Implement standard inference modes

[justheuristic]

It would be awesome to have a collection of standard inference methods, e.g. greedy, temperature, top-p, top-k, eventually tree / beam search and batched inference, once we support it on the backend.

For now, perhaps, it would be best to implement them as standalone functions / functors that take the full model as input and do the inference. Eventually, we'll figure out the best way of integrating them together.

Roadmap (tentative)

1. sampling, greedy, top-k, nucleus, etc -- with obligatory support for prefixes
2. inference with prompt-tuned model
3. beam search (requires changes on backend)

.. and then, in no particular order,

• inference with LoRA / AdaMix
• user-defined, constraints, other crazy stuff

[justheuristic]

Done by @artek0chumak in #87 , will discuss next steps in a separate issue