socialfoundations

roberta-large-pile-lr2e-5-bs16-8gpu-1700000

socialfoundations/roberta-large-pile-lr2e-5-bs16-8gpu-1700000

roberta-large-pile-lr2e-5-bs16-8gpu-1700000 is a fill-mask model from socialfoundations. Use it when you need the model to fill a missing word. It is set up for transformers. The card lists the license as cc-by-nc-4.0.

Standard roberta-large model fine-tuned for one pass over the entire Pile dataset.