jihuny/llama_hh_10k_armo_s005_dpo_random
收藏官方服务:
资源简介:
--- dataset_info: features: - name: prompt dtype: string - name: chosen dtype: string - name: rejected dtype: string - name: score_chosen dtype: float64 - name: score_rejected dtype: float64 - name: reward_margin dtype: float64 splits: - name: train num_bytes: 28869695 num_examples: 10000 download_size: 16196931 dataset_size: 28869695 configs: - config_name: default data_files: - split: train path: data/train-* ---
提供机构:
jihuny


