ace-1
/

mgpt2-dpo

Text Generation

instruction-tuned

preference-alignment

Model card Files Files and versions

mgpt2-dpo / tokenizer

Ctrl+K

Ctrl+K

1 contributor

History: 1 commit

ace-1's picture

Publish mgpt2 dpo checkpoint (step 420, val_loss 0.001878)

b640ec6 verified 5 days ago