Xiaodong/DPO_sdf_17k
Updated
•
12
•
1
VLMM-DPO-data
some dpo perference data
-
-
Xiaodong/video_instruction_train_dpo
Viewer • Updated • 17k • 4 -
Xiaodong/Next-DPO-iter1
Updated -
Xiaodong/Next-DPO-iter2
Updated -
Xiaodong/llava_dpo_17k_flash-attn_DPO_iter3_8k_data
Updated -
Xiaodong/DPO-iter2-data-8k
Viewer • Updated • 8k • 17 -
Xiaodong/DPO-iter3-data-8k
Viewer • Updated • 8k • 7 -
Xiaodong/hound_QA-16k
Updated • 11