kwrobel.eth

The `v` flag works in `jest`.

Parsing markup from http://en.wikipedia.org/wiki/List_of_female_tennis_players is much more longer (I didn't wait for finish).

I have tried with this `sed` solution while parsing Wikidata, but: `lightrdf.Error: error while parsing IRI 'http://archive.is/EKEWo#34.7%': Invalid IRI percent encoding '%' on line 49533684 at position 41` Another: `lightrdf.Error:...

Almost all Polish tasks, we have created, are in two versions: multiple choice and generate, e.g. https://github.com/speakleash/lm-evaluation-harness/tree/polish2/lm_eval/tasks/polish_ppc Results are published on https://huggingface.co/spaces/speakleash/open_pl_llm_leaderboard with task name suffixes `_g` or `_mc`. There...

@daniel-furman @haileyschoelkopf @KonradSzafer I have tested some models without template, with template and with template as multiturn. Results are published in LB: https://huggingface.co/spaces/speakleash/open_pl_llm_leaderboard Comparison sheet: https://docs.google.com/spreadsheets/d/1b5s0LuhAQLbtzexxasLBA47gQ-R3HOuIKFRfIgJflf0/edit?usp=sharing There are average scores...

Me too. mt5-xl has very high word-level perplexity.

They are MLM models so maybe it doesn't make sense or it needs to add MASK token add the end of each sub sequence. I will remove these models from...

The error still exists in: transformers==4.3.2, tokenizers==0.10.1. I am using gunicorn (with threads) with flask and the error shows if parallel requests are made. The problem does not exist in...

Anyone tested this fix?

Is it a duplicate of https://github.com/EleutherAI/lm-evaluation-harness/pull/1287?