David Pomerenke
commited on
Commit
·
c1db7ba
1
Parent(s):
2c21cf7
Add indic datasets
Browse files- datasets.json +73 -49
datasets.json
CHANGED
@@ -167,6 +167,17 @@
|
|
167 |
"parallel": true,
|
168 |
"base": "XNLI"
|
169 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
170 |
{
|
171 |
"name": "Okapi HellaSwag",
|
172 |
"author": "Okapi",
|
@@ -179,51 +190,23 @@
|
|
179 |
"base": "HellaSwag"
|
180 |
},
|
181 |
{
|
182 |
-
"name": "
|
183 |
-
"author": "
|
184 |
-
"url": "https://huggingface.co/datasets/
|
185 |
-
"n_languages":
|
186 |
"tasks": [
|
|
|
|
|
|
|
187 |
"ner"
|
188 |
],
|
189 |
-
"parallel":
|
190 |
-
},
|
191 |
-
{
|
192 |
-
"name": "MSVAMP",
|
193 |
-
"author": "Microsoft",
|
194 |
-
"url": "https://huggingface.co/datasets/Mathoctopus/MSVAMP",
|
195 |
-
"n_languages": 10,
|
196 |
-
"tasks": [
|
197 |
-
"math"
|
198 |
-
],
|
199 |
-
"parallel": true
|
200 |
-
},
|
201 |
-
{
|
202 |
-
"name": "XLSUM",
|
203 |
-
"author": "Academic",
|
204 |
-
"url": "https://huggingface.co/datasets/csebuetnlp/xlsum",
|
205 |
-
"n_languages": 45,
|
206 |
-
"tasks": [
|
207 |
-
"summarization"
|
208 |
-
],
|
209 |
-
"parallel": true
|
210 |
-
},
|
211 |
-
{
|
212 |
-
"name": "SEA-IFEVAL",
|
213 |
-
"author": "AI Singapore",
|
214 |
-
"url": "https://huggingface.co/datasets/aisingapore/instruction_following-ifeval",
|
215 |
-
"n_languages": 7,
|
216 |
-
"tasks": [
|
217 |
-
"instruction_following"
|
218 |
-
],
|
219 |
-
"parallel": true,
|
220 |
-
"base": "IFEVAL"
|
221 |
},
|
222 |
{
|
223 |
-
"name": "
|
224 |
-
"author": "
|
225 |
-
"url": "https://huggingface.co/
|
226 |
-
"n_languages":
|
227 |
"tasks": [
|
228 |
"translation",
|
229 |
"classification",
|
@@ -254,6 +237,16 @@
|
|
254 |
"parallel": null,
|
255 |
"base": "GLUE"
|
256 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
257 |
{
|
258 |
"name": "Opus Gnome",
|
259 |
"author": "Helsinki NLP",
|
@@ -275,25 +268,56 @@
|
|
275 |
"parallel": false
|
276 |
},
|
277 |
{
|
278 |
-
"name": "
|
279 |
-
"author": "
|
280 |
-
"url": "https://
|
281 |
-
"n_languages":
|
282 |
"tasks": [
|
283 |
"translation"
|
284 |
],
|
285 |
"parallel": false
|
286 |
},
|
287 |
{
|
288 |
-
"name": "
|
289 |
-
"author": "
|
290 |
-
"url": "https://
|
291 |
-
"n_languages":
|
292 |
"tasks": [
|
293 |
-
"
|
294 |
],
|
295 |
"parallel": false
|
296 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
297 |
{
|
298 |
"name": "MasakhaNER",
|
299 |
"author": "Masakhane",
|
|
|
167 |
"parallel": true,
|
168 |
"base": "XNLI"
|
169 |
},
|
170 |
+
{
|
171 |
+
"name": "IndicXNLI",
|
172 |
+
"author": "AI4Bharat",
|
173 |
+
"url": "https://huggingface.co/datasets/Divyanshu/indicxnli",
|
174 |
+
"n_languages": 11,
|
175 |
+
"tasks": [
|
176 |
+
"classification"
|
177 |
+
],
