DaveGabe/TinyStoriesV2_cleaned

--- dataset_info: features: - name: input_ids sequence: int32 - name: token_type_ids sequence: int8 - name: attention_mask sequence: int8 - name: length dtype: int64 - name: overflow_to_sample_mapping dtype: int64 splits: - name: train num_bytes: 433478440.53686553 num_examples: 386092 - name: test num_bytes: 54184243.70033481 num_examples: 48261 - name: validation num_bytes: 54185366.43388157 num_examples: 48262 download_size: 176697454 dataset_size: 541848050.6710819 configs: - config_name: default data_files: - split: train path: data/train-* - split: test path: data/test-* - split: validation path: data/validation-* ---