HF RL Explorer

sungyub/skywork-or1-code-verl

skywork-or1-code-verl: Skywork-OR1-RL-Data (Code Split - Cleaned): RL dataset on Hugging Face. This dataset contains 14,057 coding problems from the Skywork-OR1-RL-Data dataset, cleaned of repetitive instruction prefixes. The dataset is in VERL format and includes model difficulty ratings for…

sungyub/skywork-or1-code-verl on the Hugging Face Hub