1import tokie
2
3tokenizer = tokie.Tokenizer.from_pretrained("tokiers/jina-embeddings-v2-base-en")
4encoding = tokenizer.encode("Hello, world!")
5print(encoding.ids)
6print(encoding.attention_mask)
1[dependencies]
2tokie = { version = "0.0.4", features = ["hf"] }
1use tokie::Tokenizer;
2
3let tokenizer = Tokenizer::from_pretrained("tokiers/jina-embeddings-v2-base-en").unwrap();
4let encoding = tokenizer.encode("Hello, world!", true);
5println!("{:?}", encoding.ids);
tokie is a drop-in replacement for HuggingFace tokenizers, built in Rust. See
GitHub for benchmarks and documentation.
MIT OR Apache-2.0 (tokie library). Original model files retain their original license from
jinaai/jina-embeddings-v2-base-en.