alina0195/fineweb2-ro-split

--- dataset_info: features: - name: id dtype: string - name: text dtype: string - name: url dtype: string - name: date dtype: string - name: dump dtype: string - name: file_path dtype: string - name: language_score dtype: float64 - name: minhash_cluster_size dtype: int64 - name: top_langs dtype: string - name: output dtype: string - name: explanation dtype: string - name: int_score dtype: string - name: age_group dtype: string - name: topic dtype: string - name: subtopic dtype: string - name: format dtype: string splits: - name: train num_bytes: 4944006065 num_examples: 952380 - name: validation num_bytes: 548795000 num_examples: 105820 download_size: 2919207305 dataset_size: 5492801065 configs: - config_name: default data_files: - split: train path: data/train-* - split: validation path: data/validation-* ---