DPO for Multiple-Choice Reasoning nevertmr/mistral-7b-qlora-dpo Text Generation • 7B • Updated Jul 16 • 23
SO-101 cup → blue circle One instruction for the whole motion. White paper cup, 70 solo episodes + the pi05 fine-tunes trained on them. nevertmr/so101_cup_bluecircle_1task SO-101 • Updated Jul 22 • 50 episodes • 149 • 1 nevertmr/so101_cup_bluecircle_1task_var SO-101 • Updated Jul 22 • 20 episodes • 114 • 1 aailabkaist/pi05_coffee_NorRec_RW_10k Robotics • 4B • Updated Aug 1 • 58 nevertmr/so101_cup_bluecircle_2task SO-101 • Updated Jul 22 • 113 episodes • 135
DPO for Multiple-Choice Reasoning nevertmr/mistral-7b-qlora-dpo Text Generation • 7B • Updated Jul 16 • 23
SO-101 cup → blue circle One instruction for the whole motion. White paper cup, 70 solo episodes + the pi05 fine-tunes trained on them. nevertmr/so101_cup_bluecircle_1task SO-101 • Updated Jul 22 • 50 episodes • 149 • 1 nevertmr/so101_cup_bluecircle_1task_var SO-101 • Updated Jul 22 • 20 episodes • 114 • 1 aailabkaist/pi05_coffee_NorRec_RW_10k Robotics • 4B • Updated Aug 1 • 58 nevertmr/so101_cup_bluecircle_2task SO-101 • Updated Jul 22 • 113 episodes • 135
