silsilhfu/albanian-wiki-clean-lm

---
dataset_info:
features:
- name: input_ids
list: int32
- name: attention_mask
list: int8
- name: labels
list: int64
splits:
- name: train
num_bytes: 869193804
num_examples: 130353
- name: test
num_bytes: 44982328
num_examples: 6746
download_size: 241082451
dataset_size: 914176132
configs:
- config_name: default
data_files:
- split: train
path: data/train-*
- split: test
path: data/test-*
---