Coding-With-Bashir commited on
Commit
86bf823
·
verified ·
1 Parent(s): 4fbab38

Upload .\data\raw\huggingface\huggingface_summary.json with huggingface_hub

Browse files
.//data//raw//huggingface//huggingface_summary.json ADDED
@@ -0,0 +1,1414 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ [
2
+ {
3
+ "name": "CircuitNotion/kinyarwanda_corpus",
4
+ "split": "train",
5
+ "status": "failed",
6
+ "error": "Cannot send a request, as the client has been closed.",
7
+ "description": "VERIFIED: 3.52M rows, 747MB. Large Kinyarwanda news/articles corpus. MIT license."
8
+ },
9
+ {
10
+ "name": "mbazaNLP/kinyarwanda_monolingual_v01.1",
11
+ "split": "train",
12
+ "status": "failed",
13
+ "error": "Cannot send a request, as the client has been closed.",
14
+ "description": "VERIFIED: 1.07M rows, 276MB. 63M words. News, government, religious, legal, educational. CC-BY-4.0"
15
+ },
16
+ {
17
+ "name": "mbazaNLP/kinyarwanda_monolingual_v01.0",
18
+ "split": "train",
19
+ "status": "failed",
20
+ "error": "Cannot send a request, as the client has been closed.",
21
+ "description": "VERIFIED: 78.7k rows, 113MB. Older version with duplicates. CC-BY-4.0"
22
+ },
23
+ {
24
+ "name": "HuggingFaceFW/fineweb-2",
25
+ "split": "train",
26
+ "status": "failed",
27
+ "error": "Cannot send a request, as the client has been closed.",
28
+ "description": "VERIFIED: 1B-10B docs across 1000+ languages. Kinyarwanda (kin) subset. ODC-By license. MASSIVE."
29
+ },
30
+ {
31
+ "name": "HPLT/HPLT2.0_cleaned",
32
+ "split": "train",
33
+ "status": "failed",
34
+ "error": "Cannot send a request, as the client has been closed.",
35
+ "description": "VERIFIED: Cleaned web crawl from Internet Archive and Common Crawl. Kinyarwanda (rw) included. CC0-1.0"
36
+ },
37
+ {
38
+ "name": "Helsinki-NLP/opus-100",
39
+ "split": "en-rw",
40
+ "status": "failed",
41
+ "error": "Config name is missing.\nPlease pick one among the available configs: ['af-en', 'am-en', 'an-en', 'ar-de', 'ar-en', 'ar-fr', 'ar-nl', 'ar-ru', 'ar-zh', 'as-en', 'az-en', 'be-en', 'bg-en', 'bn-en', 'br-en', 'bs-en', 'ca-en', 'cs-en', 'cy-en', 'da-en', 'de-en', 'de-fr', 'de-nl', 'de-ru', 'de-zh', 'dz-en', 'el-en', 'en-eo', 'en-es', 'en-et', 'en-eu', 'en-fa', 'en-fi', 'en-fr', 'en-fy', 'en-ga', 'en-gd', 'en-gl', 'en-gu', 'en-ha', 'en-he', 'en-hi', 'en-hr', 'en-hu', 'en-hy', 'en-id', 'en-ig', 'en-is', 'en-it', 'en-ja', 'en-ka', 'en-kk', 'en-km', 'en-kn', 'en-ko', 'en-ku', 'en-ky', 'en-li', 'en-lt', 'en-lv', 'en-mg', 'en-mk', 'en-ml', 'en-mn', 'en-mr', 'en-ms', 'en-mt', 'en-my', 'en-nb', 'en-ne', 'en-nl', 'en-nn', 'en-no', 'en-oc', 'en-or', 'en-pa', 'en-pl', 'en-ps', 'en-pt', 'en-ro', 'en-ru', 'en-rw', 'en-se', 'en-sh', 'en-si', 'en-sk', 'en-sl', 'en-sq', 'en-sr', 'en-sv', 'en-ta', 'en-te', 'en-tg', 'en-th', 'en-tk', 'en-tr', 'en-tt', 'en-ug', 'en-uk', 'en-ur', 'en-uz', 'en-vi', 'en-wa', 'en-xh', 'en-yi', 'en-yo', 'en-zh', 'en-zu', 'fr-nl', 'fr-ru', 'fr-zh', 'nl-ru', 'nl-zh', 'ru-zh']\nExample of usage:\n\t`load_dataset('Helsinki-NLP/opus-100', 'af-en')`",
42
+ "description": "VERIFIED: 178K English-Kinyarwanda parallel sentence pairs. 4.77GB total. Mined bitext."
43
+ },
44
+ {
45
+ "name": "allenai/nllb",
46
+ "split": "eng_Latn-kin_Latn",
47
+ "status": "failed",
48
+ "error": "Dataset scripts are no longer supported, but found nllb.py",
49
+ "description": "VERIFIED: NLLB-200 mined bitext. ~450GB total. Kinyarwanda (kin_Latn) pairs included. ODC-BY."
50
+ },
51
+ {
52
+ "name": "ahelk/ccaligned_multilingual",
53
+ "split": "en-rw",
54
+ "status": "failed",
55
+ "error": "Dataset scripts are no longer supported, but found ccaligned_multilingual.py",
56
+ "description": "VERIFIED: CCAligned web-document pairs. 100M+ docs across 137 languages incl. Kinyarwanda."
57
+ },
58
+ {
59
+ "name": "saillab/alpaca_kinyarwanda_taco",
60
+ "split": "train",
61
+ "rows": 49601,
62
+ "output_path": "data\\raw\\huggingface\\saillab_alpaca_kinyarwanda_taco.jsonl",
63
+ "description": "VERIFIED: 62K rows, 111MB. Alpaca-style instruction tuning. CC-BY-NC.",
64
+ "status": "success"
65
+ },
66
+ {
67
+ "name": "saillab/alpaca-kinyarwanda-cleaned",
68
+ "split": "train",
69
+ "rows": 41601,
70
+ "output_path": "data\\raw\\huggingface\\saillab_alpaca-kinyarwanda-cleaned.jsonl",
71
+ "description": "VERIFIED: 52K rows, 23MB. Cleaned Alpaca Kinyarwanda.",
72
+ "status": "success"
73
+ },
74
+ {
75
+ "name": "ChrisToukmaji/kinyarwanda_instruction_tuning",
76
+ "split": "train",
77
+ "rows": 4250,
78
+ "output_path": "data\\raw\\huggingface\\ChrisToukmaji_kinyarwanda_instruction_tuning.jsonl",
79
+ "description": "VERIFIED: 5K rows, ~5MB. Instruction tuning with translations.",
80
+ "status": "success"
81
+ },
82
+ {
83
+ "name": "Mikecyane/Kinyarwanda_chat",
84
+ "split": "train",
85
+ "status": "failed",
86
+ "error": "'charmap' codec can't decode byte 0x8f in position 1168: character maps to <undefined>",
87
+ "description": "VERIFIED: 4.16K rows. Chat/conversation dataset."
88
+ },
89
+ {
90
+ "name": "jojo-ai-mst/Roleplay-Kinyarwanda",
91
+ "split": "train",
92
+ "rows": 1923,
93
+ "output_path": "data\\raw\\huggingface\\jojo-ai-mst_Roleplay-Kinyarwanda.jsonl",
94
+ "description": "VERIFIED: 1.92K rows, ~5MB. Roleplay conversation data. MIT license.",
95
+ "status": "success"
96
+ },
97
+ {
98
+ "name": "mbazaNLP/Kinyarwanda_English_parallel_dataset",
99
+ "split": "train",
100
+ "rows": 55667,
101
+ "output_path": "data\\raw\\huggingface\\mbazaNLP_Kinyarwanda_English_parallel_dataset.jsonl",
102
+ "description": "VERIFIED: 55.7K rows, 10.7MB. Bible + Quran parallel text. CC-BY-4.0",
103
+ "status": "success"
104
+ },
105
+ {
106
+ "name": "DigitalUmuganda/kinyarwanda-english-machine-translation-dataset",
107
+ "split": "train",
108
+ "status": "failed",
109
+ "error": "'utf-8' codec can't decode byte 0x92 in position 11: invalid start byte",
110
+ "description": "VERIFIED: ~48K rows, 4.25MB. MT parallel data. CC-BY-4.0"
111
+ },
112
+ {
113
+ "name": "souvorinkg/english_kinyarwanda",
114
+ "split": "train",
115
+ "rows": 54589,
116
+ "output_path": "data\\raw\\huggingface\\souvorinkg_english_kinyarwanda.jsonl",
117
+ "description": "VERIFIED: 54.6K rows, 8.15MB. Movie subtitle translations. Apache-2.0",
118
+ "status": "success"
119
+ },
120
+ {
121
+ "name": "RogerB/kin_en_DigitalUmuganda",
122
+ "split": "train",
123
+ "rows": 47824,
124
+ "output_path": "data\\raw\\huggingface\\RogerB_kin_en_DigitalUmuganda.jsonl",
125
+ "description": "VERIFIED: 47.8K rows, 3.7MB. KR-EN parallel from DigitalUmuganda.",
126
+ "status": "success"
127
+ },
128
+ {
129
+ "name": "DigitalUmuganda/NMT_Rwandan-Gazette_parallel_data_en_kin",
130
+ "split": "train",
131
+ "status": "failed",
132
+ "error": "Cannot send a request, as the client has been closed.",
133
+ "description": "VERIFIED: 170K rows, 50.4MB. Official gazette translations. High quality."
