Introducing HUGS - Scale your AI with Open Models
•
30
distilabel
, so we implemented PrometheusEval
.PrometheusEval
running their 7B variant with vLLM in a single L40 on top of
HuggingFaceH4/instruction-dataset, we got the 327 existing prompt-completion pairs evaluated and pushed to the Hub in less than 2 minutes!