[newhouseb]

I think you mean "run as part of the sampler," the tokenizer (and tokenization) is fixed for a given model. The sampler blob would basically:

1. Modify the output token probabilities to fit any arbitrary use case

2. Perhaps do trigger some sort of backtracking / beam-search

(I'm not Grant but we've chatted on twitter and built similar things)

[simonw]

Yes, I meant sampler, not tokenizer.