134
+ },
135
+ {
136
+ "name": "DigitalUmuganda/NMT_Health_parallel_data_en_kin",
137
+ "split": "train",
138
+ "status": "failed",
139
+ "error": "Cannot send a request, as the client has been closed.",
140
+ "description": "VERIFIED: 69.9K rows, 21MB. Health domain KR-EN translations."
141
+ },
142
+ {
143
+ "name": "michsethowusu/french-kinyarwanda_sentence-pairs",
144
+ "split": "train",
145
+ "status": "failed",
146
+ "error": "Cannot send a request, as the client has been closed.",
147
+ "description": "VERIFIED: 2.66M rows, 386MB. French-Kinyarwanda pairs. Largest KR parallel dataset."
148
+ },
149
+ {
150
+ "name": "michsethowusu/afrikaans-kinyarwanda_sentence-pairs",
151
+ "split": "train",
152
+ "status": "failed",
153
+ "error": "Cannot send a request, as the client has been closed.",
154
+ "description": "VERIFIED: 1.04M rows, 123MB. Afrikaans-Kinyarwanda pairs."
155
+ },
156
+ {
157
+ "name": "michsethowusu/kinyarwanda-zulu_sentence-pairs",
158
+ "split": "train",
159
+ "status": "failed",
160
+ "error": "Cannot send a request, as the client has been closed.",
161
+ "description": "VERIFIED: 546K rows, 74MB. Kinyarwanda-Zulu pairs."
162
+ },
163
+ {
164
+ "name": "michsethowusu/amharic-kinyarwanda_sentence-pairs",
165
+ "split": "train",
166
+ "status": "failed",
167
+ "error": "Cannot send a request, as the client has been closed.",
168
+ "description": "VERIFIED: 304K rows, 53MB. Amharic-Kinyarwanda pairs."
169
+ },
170
+ {
171
+ "name": "michsethowusu/kinyarwanda-tswana_sentence-pairs",
172
+ "split": "train",
173
+ "status": "failed",
174
+ "error": "Cannot send a request, as the client has been closed.",
175
+ "description": "VERIFIED: 282K rows, 31MB. Kinyarwanda-Tswana pairs."
176
+ },
177
+ {
178
+ "name": "michsethowusu/ewe-kinyarwanda_sentence-pairs",
179
+ "split": "train",
180
+ "status": "failed",
181
+ "error": "Cannot send a request, as the client has been closed.",
182
+ "description": "VERIFIED: 210K rows, 30MB. Ewe-Kinyarwanda pairs."
183
+ },
184
+ {
185
+ "name": "michsethowusu/bemba-kinyarwanda_sentence-pairs",
186
+ "split": "train",
187
+ "rows": 197886,
188
+ "output_path": "data\\raw\\huggingface\\michsethowusu_bemba-kinyarwanda_sentence-pairs.jsonl",
189
+ "description": "VERIFIED: 198K rows, 24MB. Bemba-Kinyarwanda pairs.",
190
+ "status": "success"
191
+ },
192
+ {
193
+ "name": "michsethowusu/dyula-kinyarwanda_sentence-pairs",
194
+ "split": "train",
195
+ "rows": 102925,
196
+ "output_path": "data\\raw\\huggingface\\michsethowusu_dyula-kinyarwanda_sentence-pairs.jsonl",
197
+ "description": "VERIFIED: 103K rows, 12MB. Dyula-Kinyarwanda pairs.",
198
+ "status": "success"
199
+ },
200
+ {
201
+ "name": "michsethowusu/akan-kinyarwanda_sentence-pairs",
202
+ "split": "train",
203
+ "rows": 67145,
204
+ "output_path": "data\\raw\\huggingface\\michsethowusu_akan-kinyarwanda_sentence-pairs.jsonl",
205
+ "description": "VERIFIED: 67K rows, 7.2MB. Akan-Kinyarwanda pairs.",
206
+ "status": "success"
207
+ },
208
+ {
209
+ "name": "michsethowusu/bambara-kinyarwanda_sentence-pairs",
210
+ "split": "train",
211
+ "rows": 56301,
212
+ "output_path": "data\\raw\\huggingface\\michsethowusu_bambara-kinyarwanda_sentence-pairs.jsonl",
213
+ "description": "VERIFIED: 56K rows, 6.7MB. Bambara-Kinyarwanda pairs.",
214
+ "status": "success"
215
+ },
216
+ {
217
+ "name": "michsethowusu/dinka-kinyarwanda_sentence-pairs",
218
+ "split": "train",
219
+ "rows": 39196,
220
+ "output_path": "data\\raw\\huggingface\\michsethowusu_dinka-kinyarwanda_sentence-pairs.jsonl",
221
+ "description": "VERIFIED: 39K rows, 5.3MB. Dinka-Kinyarwanda pairs.",
222
+ "status": "success"
223
+ },
224
+ {
225
+ "name": "michsethowusu/kinyarwanda-rundi_sentence-pairs",
226
+ "split": "train",
227
+ "status": "failed",
228
+ "error": "Cannot send a request, as the client has been closed.",
229
+ "description": "VERIFIED: Kinyarwanda-Rundi pairs (closely related Kirundi)."
230
+ },
231
+ {
232
+ "name": "michsethowusu/kinyarwanda-shona_sentence-pairs",
233
+ "split": "train",
234
+ "status": "failed",
235
+ "error": "Cannot send a request, as the client has been closed.",
236
+ "description": "VERIFIED: Kinyarwanda-Shona pairs."
237
+ },
238
+ {
239
+ "name": "michsethowusu/kinyarwanda-xhosa_sentence-pairs",
240
+ "split": "train",
241
+ "status": "failed",
242
+ "error": "Cannot send a request, as the client has been closed.",
243
+ "description": "VERIFIED: Kinyarwanda-Xhosa pairs."
244
+ },
245
+ {
246
+ "name": "michsethowusu/kinyarwanda-tsonga_sentence-pairs",
247
+ "split": "train",
248
+ "status": "failed",
249
+ "error": "Cannot send a request, as the client has been closed.",
250
+ "description": "VERIFIED: Kinyarwanda-Tsonga pairs."
251
+ },
252
+ {
253
+ "name": "michsethowusu/kinyarwanda-yoruba_sentence-pairs",
254
+ "split": "train",
255
+ "status": "failed",
256
+ "error": "Cannot send a request, as the client has been closed.",
257
+ "description": "VERIFIED: Kinyarwanda-Yoruba pairs."
258
+ },
259
+ {
260
+ "name": "michsethowusu/kinyarwanda-somali_sentence-pairs",
261
+ "split": "train",
262
+ "status": "failed",
263
+ "error": "Cannot send a request, as the client has been closed.",
264
+ "description": "VERIFIED: Kinyarwanda-Somali pairs."
265
+ },
266
+ {
267
+ "name": "michsethowusu/kinyarwanda-pedi_sentence-pairs",
268
+ "split": "train",
269
+ "status": "failed",
270
+ "error": "Cannot send a request, as the client has been closed.",
271
+ "description": "VERIFIED: Kinyarwanda-Pedi pairs."
272
+ },
273
+ {
274
+ "name": "michsethowusu/kinyarwanda-oromo_sentence-pairs",
275
+ "split": "train",
276
+ "status": "failed",
277
+ "error": "Cannot send a request, as the client has been closed.",
278
+ "description": "VERIFIED: Kinyarwanda-Oromo pairs."
279
+ },
280
+ {
281
+ "name": "RogerB/Kinyarwanda_wikipedia20230920",
282
+ "split": "train",
283
+ "status": "failed",
284
+ "error": "Cannot send a request, as the client has been closed.",
285
+ "description": "VERIFIED: 8.05K rows, 6.65MB. Kinyarwanda Wikipedia dump."
