yuhan-nlp/collabllm-medium-rl-grpo download history

yuhan-nlp/collabllm-medium-rl-grpo is a text generation dataset on the Hugging Face Hub. In the last 30 days it was downloaded 13 times (1 in the last 7 days), and 73 times in total. It ranks #491,332 among datasets by monthly downloads.

CollabLLM medium — RL (GRPO) train/validation split Inputs for GRPO training on the CollabLLM medium document-writing task, as used to produce the verl-grpo-medium-qwen3-4b-step{50,100,129} checkpoints. file rows size rl_train.parquet 2072 16M rl_validation.parquet — 2.2M

Models trained on collabllm-medium-rl-grpo

6 models list it as training data.

Open yuhan-nlp/collabllm-medium-rl-grpo on Hugging Face

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