aditya-6122/tinystories-custom-full-dataset-vs-4k-v1

---
dataset_info:
features:
- name: input_ids
list: int32
- name: output_ids
list: int64
- name: text
dtype: string
splits:
- name: train
num_bytes: 4908254156
num_examples: 1667691
- name: validation
num_bytes: 1225831699
num_examples: 416537
download_size: 5368392978
dataset_size: 6134085855
configs:
- config_name: default
data_files:
- split: train
path: data/train-*
- split: validation
path: data/validation-*
---