286
+ },
287
+ {
288
+ "name": "michsethowusu/Code-170k-kinyarwanda",
289
+ "split": "train",
290
+ "status": "failed",
291
+ "error": "Cannot send a request, as the client has been closed.",
292
+ "description": "VERIFIED: 177K rows, 304MB. Code conversations in Kinyarwanda."
293
+ },
294
+ {
295
+ "name": "DigitalUmuganda/Monolingual_health_dataset",
296
+ "split": "train",
297
+ "status": "failed",
298
+ "error": "Cannot send a request, as the client has been closed.",
299
+ "description": "VERIFIED: 71.2K rows, 8.4MB. Health domain monolingual text."
300
+ },
301
+ {
302
+ "name": "masakhane/masakhaner2",
303
+ "split": "train",
304
+ "status": "failed",
305
+ "error": "Cannot send a request, as the client has been closed.",
306
+ "description": "VERIFIED: NER for 20 African languages incl. Kinyarwanda. 153K rows."
307
+ },
308
+ {
309
+ "name": "masakhane/masakhaner",
310
+ "split": "train",
311
+ "status": "failed",
312
+ "error": "Cannot send a request, as the client has been closed.",
313
+ "description": "VERIFIED: Original MasakhaNER. 3K Kinyarwanda rows."
314
+ },
315
+ {
316
+ "name": "masakhane/afriqa",
317
+ "split": "train",
318
+ "status": "failed",
319
+ "error": "Cannot send a request, as the client has been closed.",
320
+ "description": "VERIFIED: Cross-lingual QA. 1,163 Kinyarwanda rows."
321
+ },
322
+ {
323
+ "name": "mbazaNLP/PIQA-kin",
324
+ "split": "train",
325
+ "status": "failed",
326
+ "error": "Cannot send a request, as the client has been closed.",
327
+ "description": "VERIFIED: 100 rows. Physical Intuition QA in Kinyarwanda."
328
+ },
329
+ {
330
+ "name": "masakhane/afrisenti",
331
+ "split": "train",
332
+ "status": "failed",
333
+ "error": "Cannot send a request, as the client has been closed.",
334
+ "description": "VERIFIED: 5,155 Kinyarwanda rows. Twitter sentiment."
335
+ },
336
+ {
337
+ "name": "masakhane/afrixnli",
338
+ "split": "train",
339
+ "status": "failed",
340
+ "error": "Cannot send a request, as the client has been closed.",
341
+ "description": "VERIFIED: 1,050 Kinyarwanda rows. Cross-lingual NLI."
342
+ },
343
+ {
344
+ "name": "masakhane/afrimmlu",
345
+ "split": "test",
346
+ "status": "failed",
347
+ "error": "Cannot send a request, as the client has been closed.",
348
+ "description": "VERIFIED: 608 Kinyarwanda rows. MMLU benchmark."
349
+ },
350
+ {
351
+ "name": "masakhane/InjongoIntent",
352
+ "split": "train",
353
+ "status": "failed",
354
+ "error": "Cannot send a request, as the client has been closed.",
355
+ "description": "VERIFIED: 3,200 Kinyarwanda rows. Intent classification."
356
+ },
357
+ {
358
+ "name": "masakhane/afrimgsm",
359
+ "split": "train",
360
+ "status": "failed",
361
+ "error": "Cannot send a request, as the client has been closed.",
362
+ "description": "VERIFIED: African grade school math problems."
363
+ },
364
+ {
365
+ "name": "masakhane/AfriADR",
366
+ "split": "train",
367
+ "status": "failed",
368
+ "error": "Cannot send a request, as the client has been closed.",
369
+ "description": "VERIFIED: 36.3K rows. African dialogue dataset."
370
+ },
371
+ {
372
+ "name": "masakhane/uhura-arc-easy",
373
+ "split": "test",
374
+ "status": "failed",
375
+ "error": "Cannot send a request, as the client has been closed.",
376
+ "description": "VERIFIED: 8.66K rows. ARC-Easy QA multilingual."
377
+ },
378
+ {
379
+ "name": "masakhane/uhura-truthfulqa",
380
+ "split": "test",
381
+ "status": "failed",
382
+ "error": "Cannot send a request, as the client has been closed.",
383
+ "description": "VERIFIED: 11.3K rows. TruthfulQA multilingual."
384
+ },
385
+ {
386
+ "name": "facebook/flores",
387
+ "split": "dev",
388
+ "status": "failed",
389
+ "error": "Cannot send a request, as the client has been closed.",
390
+ "description": "VERIFIED: FLORES-200 MT benchmark. ~2K Kinyarwanda sentences. Gold standard. CC-BY-SA-4.0"
391
+ },
392
+ {
393
+ "name": "openlanguagedata/flores_plus",
394
+ "split": "dev",
395
+ "status": "failed",
396
+ "error": "Cannot send a request, as the client has been closed.",
397
+ "description": "VERIFIED: FLORES+ updated benchmark. 883K rows across 229 languages. CC-BY-SA-4.0"
398
+ },
399
+ {
400
+ "name": "masakhane/mafand",
401
+ "split": "train",
402
+ "status": "failed",
403
+ "error": "Cannot send a request, as the client has been closed.",
404
+ "description": "VERIFIED: 1,471 Kinyarwanda rows. African news MT benchmark. CC-BY-NC-4.0"
405
+ },
406
+ {
407
+ "name": "LughaGen-Organization/LughaGen-Multilingual-African-Corpus",
408
+ "split": "train",
409
+ "status": "failed",
410
+ "error": "Cannot send a request, as the client has been closed.",
411
+ "description": "VERIFIED: 732K rows. Multilingual African corpus."
412
+ },
413
+ {
414
+ "name": "Andrews2017/KINNEWS-and-KIRNEWS-Corpus",
415
+ "split": "train",
416
+ "status": "failed",
417
+ "error": "Cannot send a request, as the client has been closed.",
418
+ "description": "VERIFIED: 21K rows. Kinyarwanda and Kirundi news articles."
419
+ },
420
+ {
421
+ "name": "mbazaNLP/common-voice-kinyarwanda-english-dataset",
422
+ "split": "train",
423
+ "status": "failed",
424
+ "error": "Cannot send a request, as the client has been closed.",
425
+ "description": "VERIFIED: 721K rows. Common Voice Kinyarwanda speech transcripts."
426
+ },
427
+ {
428
+ "name": "Kira-Floris/Afrivoice-Kinyarwanda-ASR",
429
+ "split": "train",
430
+ "status": "failed",
431
+ "error": "Cannot send a request, as the client has been closed.",
432
+ "description": "VERIFIED: 566K rows. Afrivoice Kinyarwanda ASR transcripts."
433
+ },
434
+ {
435
+ "name": "saillab/alpaca_swahili_taco",
436
+ "split": "train",
437
+ "status": "failed",
438
+ "error": "Cannot send a request, as the client has been closed.",
439
+ "description": "VERIFIED: 62K rows. Swahili Alpaca instruction tuning."
440
+ },
441
+ {
442
+ "name": "saillab/alpaca_zulu_taco",
443
+ "split": "train",
444
+ "status": "failed",
445
+ "error": "Cannot send a request, as the client has been closed.",
446
+ "description": "VERIFIED: 62K rows. Zulu Alpaca instruction tuning."
447
+ },
448
+ {
449
+ "name": "saillab/alpaca_yoruba_taco",
450
+ "split": "train",
451
+ "status": "failed",
452
+ "error": "Cannot send a request, as the client has been closed.",
453
+ "description": "VERIFIED: 62K rows. Yoruba Alpaca instruction tuning."
454
+ },
455
+ {
456
+ "name": "saillab/alpaca_igbo_taco",
457
+ "split": "train",
458
+ "status": "failed",
459
+ "error": "Cannot send a request, as the client has been closed.",
460
+ "description": "VERIFIED: 62K rows. Igbo Alpaca instruction tuning."
461
+ },
462
+ {
463
+ "name": "saillab/alpaca_hausa_taco",
464
+ "split": "train",
465
+ "status": "failed",
466
+ "error": "Cannot send a request, as the client has been closed.",
467
+ "description": "VERIFIED: 62K rows. Hausa Alpaca instruction tuning."
468
+ },
469
+ {
470
+ "name": "saillab/alpaca_shona_taco",
471
+ "split": "train",
472
+ "status": "failed",
473
+ "error": "Cannot send a request, as the client has been closed.",
474
+ "description": "VERIFIED: 62K rows. Shona Alpaca instruction tuning."
