hooriehsabzevari/Daniar_tokenized_

--- dataset_info: features: - name: chosen list: - name: content dtype: string - name: role dtype: string - name: reject list: - name: content dtype: string - name: role dtype: string - name: chosen_token sequence: int64 - name: reject_token sequence: int64 - name: chosen_mask sequence: int64 - name: reject_mask sequence: int64 - name: chosen_reward dtype: float64 - name: reject_reward dtype: float64 splits: - name: train num_bytes: 4353712137.024563 num_examples: 8390 - name: test num_bytes: 484149394.9754371 num_examples: 933 download_size: 41522247 dataset_size: 4837861532.0 configs: - config_name: default data_files: - split: train path: data/train-* - split: test path: data/test-* ---