ReySajju742/shaistagi_standardized

---
dataset_info:
- config_name: c4
features:
- name: text
dtype: string
splits:
- name: train
num_bytes: 10907184854
num_examples: 1950124
download_size: 5175849125
dataset_size: 10907184854
- config_name: cc100
features:
- name: text
dtype: string
splits:
- name: train
num_bytes: 6358892405
num_examples: 22866293
download_size: 3061780499
dataset_size: 6358892405
- config_name: local
features:
- name: text
dtype: string
splits:
- name: train
num_bytes: 3577775
num_examples: 24492
download_size: 1882920
dataset_size: 3577775
- config_name: names
features:
- name: text
dtype: string
splits:
- name: train
num_bytes: 5668
num_examples: 545
download_size: 5381
dataset_size: 5668
- config_name: nmt
features:
- name: text
dtype: string
splits:
- name: train
num_bytes: 2457166692
num_examples: 20269560
download_size: 1417538349
dataset_size: 2457166692
- config_name: reasoning_parquet
features:
- name: text
dtype: string
splits:
- name: train
num_bytes: 70812344
num_examples: 199999
download_size: 18780484
dataset_size: 70812344
- config_name: roman_urdu
features:
- name: text
dtype: string
splits:
- name: train
num_bytes: 16560931
num_examples: 314273
download_size: 11211425
dataset_size: 16560931
- config_name: sentiment
features:
- name: text
dtype: string
splits:
- name: train
num_bytes: 178502
num_examples: 7073
download_size: 117199
dataset_size: 178502
configs:
- config_name: c4
data_files:
- split: train
path: c4/train-*
- config_name: cc100
data_files:
- split: train
path: cc100/train-*
- config_name: local
data_files:
- split: train
path: local/train-*
- config_name: names
data_files:
- split: train
path: names/train-*
- config_name: nmt
data_files:
- split: train
path: nmt/train-*
- config_name: reasoning_parquet
data_files:
- split: train
path: reasoning_parquet/train-*
- config_name: roman_urdu
data_files:
- split: train
path: roman_urdu/train-*
- config_name: sentiment
data_files:
- split: train
path: sentiment/train-*
---