rouge/
daybreak-kunoichi-2dpo-7b

270 1 year ago

Experimental model doing a DPO training on top of Kunoichi-DPO-v2-7b, i.e. double-DPO.

1 model

daybreak-kunoichi-2dpo-7b:latest
4742d588810c • 7.7GB • 16K context window •
Text input • 1 year ago