This is a Java implementation of a GPT3/4 tokenizer, loosely ported from Tiktoken with the help of ChatGPT. ...that all 3.5-turbo models released after 0613 now have ...

Tokenize text for Llama, Gemini, GPT-4, DeepSeek, Mistral and many others; in the web, on the client and any platform. Kitoken can load and convert many existing tokenizer formats. Every supported ...