Missing model caching in perplexity metrics
daskol opened this issue · comments
The "official" implementation of perplexity metric does not cache language model [1]. It seems that metric instance should fetch model and prepare it for further usage in _download_and_prepare. I suppose that there should be clear API on caching and cache resetting. Also, it is totally unclear how to configure metrics on loading (there is only config_name but kwargs are just ignored).