YangyiYY/rl-value-confidence-train download history
YangyiYY/rl-value-confidence-train is a text generation dataset on the Hugging Face Hub. In the last 30 days it was downloaded 22 times (4 in the last 7 days), and 114 times in total. It ranks #349,066 among datasets by monthly downloads.
rl-value-confidence-train A held-out training set for a confidence / correctness estimator (~5.7k prompts), paired with YangyiYY/rl-value-eval (evaluation) and the nct-ppo actor/critic models. Each row is a (prompt, ground_truth) in the exact verl RL schema, so the same rule-based ver