Re:Introducing ChatGPT and Whisper APIs
by jncraton on Wednesday March 01, 2023 @03:32PM
(#34987887)
If an example would be helpful, OpenAI's tokenizer is publicly usable on their website:
https://platform.openai.com/tokenizer
You can drop sample text in there and visually see how it is split into tokens. The GPT2/3 tokenizer uses about 50k unique tokens that were learned to be an efficient representation of the training data.
https://en.wikipedia.org/wiki/Byte_pair_encoding
In short, common words cost one token, rarer words cost a few tokens
Edit: and better yet, is there a good resource for learning the vernacular in general? Should I just read something like "Dive into Deep Learning"?