Not 100% sure if sampling parameters is correct

[kirill-fedyanin]

https://github.com/IINemo/lm-polygraph/blame/00851972311db837de6358c90dac65616495d4de/src/lm_polygraph/stat_calculators/sample.py#L27

It's now setting both top_k=50 and top_p if we just set top_p, if i understand code correctly. Having both top_k and top_p is kind of weird to me.
Also there seems there is no do_sample; from the hf docs, we could accidentaly get contrastive_search() instead of sample()

Would be nice to test this

[rvashurin]

Yep, blackbox sampling parameters seem sketchy, we'll need to check them after we're finished with benchmarks.

[rvashurin]

@cant-access-rediska0123 why do we set 50 as default topK?

[IINemo]

We use default value of huggingface.