HaoranLiu/DPO-Qwen3-LiteOS-ecb96fbe6 download history

HaoranLiu/DPO-Qwen3-LiteOS-ecb96fbe6 is an other dataset on the Hugging Face Hub. In the last 30 days it was downloaded 20 times (6 in the last 7 days), and 96 times in total. It ranks #374,093 among datasets by monthly downloads.

DPO-Qwen3-LiteOS-ecb96fbe6 Trajectory-level DPO preference pairs for GUI computer-use agents, built on lite.osworld (train.perturb) and tokenized for Qwen/Qwen3-VL-4B-Instruct. Generated at cua-lite commit ecb96fbe6. What a row is One (chosen, rejected) trajectory pair

Models trained on DPO-Qwen3-LiteOS-ecb96fbe6

1 models list it as training data.

Open HaoranLiu/DPO-Qwen3-LiteOS-ecb96fbe6 on Hugging Face

Sister project: Paper Pulse, the upvote history of every Hugging Face Daily Paper.