LightEval is a lightweight LLM evaluation suite that Hugging Face has been using internally with the recently released LLM data processing library datatrove and LLM training library nanotron.
MIT License
471
stars
55
forks
source link
Problem with mutliple tasks from the same dataset #91
Need to see if it can be repro, but I can only load BBH by manually forcing all my processes to wait for one another.