mbzuai-ugrip-statement-tuning/flores_101_32_langs

---
dataset_info:
- config_name: af
features:
- name: label
dtype: int64
- name: statement
dtype: string
splits:
- name: train
num_bytes: 9541202
num_examples: 24925
download_size: 4773824
dataset_size: 9541202
- config_name: ar
features:
- name: label
dtype: int64
- name: statement
dtype: string
splits:
- name: train
num_bytes: 11054956
num_examples: 24925
download_size: 5387759
dataset_size: 11054956
- config_name: de
features:
- name: label
dtype: int64
- name: statement
dtype: string
splits:
- name: train
num_bytes: 9809823
num_examples: 24925
download_size: 5034332
dataset_size: 9809823
- config_name: en
features:
- name: label
dtype: int64
- name: statement
dtype: string
splits:
- name: train
num_bytes: 9258917
num_examples: 24925
download_size: 4612484
dataset_size: 9258917
- config_name: es
features:
- name: label
dtype: int64
- name: statement
dtype: string
splits:
- name: train
num_bytes: 9912211
num_examples: 24925
download_size: 5070161
dataset_size: 9912211
- config_name: fr
features:
- name: label
dtype: int64
- name: statement
dtype: string
splits:
- name: train
num_bytes: 9955322
num_examples: 24925
download_size: 5076546
dataset_size: 9955322
- config_name: ga
features:
- name: label
dtype: int64
- name: statement
dtype: string
splits:
- name: train
num_bytes: 9929720
num_examples: 24925
download_size: 5097405
dataset_size: 9929720
- config_name: gu
features:
- name: label
dtype: int64
- name: statement
dtype: string
splits:
- name: train
num_bytes: 13841961
num_examples: 24925
download_size: 6023037
dataset_size: 13841961
- config_name: ha
features:
- name: label
dtype: int64
- name: statement
dtype: string
splits:
- name: train
num_bytes: 9483850
num_examples: 24925
download_size: 4764003
dataset_size: 9483850
- config_name: hi
features:
- name: label
dtype: int64
- name: statement
dtype: string
splits:
- name: train
num_bytes: 13963061
num_examples: 24925
download_size: 6017687
dataset_size: 13963061
- config_name: id
features:
- name: label
dtype: int64
- name: statement
dtype: string
splits:
- name: train
num_bytes: 9614776
num_examples: 24925
download_size: 4693763
dataset_size: 9614776
- config_name: ig
features:
- name: label
dtype: int64
- name: statement
dtype: string
splits:
- name: train
num_bytes: 9791396
num_examples: 24925
download_size: 4815865
dataset_size: 9791396
- config_name: is
features: []
splits:
- name: train
num_bytes: 0
num_examples: 0
download_size: 324
dataset_size: 0
- config_name: it
features:
- name: label
dtype: int64
- name: statement
dtype: string
splits:
- name: train
num_bytes: 9814374
num_examples: 24925
download_size: 5028836
dataset_size: 9814374
- config_name: kk
features:
- name: label
dtype: int64
- name: statement
dtype: string
splits:
- name: train
num_bytes: 11929641
num_examples: 24925
download_size: 5632599
dataset_size: 11929641
- config_name: ku
features: []
splits:
- name: train
num_bytes: 0
num_examples: 0
download_size: 324
dataset_size: 0
- config_name: ky
features:
- name: label
dtype: int64
- name: statement
dtype: string
splits:
- name: train
num_bytes: 11894418
num_examples: 24925
download_size: 5690162
dataset_size: 11894418
- config_name: la
features: []
splits:
- name: train
num_bytes: 0
num_examples: 0
download_size: 324
dataset_size: 0
- config_name: lb
features:
- name: label
dtype: int64
- name: statement
dtype: string
splits:
- name: train
num_bytes: 9884477
num_examples: 24925
download_size: 4964908
dataset_size: 9884477
- config_name: lo
features:
- name: label
dtype: int64
- name: statement
dtype: string
splits:
- name: train
num_bytes: 14451960
num_examples: 24925
download_size: 6233309
dataset_size: 14451960
- config_name: lv
features:
- name: label
dtype: int64
- name: statement
dtype: string
splits:
- name: train
num_bytes: 9667245
num_examples: 24925
download_size: 5023404
dataset_size: 9667245
