Re: [ot][spam][crazy] adapters for semibalanced trees?

this is where i left off process.cpp given that i'll need to figure out how to implement (or otherwise handle) diffing files, possibly including moving them (might make sense to use an existing git library) ; it seems a better investment of time would be setting up adapters to train embeddings. since generating data slowly is not a stopping issue, but the model may not succeed at useful data without a slightly better tokenizer.