fpadovani/goldfish-eng-latn-100mb-tokenized

---
dataset_info:
features:
- name: input_ids
list: int32
- name: attention_mask
list: int8
splits:
- name: train
num_bytes: 102126127
num_examples: 284899
- name: validation
num_bytes: 10724589
num_examples: 31013
download_size: 179274581
dataset_size: 112850716
configs:
- config_name: default
data_files:
- split: train
path: data/train-*
- split: validation
path: data/validation-*
---