- config_name: mt
features:
- name: label
dtype: int64
- name: statement
dtype: string
splits:
- name: train
num_bytes: 9761756
num_examples: 24925
download_size: 4990421
dataset_size: 9761756
- config_name: ny
features:
- name: label
dtype: int64
- name: statement
dtype: string
splits:
- name: train
num_bytes: 9648654
num_examples: 24925
download_size: 4787978
dataset_size: 9648654
- config_name: pt
features:
- name: label
dtype: int64
- name: statement
dtype: string
splits:
- name: train
num_bytes: 9706769
num_examples: 24925
download_size: 4898260
dataset_size: 9706769
- config_name: ru
features:
- name: label
dtype: int64
- name: statement
dtype: string
splits:
- name: train
num_bytes: 12310640
num_examples: 24925
download_size: 6038908
dataset_size: 12310640
- config_name: si
features: []
splits:
- name: train
num_bytes: 0
num_examples: 0
download_size: 324
dataset_size: 0
- config_name: sq
features: []
splits:
- name: train
num_bytes: 0
num_examples: 0
download_size: 324
dataset_size: 0
- config_name: sw
features:
- name: label
dtype: int64
- name: statement
dtype: string
splits:
- name: train
num_bytes: 9442868
num_examples: 24925
download_size: 4689957
dataset_size: 9442868
- config_name: tr
features:
- name: label
dtype: int64
- name: statement
dtype: string
splits:
- name: train
num_bytes: 9618050
num_examples: 24925
download_size: 4890117
dataset_size: 9618050
- config_name: vi
features:
- name: label
dtype: int64
- name: statement
dtype: string
splits:
- name: train
num_bytes: 10534745
num_examples: 24925
download_size: 5116737
dataset_size: 10534745
- config_name: yi
features: []
splits:
- name: train
num_bytes: 0
num_examples: 0
download_size: 324
dataset_size: 0
- config_name: zh
features:
- name: label
dtype: int64
- name: statement
dtype: string
splits:
- name: train
num_bytes: 9093847
num_examples: 24925
download_size: 4798082
dataset_size: 9093847
configs:
- config_name: af
data_files:
- split: train
path: af/train-*
- config_name: ar
data_files:
- split: train
path: ar/train-*
- config_name: de
data_files:
- split: train
path: de/train-*
- config_name: en
data_files:
- split: train
path: en/train-*
- config_name: es
data_files:
- split: train
path: es/train-*
- config_name: fr
data_files:
- split: train
path: fr/train-*
- config_name: ga
data_files:
- split: train
path: ga/train-*
- config_name: gu
data_files:
- split: train
path: gu/train-*
- config_name: ha
data_files:
- split: train
path: ha/train-*
- config_name: hi
data_files:
- split: train
path: hi/train-*
- config_name: id
data_files:
- split: train
path: id/train-*
- config_name: ig
data_files:
- split: train
path: ig/train-*
- config_name: is
data_files:
- split: train
path: is/train-*
- config_name: it
data_files:
- split: train
path: it/train-*
- config_name: kk
data_files:
- split: train
path: kk/train-*
- config_name: ku
data_files:
- split: train
path: ku/train-*
- config_name: ky
data_files:
- split: train
path: ky/train-*
- config_name: la
data_files:
- split: train
path: la/train-*
- config_name: lb
data_files:
- split: train
path: lb/train-*
- config_name: lo
data_files:
- split: train
path: lo/train-*
- config_name: lv
data_files:
- split: train
path: lv/train-*
- config_name: mt
data_files:
- split: train
path: mt/train-*
- config_name: ny
data_files:
- split: train
path: ny/train-*
- config_name: pt
data_files:
- split: train
path: pt/train-*
- config_name: ru
data_files:
- split: train
path: ru/train-*
- config_name: si
data_files:
- split: train
path: si/train-*
- config_name: sq
data_files:
- split: train
path: sq/train-*
- config_name: sw
data_files:
- split: train
path: sw/train-*
- config_name: tr
data_files:
- split: train
path: tr/train-*
- config_name: vi
data_files:
- split: train
path: vi/train-*
- config_name: yi
data_files:
- split: train
path: yi/train-*
- config_name: zh
data_files:
- split: train
path: zh/train-*
---