Skip to content

Commit

Permalink
Add text embedding models
Browse files Browse the repository at this point in the history
  • Loading branch information
zurawiki committed Mar 20, 2024
1 parent 14821ea commit eb9c1de
Showing 1 changed file with 2 additions and 0 deletions.
2 changes: 2 additions & 0 deletions tiktoken-rs/src/tokenizer.rs
Original file line number Diff line number Diff line change
Expand Up @@ -68,6 +68,8 @@ const MODEL_TO_TOKENIZER: &[(&str, Tokenizer)] = &[
("code-davinci-edit-001", Tokenizer::P50kEdit),
// embeddings
("text-embedding-ada-002", Tokenizer::Cl100kBase),
("text-embedding-3-small", Tokenizer::Cl100kBase),
("text-embedding-3-large", Tokenizer::Cl100kBase),
// old embeddings
("text-similarity-davinci-001", Tokenizer::R50kBase),
("text-similarity-curie-001", Tokenizer::R50kBase),
Expand Down

0 comments on commit eb9c1de

Please sign in to comment.