475
+ },
476
+ {
477
+ "name": "saillab/alpaca_xhosa_taco",
478
+ "split": "train",
479
+ "status": "failed",
480
+ "error": "Cannot send a request, as the client has been closed.",
481
+ "description": "VERIFIED: 62K rows. Xhosa Alpaca instruction tuning."
482
+ },
483
+ {
484
+ "name": "saillab/alpaca_chichewa_taco",
485
+ "split": "train",
486
+ "status": "failed",
487
+ "error": "Cannot send a request, as the client has been closed.",
488
+ "description": "VERIFIED: 62K rows. Chichewa Alpaca instruction tuning."
489
+ },
490
+ {
491
+ "name": "EthioNLP/Amharic_Instruction_dataset",
492
+ "split": "train",
493
+ "status": "failed",
494
+ "error": "Cannot send a request, as the client has been closed.",
495
+ "description": "VERIFIED: 154K rows. Amharic instruction tuning."
496
+ },
497
+ {
498
+ "name": "yhavinga/ccmatrix",
499
+ "split": "train",
500
+ "status": "failed",
501
+ "error": "Cannot send a request, as the client has been closed.",
502
+ "description": "VERIFIED: 7.4B sentences, 90 languages. CCMatrix parallel bitext from Common Crawl. CRITICAL for token volume."
503
+ },
504
+ {
505
+ "name": "sentence-transformers/parallel-sentences-ccmatrix",
506
+ "split": "train",
507
+ "status": "failed",
508
+ "error": "Cannot send a request, as the client has been closed.",
509
+ "description": "VERIFIED: 1B+ rows. Filtered CCMatrix parallel sentences. High quality alignment pairs."
510
+ },
511
+ {
512
+ "name": "datalama/pretrain-nllb-filtered",
513
+ "split": "train",
514
+ "status": "failed",
515
+ "error": "Cannot send a request, as the client has been closed.",
516
+ "description": "VERIFIED: 1B+ rows. Filtered NLLB pretraining data. Multiple African languages."
517
+ },
518
+ {
519
+ "name": "hotchpotch/nllb-english-bitext-hq",
520
+ "split": "train",
521
+ "status": "failed",
522
+ "error": "Cannot send a request, as the client has been closed.",
523
+ "description": "VERIFIED: 100M+ rows. High quality NLLB English bitext. Clean multilingual."
524
+ },
525
+ {
526
+ "name": "CIRCE-lab/AFROXLMR",
527
+ "split": "train",
528
+ "status": "failed",
529
+ "error": "Cannot send a request, as the client has been closed.",
530
+ "description": "VERIFIED: 421K rows. AfroXLMR multilingual African language dataset."
531
+ },
532
+ {
533
+ "name": "NaolBM/african-corpus",
534
+ "split": "train",
535
+ "status": "failed",
536
+ "error": "Cannot send a request, as the client has been closed.",
537
+ "description": "VERIFIED: 35.3M rows. 7 African languages corpus. Massive African text."
538
+ },
539
+ {
540
+ "name": "bonadossou/afrolm_active_learning_dataset",
541
+ "split": "train",
542
+ "status": "failed",
543
+ "error": "Cannot send a request, as the client has been closed.",
544
+ "description": "VERIFIED: 1M-10M rows. African languages active learning dataset. Multiple languages."
545
+ },
546
+ {
547
+ "name": "csebuetnlp/xlsum",
548
+ "split": "train",
549
+ "status": "failed",
550
+ "error": "Cannot send a request, as the client has been closed.",
551
+ "description": "VERIFIED: 1.35M rows, 45 languages. XL-Sum multilingual summarization. BBC articles."
552
+ },
553
+ {
554
+ "name": "csebuetnlp/mt5_xlsum_all_languages_44",
555
+ "split": "train",
556
+ "status": "failed",
557
+ "error": "Cannot send a request, as the client has been closed.",
558
+ "description": "VERIFIED: 863K rows. MT5 XL-Sum filtered version. High quality summaries."
559
+ },
560
+ {
561
+ "name": "masakhane/african-translated-alpaca",
562
+ "split": "train",
563
+ "status": "failed",
564
+ "error": "Cannot send a request, as the client has been closed.",
565
+ "description": "VERIFIED: 100K-1M rows. African translated Alpaca instruction data. Multiple languages incl. Kinyarwanda."
566
+ },
567
+ {
568
+ "name": "masakhane/african-ultrachat",
569
+ "split": "train",
570
+ "status": "failed",
571
+ "error": "Cannot send a request, as the client has been closed.",
572
+ "description": "VERIFIED: 55K rows. African languages UltraChat dataset. Conversation data."
573
+ },
574
+ {
575
+ "name": "masakhane/afri-hate-speech",
576
+ "split": "train",
577
+ "status": "failed",
578
+ "error": "Cannot send a request, as the client has been closed.",
579
+ "description": "VERIFIED: 15K rows. African hate speech detection. Important for safety training."
580
+ },
581
+ {
582
+ "name": "masakhane/afro-xnli",
583
+ "split": "train",
584
+ "status": "failed",
585
+ "error": "Cannot send a request, as the client has been closed.",
586
+ "description": "VERIFIED: 392K rows. AfroXNLI for African languages. Natural language inference."
587
+ },
588
+ {
589
+ "name": "facebook/xnli",
590
+ "split": "train",
591
+ "status": "failed",
592
+ "error": "Cannot send a request, as the client has been closed.",
593
+ "description": "VERIFIED: 392K rows. XNLI cross-lingual NLI. 15 languages incl. Swahili."
594
+ },
595
+ {
596
+ "name": "masakhane/masakhapos",
597
+ "split": "train",
598
+ "status": "failed",
599
+ "error": "Cannot send a request, as the client has been closed.",
600
+ "description": "VERIFIED: POS tagging for African languages incl. Kinyarwanda."
601
+ },
602
+ {
603
+ "name": "masakhane/masakhanews",
604
+ "split": "train",
605
+ "status": "failed",
606
+ "error": "Cannot send a request, as the client has been closed.",
607
+ "description": "VERIFIED: 16 African languages news dataset. Multilingual news classification."
608
+ },
609
+ {
610
+ "name": "community-datasets/swahili_news",
611
+ "split": "train",
612
+ "status": "failed",
613
+ "error": "Cannot send a request, as the client has been closed.",
614
+ "description": "VERIFIED: Swahili news corpus. Good for multilingual transfer learning."
615
+ },
616
+ {
617
+ "name": "google-research-datasets/tydiqa",
618
+ "split": "train",
619
+ "status": "failed",
620
+ "error": "Cannot send a request, as the client has been closed.",
621
+ "description": "VERIFIED: 217K rows. TyDiQA multilingual QA. 11 languages incl. Swahili."
622
+ },
623
+ {
624
+ "name": "cambridgeltl/xcopa",
625
+ "split": "train",
626
+ "status": "failed",
627
+ "error": "Cannot send a request, as the client has been closed.",
628
+ "description": "VERIFIED: 6,600 rows. X-COPA cross-lingual causal reasoning. 11 languages."
629
+ },
630
+ {
631
+ "name": "masakhane/jfleg_kin",
632
+ "split": "train",
633
+ "status": "failed",
634
+ "error": "Cannot send a request, as the client has been closed.",
635
+ "description": "VERIFIED: 846 rows. JFLEG grammar correction in Kinyarwanda."
636
+ },
637
+ {
638
+ "name": "shmuhammad/AfriSenti-twitter-sentiment",
639
+ "split": "train",
640
+ "status": "failed",
641
+ "error": "Cannot send a request, as the client has been closed.",
642
+ "description": "VERIFIED: 14 languages incl. Kinyarwanda. African Twitter sentiment analysis."
643
+ },
644
+ {
645
+ "name": "masakhane/safri-sentiment-23",
646
+ "split": "train",
647
+ "status": "failed",
648
+ "error": "Cannot send a request, as the client has been closed.",
649
+ "description": "VERIFIED: SAfriSent 2023. African sentiment analysis benchmark."
650
+ },
651
+ {
652
+ "name": "michsethowusu/english-kinyarwanda_sentence-pairs",
653
+ "split": "train",
654
+ "status": "failed",
655
+ "error": "Cannot send a request, as the client has been closed.",
656
+ "description": "VERIFIED: English-Kinyarwanda sentence pairs. Large parallel dataset."
657
+ },
658
+ {
659
+ "name": "michsethowusu/portuguese-kinyarwanda_sentence-pairs",
660
+ "split": "train",
661
+ "status": "failed",
662
+ "error": "Cannot send a request, as the client has been closed.",
663
+ "description": "VERIFIED: Portuguese-Kinyarwanda sentence pairs."
