aditya-6122/tinystories-custom-vs-4k-v2

--- dataset_info: features: - name: text dtype: string - name: raw_ids list: int64 - name: text_with_special_tokens dtype: string - name: ids list: int64 splits: - name: train num_bytes: 447119562 num_examples: 100000 - name: validation num_bytes: 89570090 num_examples: 20000 download_size: 156437489 dataset_size: 536689652 configs: - config_name: default data_files: - split: train path: data/train-* - split: validation path: data/validation-* ---