search

openai / tiktoken

tiktoken is a fast BPE tokeniser for use with OpenAI's models.
MIT License
11.61k stars 784 forks source link

How to forbid tokens for specific words only? #183

Closed Clement-Lelievre closed 11 months ago

Clement-Lelievre commented 11 months ago

I need to use the openAI Chat endpoint and prevent some words from appearing in the model's completion. To achieve this, I use the logit_bias parameter, which expects a mapping of tokens to an int value (-100 in my case). This is where tiktoken comes in.

PROBLEM: the forbidding mechanism described above works at token-level, not at word-level. Therefore, and because some tokens are shared across words, forbidding a token with a specific word in mind can result in unintended consequences, namely forbidding other words in the process.

EXAMPLE: I want the model's completion to NOT include the word "impossible". The tokens for this word as per cl100k_base are: [318, 10236] . So I pass to my openai query: logit_bias = {318 : -100, 10236 : -100} . However, because the token list for the word "possible" using the same encoder is : [10236] this could result in an unwanted ban of the word "possible".

hauntsaninja commented 11 months ago

This cannot be done naively using the logit bias parameter, for the reasons you mention. Although you could take a resampling approach to make it work. I think it'd be great if the API let you specify a grammar or state machine or something to have more control over sampling, but that's out of scope for this repo.