Gpt3_tokenizer - BPE Encoder Decoder for GPT-3 implemented in Elixir

No, i haven’t.

It seems using Rustler to NIF bind the Rust implementation of the HuggingFace tokenizer. The HF tokenizer use the same mechanism (BPE) as the GPT-3’s, but they are different and give different results. (I just confirmed it by comparing the result in its README vs https://platform.openai.com/tokenizer)

Anyway, binding the rust implementation is a promising direction. GPT-3 encoder also has a rust implementation called tiktoken. For my own use case, the native one is good enough tho.

2 Likes