* If the first letter is capital, only capitalized first tokens will be sampled. If the whole text is capitalized, then only fully capital tokens will be sampled for the whole word
* If a word is an exact match, it gets boosted relative to others
* Probability threshold for autocorrect is now 18.0
* Add "clueless" threshold, if it's less than 1.3 then just show the user's typed word in the middle instead.

Fix finetuning, add a finetuning screen, handle errors during importing model, update metadata format, add model exporting

Fix embedded tokenizer loading, implement new model management methods, implement model info loading, model importing