Modelpublic

abacusai/MM-OV-bagel-DPO-34b-c1000-250

sourceHugging Faceapache-2.0updated 3y agoView on Hugging Face

1likes63downloads

Model Card

DPO finetune of (https://huggingface.co/abacusai/MM-Orc-Vic-bagel-34b-c1000) on the Bagel DPO dataset

Average	ARC	HellaSwag	MMLU	TruthfulQA	Winogrande	GSM8K