asaverren/openhands-divergence-dpo download history
asaverren/openhands-divergence-dpo is a text generation dataset on the Hugging Face Hub. In the last 30 days it was downloaded 75 times (12 in the last 7 days), and 75 times in total. It ranks #139,686 among datasets by monthly downloads.
openhands-divergence-dpo 5,420 divergence-point DPO pairs mined from nebius/SWE-rebench-openhands-trajectories (67,074 OpenHands v0.54.0 trajectories by Qwen3-Coder-480B-A35B-Instruct on real GitHub issues from SWE-rebench). Where Nebius released raw trajectories for RFT/RL, this data
Models trained on openhands-divergence-dpo
1 models list it as training data.
- asaverren/qwen35-4b-openhands-divergence-dpo 89 downloads in 30 days
Open asaverren/openhands-divergence-dpo on Hugging Face
Sister project: Paper Pulse, the upvote history of every Hugging Face Daily Paper.