jamalimubashirali/sindhi-pretraining-corpus-part3

--- dataset_info: features: - name: book_id dtype: int64 - name: url dtype: string - name: source dtype: string - name: text dtype: string - name: chunk_index dtype: int64 - name: chunk_total dtype: int64 splits: - name: train num_bytes: 49173149 num_examples: 9237 download_size: 23401818 dataset_size: 49173149 configs: - config_name: default data_files: - split: train path: data/train-* ---