ggg-llms-team/wikipedia-pt-br-extract-cpt-2048-traineval

--- dataset_info: features: - name: title dtype: string - name: page_id dtype: string - name: text dtype: string - name: ns dtype: int32 - name: section_texts list: string - name: token_count dtype: int64 - name: chunk_index dtype: int64 - name: chunk_total dtype: int64 splits: - name: train num_bytes: 21285863235 num_examples: 1369663 - name: validation num_bytes: 1128785770 num_examples: 72633 download_size: 8313437620 dataset_size: 22414649005 configs: - config_name: default data_files: - split: train path: data/train-* - split: validation path: data/validation-* ---