five

ReactiveAI/Beta-Progressive-DMPO

收藏
Hugging Face2026-03-31 更新2026-04-12 收录
下载链接:
https://hf-mirror.com/datasets/ReactiveAI/Beta-Progressive-DMPO
下载链接
链接失效反馈
官方服务:
资源简介:
--- dataset_info: config_name: steps-7 features: - name: interactions list: - name: answer dtype: string - name: internal dtype: string - name: query dtype: string - name: think dtype: string - name: tool_call dtype: string - name: tool_response dtype: string - name: model dtype: string - name: mode dtype: string splits: - name: train num_bytes: 1180648267.271233 num_examples: 52916 download_size: 551479835 dataset_size: 1180648267.271233 configs: - config_name: steps-7 data_files: - split: train path: steps-7/train-* ---
提供机构:
ReactiveAI
二维码
社区交流群
二维码
科研交流群
商业服务