kashif/train_rl_opd_completions download history
kashif/train_rl_opd_completions is a dataset on the Hugging Face Hub. In the last 30 days it was downloaded 120 times (33 in the last 7 days), and 1,036 times in total. It ranks #131,542 among datasets by monthly downloads.
train_rl Completion Logs This dataset contains the on-policy generations produced during RL training with train_rl. Training details Key Value Algorithm OPD Model (student) Qwen/Qwen3-8B-Base Model (teacher) Qwen/Qwen3-8B Prompt dataset openai/gsm8k G
Open kashif/train_rl_opd_completions on Hugging Face
Sister project: Paper Pulse, the upvote history of every Hugging Face Daily Paper.