|
178 |
+
"parallel": true,
|
179 |
+
"base": "XNLI"
|
180 |
+
},
|
181 |
{
|
182 |
"name": "Okapi HellaSwag",
|
183 |
"author": "Okapi",
|
|
|
190 |
"base": "HellaSwag"
|
191 |
},
|
192 |
{
|
193 |
+
"name": "XTREME",
|
194 |
+
"author": "Google",
|
195 |
+
"url": "https://huggingface.co/datasets/google/xtreme",
|
196 |
+
"n_languages": 40,
|
197 |
"tasks": [
|
198 |
+
"translation",
|
199 |
+
"classification",
|
200 |
+
"question_answering",
|
201 |
"ner"
|
202 |
],
|
203 |
+
"parallel": null
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
204 |
},
|
205 |
{
|
206 |
+
"name": "IndicXTREME",
|
207 |
+
"author": "AI4Bharat",
|
208 |
+
"url": "https://huggingface.co/collections/ai4bharat/indicxtreme-66c59f576386ba2955650030",
|
209 |
+
"n_languages": 20,
|
210 |
"tasks": [
|
211 |
"translation",
|
212 |
"classification",
|
|
|
237 |
"parallel": null,
|
238 |
"base": "GLUE"
|
239 |
},
|
240 |
+
{
|
241 |
+
"name": "CCAligned",
|
242 |
+
"author": "Meta",
|
243 |
+
"url": "https://huggingface.co/datasets/ahelk/ccaligned_multilingual",
|
244 |
+
"n_languages": 137,
|
245 |
+
"tasks": [
|
246 |
+
"translation"
|
247 |
+
],
|
248 |
+
"parallel": false
|
249 |
+
},
|
250 |
{
|
251 |
"name": "Opus Gnome",
|
252 |
"author": "Helsinki NLP",
|
|
|
268 |
"parallel": false
|
269 |
},
|
270 |
{
|
271 |
+
"name": "OPUS Collection",
|
272 |
+
"author": "Helsinki NLP",
|
273 |
+
"url": "https://opus.nlpl.eu/",
|
274 |
+
"n_languages": 747,
|
275 |
"tasks": [
|
276 |
"translation"
|
277 |
],
|
278 |
"parallel": false
|
279 |
},
|
280 |
{
|
281 |
+
"name": "WikiANN / PAN-X",
|
282 |
+
"author": "Academic",
|
283 |
+
"url": "https://huggingface.co/datasets/unimelb-nlp/wikiann",
|
284 |
+
"n_languages": 176,
|
285 |
"tasks": [
|
286 |
+
"ner"
|
287 |
],
|
288 |
"parallel": false
|
289 |
},
|
290 |
+
{
|
291 |
+
"name": "MSVAMP",
|
292 |
+
"author": "Microsoft",
|
293 |
+
"url": "https://huggingface.co/datasets/Mathoctopus/MSVAMP",
|
294 |
+
"n_languages": 10,
|
295 |
+
"tasks": [
|
296 |
+
"math"
|
297 |
+
],
|
298 |
+
"parallel": true
|
299 |
+
},
|
300 |
+
{
|
301 |
+
"name": "XLSUM",
|
302 |
+
"author": "Academic",
|
303 |
+
"url": "https://huggingface.co/datasets/csebuetnlp/xlsum",
|
304 |
+
"n_languages": 45,
|
305 |
+
"tasks": [
|
306 |
+
"summarization"
|
307 |
+
],
|
308 |
+
"parallel": true
|
309 |
+
},
|
310 |
+
{
|
311 |
+
"name": "SEA-IFEVAL",
|
312 |
+
"author": "AI Singapore",
|
313 |
+
"url": "https://huggingface.co/datasets/aisingapore/instruction_following-ifeval",
|
314 |
+
"n_languages": 7,
|
315 |
+
"tasks": [
|
316 |
+
"instruction_following"
|
317 |
+
],
|
318 |
+
"parallel": true,
|
319 |
+
"base": "IFEVAL"
|
320 |
+
},
|
321 |
{
|
322 |
"name": "MasakhaNER",
|
323 |
"author": "Masakhane",
|