PetarKal/curated-ascii-mix-v5-deduped

--- dataset_info: features: - name: messages list: - name: content dtype: string - name: role dtype: string - name: source dtype: string - name: source_dataset dtype: string - name: bucket dtype: string - name: category dtype: string - name: family_id dtype: string - name: prompt_family dtype: string - name: quality_score dtype: float64 - name: chosen_variant dtype: string splits: - name: train num_bytes: 11742919 num_examples: 10052 - name: validation num_bytes: 849209 num_examples: 727 download_size: 11288305 dataset_size: 12592128 configs: - config_name: default data_files: - split: train path: data/train-* - split: validation path: data/validation-* ---