pt-ffw Collection models pretrained on ffw, varying amount of math in pretraining dataset • 25 items • Updated 10 days ago
ft Collection models pretrained on fw + finetuned on different datasets • 204 items • Updated 8 days ago
ft-vary-wd-during-ft Collection models pretrained on ffw + finetuned, varying wd during ft • 54 items • Updated 10 days ago