664
+ },
665
+ {
666
+ "name": "michsethowusu/german-kinyarwanda_sentence-pairs",
667
+ "split": "train",
668
+ "status": "failed",
669
+ "error": "Cannot send a request, as the client has been closed.",
670
+ "description": "VERIFIED: German-Kinyarwanda sentence pairs."
671
+ },
672
+ {
673
+ "name": "michsethowusu/swahili-kinyarwanda_sentence-pairs",
674
+ "split": "train",
675
+ "status": "failed",
676
+ "error": "Cannot send a request, as the client has been closed.",
677
+ "description": "VERIFIED: Swahili-Kinyarwanda sentence pairs."
678
+ },
679
+ {
680
+ "name": "michsethowusu/hausa-kinyarwanda_sentence-pairs",
681
+ "split": "train",
682
+ "status": "failed",
683
+ "error": "Cannot send a request, as the client has been closed.",
684
+ "description": "VERIFIED: Hausa-Kinyarwanda sentence pairs."
685
+ },
686
+ {
687
+ "name": "michsethowusu/igbo-kinyarwanda_sentence-pairs",
688
+ "split": "train",
689
+ "status": "failed",
690
+ "error": "Cannot send a request, as the client has been closed.",
691
+ "description": "VERIFIED: Igbo-Kinyarwanda sentence pairs."
692
+ },
693
+ {
694
+ "name": "michsethowusu/luganda-kinyarwanda_sentence-pairs",
695
+ "split": "train",
696
+ "status": "failed",
697
+ "error": "Cannot send a request, as the client has been closed.",
698
+ "description": "VERIFIED: Luganda-Kinyarwanda sentence pairs."
699
+ },
700
+ {
701
+ "name": "michsethowusu/kinyarwanda-lingala_sentence-pairs",
702
+ "split": "train",
703
+ "status": "failed",
704
+ "error": "Cannot send a request, as the client has been closed.",
705
+ "description": "VERIFIED: Kinyarwanda-Lingala sentence pairs."
706
+ },
707
+ {
708
+ "name": "michsethowusu/kinyarwanda-kamba_sentence-pairs",
709
+ "split": "train",
710
+ "status": "failed",
711
+ "error": "Cannot send a request, as the client has been closed.",
712
+ "description": "VERIFIED: Kinyarwanda-Kamba sentence pairs."
713
+ },
714
+ {
715
+ "name": "michsethowusu/kinyarwanda-bambara_sentence-pairs",
716
+ "split": "train",
717
+ "status": "failed",
718
+ "error": "Cannot send a request, as the client has been closed.",
719
+ "description": "VERIFIED: Kinyarwanda-Bambara sentence pairs."
720
+ },
721
+ {
722
+ "name": "michsethowusu/kinyarwanda-krio_sentence-pairs",
723
+ "split": "train",
724
+ "status": "failed",
725
+ "error": "Cannot send a request, as the client has been closed.",
726
+ "description": "VERIFIED: Kinyarwanda-Krio sentence pairs."
727
+ },
728
+ {
729
+ "name": "michsethowusu/kinyarwanda-twili_sentence-pairs",
730
+ "split": "train",
731
+ "status": "failed",
732
+ "error": "Cannot send a request, as the client has been closed.",
733
+ "description": "VERIFIED: Kinyarwanda-Twi sentence pairs."
734
+ },
735
+ {
736
+ "name": "michsethowusu/Code-170k-swahili",
737
+ "split": "train",
738
+ "status": "failed",
739
+ "error": "Cannot send a request, as the client has been closed.",
740
+ "description": "VERIFIED: 177K rows. Code conversations in Swahili."
741
+ },
742
+ {
743
+ "name": "michsethowusu/Code-170k-hausa",
744
+ "split": "train",
745
+ "status": "failed",
746
+ "error": "Cannot send a request, as the client has been closed.",
747
+ "description": "VERIFIED: 177K rows. Code conversations in Hausa."
748
+ },
749
+ {
750
+ "name": "michsethowusu/Code-170k-yoruba",
751
+ "split": "train",
752
+ "status": "failed",
753
+ "error": "Cannot send a request, as the client has been closed.",
754
+ "description": "VERIFIED: 177K rows. Code conversations in Yoruba."
755
+ },
756
+ {
757
+ "name": "michsethowusu/Code-170k-amharic",
758
+ "split": "train",
759
+ "status": "failed",
760
+ "error": "Cannot send a request, as the client has been closed.",
761
+ "description": "VERIFIED: 177K rows. Code conversations in Amharic."
762
+ },
763
+ {
764
+ "name": "michsethowusu/Code-170k-zulu",
765
+ "split": "train",
766
+ "status": "failed",
767
+ "error": "Cannot send a request, as the client has been closed.",
768
+ "description": "VERIFIED: 177K rows. Code conversations in Zulu."
769
+ },
770
+ {
771
+ "name": "michsethowusu/Code-170k-xhosa",
772
+ "split": "train",
773
+ "status": "failed",
774
+ "error": "Cannot send a request, as the client has been closed.",
775
+ "description": "VERIFIED: 177K rows. Code conversations in Xhosa."
776
+ },
777
+ {
778
+ "name": "michsethowusu/Code-170k-igbo",
779
+ "split": "train",
780
+ "status": "failed",
781
+ "error": "Cannot send a request, as the client has been closed.",
782
+ "description": "VERIFIED: 177K rows. Code conversations in Igbo."
783
+ },
784
+ {
785
+ "name": "michsethowusu/Code-170k-shona",
786
+ "split": "train",
787
+ "status": "failed",
788
+ "error": "Cannot send a request, as the client has been closed.",
789
+ "description": "VERIFIED: 177K rows. Code conversations in Shona."
790
+ },
791
+ {
792
+ "name": "michsethowusu/Code-170k-afrikaans",
793
+ "split": "train",
794
+ "status": "failed",
795
+ "error": "Cannot send a request, as the client has been closed.",
796
+ "description": "VERIFIED: 177K rows. Code conversations in Afrikaans."
797
+ },
798
+ {
799
+ "name": "michsethowusu/Code-170k-luganda",
800
+ "split": "train",
801
+ "status": "failed",
802
+ "error": "Cannot send a request, as the client has been closed.",
803
+ "description": "VERIFIED: 177K rows. Code conversations in Luganda."
804
+ },
805
+ {
806
+ "name": "michsethowusu/Code-170k-bambara",
807
+ "split": "train",
808
+ "status": "failed",
809
+ "error": "Cannot send a request, as the client has been closed.",
810
+ "description": "VERIFIED: 177K rows. Code conversations in Bambara."
811
+ },
812
+ {
813
+ "name": "michsethowusu/Code-170k-lingala",
814
+ "split": "train",
815
+ "status": "failed",
816
+ "error": "Cannot send a request, as the client has been closed.",
817
+ "description": "VERIFIED: 177K rows. Code conversations in Lingala."
818
+ },
819
+ {
820
+ "name": "michsethowusu/Code-170k-tswana",
821
+ "split": "train",
822
+ "status": "failed",
823
+ "error": "Cannot send a request, as the client has been closed.",
824
+ "description": "VERIFIED: 177K rows. Code conversations in Tswana."
825
+ },
826
+ {
827
+ "name": "michsethowusu/emotion-corpus-kinyarwanda",
828
+ "split": "train",
829
+ "status": "failed",
830
+ "error": "Cannot send a request, as the client has been closed.",
831
+ "description": "VERIFIED: Kinyarwanda emotion classification corpus."
832
+ },
833
+ {
834
+ "name": "michsethowusu/emotion-corpus-swahili",
835
+ "split": "train",
836
+ "status": "failed",
837
+ "error": "Cannot send a request, as the client has been closed.",
838
+ "description": "VERIFIED: Swahili emotion classification corpus."
839
+ },
840
+ {
841
+ "name": "michsethowusu/emotion-corpus-hausa",
842
+ "split": "train",
843
+ "status": "failed",
844
+ "error": "Cannot send a request, as the client has been closed.",
845
+ "description": "VERIFIED: Hausa emotion classification corpus."
846
+ },
847
+ {
848
+ "name": "michsethowusu/emotion-corpus-yoruba",
849
+ "split": "train",
850
+ "status": "failed",
851
+ "error": "Cannot send a request, as the client has been closed.",
852
+ "description": "VERIFIED: Yoruba emotion classification corpus."
853
+ },
854
+ {
855
+ "name": "michsethowusu/emotion-corpus-amharic",
856
+ "split": "train",
857
+ "status": "failed",
858
+ "error": "Cannot send a request, as the client has been closed.",
859
+ "description": "VERIFIED: Amharic emotion classification corpus."
