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

---
dataset_info:
features:
- name: input_ids
list: int32
- name: attention_mask
list: int8
splits:
- name: train
num_bytes: 100732316
num_examples: 320112
- name: validation
num_bytes: 10121075
num_examples: 31045
download_size: 175853720
dataset_size: 110853391
configs:
- config_name: default
data_files:
- split: train
path: data/train-*
- split: validation
path: data/validation-*
---