five

gloriafree/RM-R1-after-Distill-RLVR-Debiased

收藏
Hugging Face2026-03-04 更新2026-03-29 收录
下载链接:
https://hf-mirror.com/datasets/gloriafree/RM-R1-after-Distill-RLVR-Debiased
下载链接
链接失效反馈
官方服务:
资源简介:
--- dataset_info: features: - name: context_messages list: - name: content dtype: string - name: role dtype: string - name: winner dtype: string - name: ground_truth dtype: string splits: - name: train num_bytes: 977482500 num_examples: 128452 download_size: 318175255 dataset_size: 977482500 configs: - config_name: default data_files: - split: train path: data/train-* ---
提供机构:
gloriafree
二维码
社区交流群
二维码
科研交流群
商业服务