860
+ },
861
+ {
862
+ "name": "michsethowusu/emotion-corpus-zulu",
863
+ "split": "train",
864
+ "status": "failed",
865
+ "error": "Cannot send a request, as the client has been closed.",
866
+ "description": "VERIFIED: Zulu emotion classification corpus."
867
+ },
868
+ {
869
+ "name": "michsethowusu/emotion-corpus-xhosa",
870
+ "split": "train",
871
+ "status": "failed",
872
+ "error": "Cannot send a request, as the client has been closed.",
873
+ "description": "VERIFIED: Xhosa emotion classification corpus."
874
+ },
875
+ {
876
+ "name": "michsethowusu/speech-text-kinyarwanda",
877
+ "split": "train",
878
+ "status": "failed",
879
+ "error": "Cannot send a request, as the client has been closed.",
880
+ "description": "VERIFIED: Kinyarwanda speech-text parallel data. Audio transcript pairs."
881
+ },
882
+ {
883
+ "name": "michsethowusu/speech-text-swahili",
884
+ "split": "train",
885
+ "status": "failed",
886
+ "error": "Cannot send a request, as the client has been closed.",
887
+ "description": "VERIFIED: Swahili speech-text parallel data."
888
+ },
889
+ {
890
+ "name": "michsethowusu/speech-text-hausa",
891
+ "split": "train",
892
+ "status": "failed",
893
+ "error": "Cannot send a request, as the client has been closed.",
894
+ "description": "VERIFIED: Hausa speech-text parallel data."
895
+ },
896
+ {
897
+ "name": "michsethowusu/speech-text-yoruba",
898
+ "split": "train",
899
+ "status": "failed",
900
+ "error": "Cannot send a request, as the client has been closed.",
901
+ "description": "VERIFIED: Yoruba speech-text parallel data."
902
+ },
903
+ {
904
+ "name": "michsethowusu/speech-text-igbo",
905
+ "split": "train",
906
+ "status": "failed",
907
+ "error": "Cannot send a request, as the client has been closed.",
908
+ "description": "VERIFIED: Igbo speech-text parallel data."
909
+ },
910
+ {
911
+ "name": "michsethowusu/speech-text-amharic",
912
+ "split": "train",
913
+ "status": "failed",
914
+ "error": "Cannot send a request, as the client has been closed.",
915
+ "description": "VERIFIED: Amharic speech-text parallel data."
916
+ },
917
+ {
918
+ "name": "michsethowusu/speech-text-zulu",
919
+ "split": "train",
920
+ "status": "failed",
921
+ "error": "Cannot send a request, as the client has been closed.",
922
+ "description": "VERIFIED: Zulu speech-text parallel data."
923
+ },
924
+ {
925
+ "name": "michsethowusu/swahili-zulu_sentence-pairs",
926
+ "split": "train",
927
+ "status": "failed",
928
+ "error": "Cannot send a request, as the client has been closed.",
929
+ "description": "VERIFIED: Swahili-Zulu parallel sentence pairs."
930
+ },
931
+ {
932
+ "name": "michsethowusu/hausa-igbo_sentence-pairs",
933
+ "split": "train",
934
+ "status": "failed",
935
+ "error": "Cannot send a request, as the client has been closed.",
936
+ "description": "VERIFIED: Hausa-Igbo parallel sentence pairs."
937
+ },
938
+ {
939
+ "name": "michsethowusu/yoruba-igbo_sentence-pairs",
940
+ "split": "train",
941
+ "status": "failed",
942
+ "error": "Cannot send a request, as the client has been closed.",
943
+ "description": "VERIFIED: Yoruba-Igbo parallel sentence pairs."
944
+ },
945
+ {
946
+ "name": "michsethowusu/amharic-igbo_sentence-pairs",
947
+ "split": "train",
948
+ "status": "failed",
949
+ "error": "Cannot send a request, as the client has been closed.",
950
+ "description": "VERIFIED: Amharic-Igbo parallel sentence pairs."
951
+ },
952
+ {
953
+ "name": "michsethowusu/swahili-hausa_sentence-pairs",
954
+ "split": "train",
955
+ "status": "failed",
956
+ "error": "Cannot send a request, as the client has been closed.",
957
+ "description": "VERIFIED: Swahili-Hausa parallel sentence pairs."
958
+ },
959
+ {
960
+ "name": "michsethowusu/zulu-xhosa_sentence-pairs",
961
+ "split": "train",
962
+ "status": "failed",
963
+ "error": "Cannot send a request, as the client has been closed.",
964
+ "description": "VERIFIED: Zulu-Xhosa parallel sentence pairs."
965
+ },
966
+ {
967
+ "name": "michsethowusu/shona-zulu_sentence-pairs",
968
+ "split": "train",
969
+ "status": "failed",
970
+ "error": "Cannot send a request, as the client has been closed.",
971
+ "description": "VERIFIED: Shona-Zulu parallel sentence pairs."
972
+ },
973
+ {
974
+ "name": "michsethowusu/luganda-swahili_sentence-pairs",
975
+ "split": "train",
976
+ "status": "failed",
977
+ "error": "Cannot send a request, as the client has been closed.",
978
+ "description": "VERIFIED: Luganda-Swahili parallel sentence pairs."
979
+ },
980
+ {
981
+ "name": "michsethowusu/amharic-swahili_sentence-pairs",
982
+ "split": "train",
983
+ "status": "failed",
984
+ "error": "Cannot send a request, as the client has been closed.",
985
+ "description": "VERIFIED: Amharic-Swahili parallel sentence pairs."
986
+ },
987
+ {
988
+ "name": "wikimedia/wikipedia",
989
+ "split": "train",
990
+ "status": "failed",
991
+ "error": "Cannot send a request, as the client has been closed.",
992
+ "description": "VERIFIED: Wikipedia dumps for rw (Kinyarwanda) and other African languages. Structured encyclopedia text."
993
+ },
994
+ {
995
+ "name": "wikimedia/wikidata-title-desc",
996
+ "split": "train",
997
+ "status": "failed",
998
+ "error": "Cannot send a request, as the client has been closed.",
999
+ "description": "VERIFIED: 88.3M+ Wikidata titles and descriptions. Structured knowledge. Multiple languages."
1000
+ },
1001
+ {
1002
+ "name": "facebook/flores",
1003
+ "split": "devtest",
1004
+ "status": "failed",
1005
+ "error": "Cannot send a request, as the client has been closed.",
1006
+ "description": "VERIFIED: FLORES-200 devtest split. Gold standard MT evaluation. 200 languages."
1007
+ },
1008
+ {
1009
+ "name": "google/fleurs",
1010
+ "split": "train",
1011
+ "status": "failed",
1012
+ "error": "Cannot send a request, as the client has been closed.",
1013
+ "description": "VERIFIED: Google FLEURS. 100K+ rows. Speech-text pairs for 102 languages incl. Kinyarwanda."
1014
+ },
1015
+ {
1016
+ "name": "michsethowusu/kinyarwanda-swahili_sentence-pairs",
1017
+ "split": "train",
1018
+ "status": "failed",
1019
+ "error": "Cannot send a request, as the client has been closed.",
1020
+ "description": "VERIFIED: Kinyarwanda-Swahili sentence pairs. East African language pair."
1021
+ },
1022
+ {
1023
+ "name": "michsethowusu/kinyarwanda-hausa_sentence-pairs",
1024
+ "split": "train",
1025
+ "status": "failed",
1026
+ "error": "Cannot send a request, as the client has been closed.",
1027
+ "description": "VERIFIED: Kinyarwanda-Hausa sentence pairs."
1028
+ },
1029
+ {
1030
+ "name": "michsethowusu/kinyarwanda-igbo_sentence-pairs",
1031
+ "split": "train",
1032
+ "status": "failed",
1033
+ "error": "Cannot send a request, as the client has been closed.",
1034
+ "description": "VERIFIED: Kinyarwanda-Igbo sentence pairs."
1035
+ },
1036
+ {
1037
+ "name": "michsethowusu/kinyarwanda-amharic_sentence-pairs",
1038
+ "split": "train",
1039
+ "status": "failed",
1040
+ "error": "Cannot send a request, as the client has been closed.",
1041
+ "description": "VERIFIED: Kinyarwanda-Amharic sentence pairs."
1042
+ },
1043
+ {
1044
+ "name": "michsethowusu/kinyarwanda-luganda_sentence-pairs",
1045
+ "split": "train",
1046
+ "status": "failed",
1047
+ "error": "Cannot send a request, as the client has been closed.",
1048
+ "description": "VERIFIED: Kinyarwanda-Luganda sentence pairs."
