Add token healing example

[mare5x]

Added an example that extends simple with different token healing strategies. Check the added README for examples.
Token healing works by chopping off some tokens from the tokenized prompt and then constraining the decoding to match the bytes of the removed tokens.

Currently, I am just using for loops for prefix searching, but performance could potentially be improved with a prefix tree (+ caching mentioned in https://arxiv.org/abs/2403.08688).

To finish #5765, we still need to include token healing into server. I think the approach is to extend llama_sampling_sample and modify the initial input tokens?

[teleprint-me]

This is awesome! <3

[mare5x]

Adding to main in #7187. Will try to add to server later.