions & 0 deletions llama.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1924,6 +1924,8 @@ struct llama_tokenizer {
if (token == vocab_.token_to_id.end()) {
// output any symbols that did not form tokens as bytes.
for (int j = 0; j < (int) symbol.n; ++j) {
// NOTE: old version, before #2420 - not sure what are the implications of this
//llama_vocab::id token_id = static_cast<uint8_t>(symbol.text[j]) + 3;
llama_vocab::id token_id = vocab_.token_to_id.at(std::string(1, symbol.text[j]));
output.push_back(token_id);
}
Expand Down
0