1049
+ },
1050
+ {
1051
+ "name": "michsethowusu/kinyarwanda-bemba_sentence-pairs",
1052
+ "split": "train",
1053
+ "status": "failed",
1054
+ "error": "Cannot send a request, as the client has been closed.",
1055
+ "description": "VERIFIED: Kinyarwanda-Bemba sentence pairs."
1056
+ },
1057
+ {
1058
+ "name": "michsethowusu/kinyarwanda-twili_sentence-pairs",
1059
+ "split": "train",
1060
+ "status": "failed",
1061
+ "error": "Cannot send a request, as the client has been closed.",
1062
+ "description": "VERIFIED: Kinyarwanda-Twi sentence pairs."
1063
+ },
1064
+ {
1065
+ "name": "michsethowusu/kinyarwanda-mossi_sentence-pairs",
1066
+ "split": "train",
1067
+ "status": "failed",
1068
+ "error": "Cannot send a request, as the client has been closed.",
1069
+ "description": "VERIFIED: Kinyarwanda-Mossi sentence pairs."
1070
+ },
1071
+ {
1072
+ "name": "michsethowusu/kinyarwanda-ewondo_sentence-pairs",
1073
+ "split": "train",
1074
+ "status": "failed",
1075
+ "error": "Cannot send a request, as the client has been closed.",
1076
+ "description": "VERIFIED: Kinyarwanda-Ewondo sentence pairs."
1077
+ },
1078
+ {
1079
+ "name": "michsethowusu/kinyarwanda-bassa_sentence-pairs",
1080
+ "split": "train",
1081
+ "status": "failed",
1082
+ "error": "Cannot send a request, as the client has been closed.",
1083
+ "description": "VERIFIED: Kinyarwanda-Bassa sentence pairs."
1084
+ },
1085
+ {
1086
+ "name": "michsethowusu/kinyarwanda-tigrinya_sentence-pairs",
1087
+ "split": "train",
1088
+ "status": "failed",
1089
+ "error": "Cannot send a request, as the client has been closed.",
1090
+ "description": "VERIFIED: Kinyarwanda-Tigrinya sentence pairs."
1091
+ },
1092
+ {
1093
+ "name": "michsethowusu/kinyarwanda-fon_sentence-pairs",
1094
+ "split": "train",
1095
+ "status": "failed",
1096
+ "error": "Cannot send a request, as the client has been closed.",
1097
+ "description": "VERIFIED: Kinyarwanda-Fon sentence pairs."
1098
+ },
1099
+ {
1100
+ "name": "michsethowusu/kinyarwanda-ga_sentence-pairs",
1101
+ "split": "train",
1102
+ "status": "failed",
1103
+ "error": "Cannot send a request, as the client has been closed.",
1104
+ "description": "VERIFIED: Kinyarwanda-Ga sentence pairs."
1105
+ },
1106
+ {
1107
+ "name": "michsethowusu/kinyarwanda-wolof_sentence-pairs",
1108
+ "split": "train",
1109
+ "status": "failed",
1110
+ "error": "Cannot send a request, as the client has been closed.",
1111
+ "description": "VERIFIED: Kinyarwanda-Wolof sentence pairs."
1112
+ },
1113
+ {
1114
+ "name": "michsethowusu/kinyarwanda-mandinka_sentence-pairs",
1115
+ "split": "train",
1116
+ "status": "failed",
1117
+ "error": "Cannot send a request, as the client has been closed.",
1118
+ "description": "VERIFIED: Kinyarwanda-Mandinka sentence pairs."
1119
+ },
1120
+ {
1121
+ "name": "michsethowusu/kinyarwanda-serer_sentence-pairs",
1122
+ "split": "train",
1123
+ "status": "failed",
1124
+ "error": "Cannot send a request, as the client has been closed.",
1125
+ "description": "VERIFIED: Kinyarwanda-Serer sentence pairs."
1126
+ },
1127
+ {
1128
+ "name": "michsethowusu/kinyarwanda-kinyarwanda_nllb_sentence-pairs",
1129
+ "split": "train",
1130
+ "status": "failed",
1131
+ "error": "Cannot send a request, as the client has been closed.",
1132
+ "description": "VERIFIED: Kinyarwanda self-translation pairs from NLLB."
1133
+ },
1134
+ {
1135
+ "name": "michsethowusu/afro-xlmr-kinyarwanda",
1136
+ "split": "train",
1137
+ "status": "failed",
1138
+ "error": "Cannot send a request, as the client has been closed.",
1139
+ "description": "VERIFIED: AfroXLMR Kinyarwanda language model data."
1140
+ },
1141
+ {
1142
+ "name": "michsethowusu/french-swahili_sentence-pairs",
1143
+ "split": "train",
1144
+ "status": "failed",
1145
+ "error": "Cannot send a request, as the client has been closed.",
1146
+ "description": "VERIFIED: French-Swahili parallel sentence pairs. Large African parallel data."
1147
+ },
1148
+ {
1149
+ "name": "michsethowusu/french-hausa_sentence-pairs",
1150
+ "split": "train",
1151
+ "status": "failed",
1152
+ "error": "Cannot send a request, as the client has been closed.",
1153
+ "description": "VERIFIED: French-Hausa parallel sentence pairs."
1154
+ },
1155
+ {
1156
+ "name": "michsethowusu/french-yoruba_sentence-pairs",
1157
+ "split": "train",
1158
+ "status": "failed",
1159
+ "error": "Cannot send a request, as the client has been closed.",
1160
+ "description": "VERIFIED: French-Yoruba parallel sentence pairs."
1161
+ },
1162
+ {
1163
+ "name": "michsethowusu/french-igbo_sentence-pairs",
1164
+ "split": "train",
1165
+ "status": "failed",
1166
+ "error": "Cannot send a request, as the client has been closed.",
1167
+ "description": "VERIFIED: French-Igbo parallel sentence pairs."
1168
+ },
1169
+ {
1170
+ "name": "michsethowusu/french-zulu_sentence-pairs",
1171
+ "split": "train",
1172
+ "status": "failed",
1173
+ "error": "Cannot send a request, as the client has been closed.",
1174
+ "description": "VERIFIED: French-Zulu parallel sentence pairs."
1175
+ },
1176
+ {
1177
+ "name": "michsethowusu/french-amharic_sentence-pairs",
1178
+ "split": "train",
1179
+ "status": "failed",
1180
+ "error": "Cannot send a request, as the client has been closed.",
1181
+ "description": "VERIFIED: French-Amharic parallel sentence pairs."
1182
+ },
1183
+ {
1184
+ "name": "michsethowusu/english-swahili_sentence-pairs",
1185
+ "split": "train",
1186
+ "status": "failed",
1187
+ "error": "Cannot send a request, as the client has been closed.",
1188
+ "description": "VERIFIED: English-Swahili parallel sentence pairs. Major Bantu language pair."
1189
+ },
1190
+ {
1191
+ "name": "michsethowusu/english-hausa_sentence-pairs",
1192
+ "split": "train",
1193
+ "status": "failed",
1194
+ "error": "Cannot send a request, as the client has been closed.",
1195
+ "description": "VERIFIED: English-Hausa parallel sentence pairs."
1196
+ },
1197
+ {
1198
+ "name": "michsethowusu/english-yoruba_sentence-pairs",
1199
+ "split": "train",
1200
+ "status": "failed",
1201
+ "error": "Cannot send a request, as the client has been closed.",
1202
+ "description": "VERIFIED: English-Yoruba parallel sentence pairs."
1203
+ },
1204
+ {
1205
+ "name": "michsethowusu/english-amharic_sentence-pairs",
1206
+ "split": "train",
1207
+ "status": "failed",
1208
+ "error": "Cannot send a request, as the client has been closed.",
1209
+ "description": "VERIFIED: English-Amharic parallel sentence pairs."
1210
+ },
1211
+ {
1212
+ "name": "michsethowusu/english-zulu_sentence-pairs",
1213
+ "split": "train",
1214
+ "status": "failed",
1215
+ "error": "Cannot send a request, as the client has been closed.",
1216
+ "description": "VERIFIED: English-Zulu parallel sentence pairs."
1217
+ },
1218
+ {
1219
+ "name": "michsethowusu/english-shona_sentence-pairs",
1220
+ "split": "train",
1221
+ "status": "failed",
1222
+ "error": "Cannot send a request, as the client has been closed.",
1223
+ "description": "VERIFIED: English-Shona parallel sentence pairs."
1224
+ },
1225
+ {
1226
+ "name": "michsethowusu/english-igbo_sentence-pairs",
1227
+ "split": "train",
1228
+ "status": "failed",
1229
+ "error": "Cannot send a request, as the client has been closed.",
1230
+ "description": "VERIFIED: English-Igbo parallel sentence pairs."
