fpadovani/goldfish-swa-latn-10mb-tokenized

---
dataset_info:
features:
- name: input_ids
list: int32
- name: attention_mask
list: int8
splits:
- name: train
num_bytes: 15248242
num_examples: 113174
- name: validation
num_bytes: 1525387
num_examples: 11284
download_size: 26068435
dataset_size: 16773629
configs:
- config_name: default
data_files:
- split: train
path: data/train-*
- split: validation
path: data/validation-*
---