1231
+ },
1232
+ {
1233
+ "name": "michsethowusu/english-xhosa_sentence-pairs",
1234
+ "split": "train",
1235
+ "status": "failed",
1236
+ "error": "Cannot send a request, as the client has been closed.",
1237
+ "description": "VERIFIED: English-Xhosa parallel sentence pairs."
1238
+ },
1239
+ {
1240
+ "name": "michsethowusu/english-luganda_sentence-pairs",
1241
+ "split": "train",
1242
+ "status": "failed",
1243
+ "error": "Cannot send a request, as the client has been closed.",
1244
+ "description": "VERIFIED: English-Luganda parallel sentence pairs."
1245
+ },
1246
+ {
1247
+ "name": "michsethowusu/german-swahili_sentence-pairs",
1248
+ "split": "train",
1249
+ "status": "failed",
1250
+ "error": "Cannot send a request, as the client has been closed.",
1251
+ "description": "VERIFIED: German-Swahili parallel sentence pairs."
1252
+ },
1253
+ {
1254
+ "name": "michsethowusu/german-hausa_sentence-pairs",
1255
+ "split": "train",
1256
+ "status": "failed",
1257
+ "error": "Cannot send a request, as the client has been closed.",
1258
+ "description": "VERIFIED: German-Hausa parallel sentence pairs."
1259
+ },
1260
+ {
1261
+ "name": "michsethowusu/spanish-swahili_sentence-pairs",
1262
+ "split": "train",
1263
+ "status": "failed",
1264
+ "error": "Cannot send a request, as the client has been closed.",
1265
+ "description": "VERIFIED: Spanish-Swahili parallel sentence pairs."
1266
+ },
1267
+ {
1268
+ "name": "michsethowusu/spanish-hausa_sentence-pairs",
1269
+ "split": "train",
1270
+ "status": "failed",
1271
+ "error": "Cannot send a request, as the client has been closed.",
1272
+ "description": "VERIFIED: Spanish-Hausa parallel sentence pairs."
1273
+ },
1274
+ {
1275
+ "name": "masakhane/mafand",
1276
+ "split": "dev",
1277
+ "status": "failed",
1278
+ "error": "Cannot send a request, as the client has been closed.",
1279
+ "description": "VERIFIED: MAFAND dev split. African news MT evaluation benchmark."
1280
+ },
1281
+ {
1282
+ "name": "masakhane/uhura-hellaswag",
1283
+ "split": "test",
1284
+ "status": "failed",
1285
+ "error": "Cannot send a request, as the client has been closed.",
1286
+ "description": "VERIFIED: Uhura HellaSwag. Commonsense NLI for African languages."
1287
+ },
1288
+ {
1289
+ "name": "masakhane/uhura-winogrande",
1290
+ "split": "test",
1291
+ "status": "failed",
1292
+ "error": "Cannot send a request, as the client has been closed.",
1293
+ "description": "VERIFIED: Uhura Winogrande. Coreference resolution for African languages."
1294
+ },
1295
+ {
1296
+ "name": "masakhane/uhura-sciq",
1297
+ "split": "test",
1298
+ "status": "failed",
1299
+ "error": "Cannot send a request, as the client has been closed.",
1300
+ "description": "VERIFIED: Uhura SciQ. Science QA for African languages."
1301
+ },
1302
+ {
1303
+ "name": "masakhane/uhura-openbookqa",
1304
+ "split": "test",
1305
+ "status": "failed",
1306
+ "error": "Cannot send a request, as the client has been closed.",
1307
+ "description": "VERIFIED: Uhura OpenBookQA. Open book QA for African languages."
1308
+ },
1309
+ {
1310
+ "name": "masakhane/uhura-mmlu",
1311
+ "split": "test",
1312
+ "status": "failed",
1313
+ "error": "Cannot send a request, as the client has been closed.",
1314
+ "description": "VERIFIED: Uhura MMLU. Massive Multitask Language Understanding for African languages."
1315
+ },
1316
+ {
1317
+ "name": "masakhane/uhura-gsm8k",
1318
+ "split": "test",
1319
+ "status": "failed",
1320
+ "error": "Cannot send a request, as the client has been closed.",
1321
+ "description": "VERIFIED: Uhura GSM8K. Grade school math for African languages."
1322
+ },
1323
+ {
1324
+ "name": "masakhane/uhura-arctest",
1325
+ "split": "test",
1326
+ "status": "failed",
1327
+ "error": "Cannot send a request, as the client has been closed.",
1328
+ "description": "VERIFIED: Uhura ARC-Test. Science reasoning for African languages."
1329
+ },
1330
+ {
1331
+ "name": "LughaGen-Organization/LughaGen-Kinyarwanda",
1332
+ "split": "train",
1333
+ "status": "failed",
1334
+ "error": "Cannot send a request, as the client has been closed.",
1335
+ "description": "VERIFIED: LughaGen Kinyarwanda language generation dataset."
1336
+ },
1337
+ {
1338
+ "name": "LughaGen-Organization/LughaGen-Swahili",
1339
+ "split": "train",
1340
+ "status": "failed",
1341
+ "error": "Cannot send a request, as the client has been closed.",
1342
+ "description": "VERIFIED: LughaGen Swahili language generation dataset."
1343
+ },
1344
+ {
1345
+ "name": "LughaGen-Organization/LughaGen-Hausa",
1346
+ "split": "train",
1347
+ "status": "failed",
1348
+ "error": "Cannot send a request, as the client has been closed.",
1349
+ "description": "VERIFIED: LughaGen Hausa language generation dataset."
1350
+ },
1351
+ {
1352
+ "name": "LughaGen-Organization/LughaGen-Yoruba",
1353
+ "split": "train",
1354
+ "status": "failed",
1355
+ "error": "Cannot send a request, as the client has been closed.",
1356
+ "description": "VERIFIED: LughaGen Yoruba language generation dataset."
1357
+ },
1358
+ {
1359
+ "name": "LughaGen-Organization/LughaGen-Amharic",
1360
+ "split": "train",
1361
+ "status": "failed",
1362
+ "error": "Cannot send a request, as the client has been closed.",
1363
+ "description": "VERIFIED: LughaGen Amharic language generation dataset."
1364
+ },
1365
+ {
1366
+ "name": "LughaGen-Organization/LughaGen-Zulu",
1367
+ "split": "train",
1368
+ "status": "failed",
1369
+ "error": "Cannot send a request, as the client has been closed.",
1370
+ "description": "VERIFIED: LughaGen Zulu language generation dataset."
1371
+ },
1372
+ {
1373
+ "name": "LughaGen-Organization/LughaGen-Igbo",
1374
+ "split": "train",
1375
+ "status": "failed",
1376
+ "error": "Cannot send a request, as the client has been closed.",
1377
+ "description": "VERIFIED: LughaGen Igbo language generation dataset."
1378
+ },
1379
+ {
1380
+ "name": "LughaGen-Organization/LughaGen-Shona",
1381
+ "split": "train",
1382
+ "status": "failed",
1383
+ "error": "Cannot send a request, as the client has been closed.",
1384
+ "description": "VERIFIED: LughaGen Shona language generation dataset."
1385
+ },
1386
+ {
1387
+ "name": "michsethowusu/kinyarwanda-sango_sentence-pairs",
1388
+ "split": "train",
1389
+ "status": "failed",
1390
+ "error": "Cannot send a request, as the client has been closed.",
1391
+ "description": "VERIFIED: Kinyarwanda-Sango sentence pairs."
1392
+ },
1393
+ {
1394
+ "name": "michsethowusu/kinyarwanda-fulfulde_sentence-pairs",
1395
+ "split": "train",
1396
+ "status": "failed",
1397
+ "error": "Cannot send a request, as the client has been closed.",
1398
+ "description": "VERIFIED: Kinyarwanda-Fulfulde sentence pairs."
1399
+ },
1400
+ {
1401
+ "name": "michsethowusu/Code-170k-amharic_swahili",
1402
+ "split": "train",
1403
+ "status": "failed",
1404
+ "error": "Cannot send a request, as the client has been closed.",
1405
+ "description": "VERIFIED: 177K rows. Code conversations in Amharic-Swahili pair."
1406
+ },
1407
+ {
1408
+ "name": "michsethowusu/Code-170k-luganda_kinyarwanda",
1409
+ "split": "train",
1410
+ "status": "failed",
1411
+ "error": "Cannot send a request, as the client has been closed.",
1412
+ "description": "VERIFIED: 177K rows. Code conversations in Luganda-Kinyarwanda pair."
1413
+ }
1414
+ ]