David Pomerenke
commited on
Commit
·
11c32ae
1
Parent(s):
c5278dd
Datasets table
Browse files- data/datasets.json +387 -0
- datasets.json +387 -0
- evals/main.py +2 -1
- frontend/public/results.json +440 -0
- frontend/src/App.css +4 -0
- frontend/src/App.js +7 -4
- frontend/src/components/DatasetTable.js +72 -0
- frontend/src/components/LanguageTable.js +5 -5
data/datasets.json
ADDED
|
@@ -0,0 +1,387 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
[
|
| 2 |
+
{
|
| 3 |
+
"name": "FLORES+",
|
| 4 |
+
"author": "Meta",
|
| 5 |
+
"url": "https://huggingface.co/datasets/openlanguagedata/flores_plus",
|
| 6 |
+
"n_languages": 200,
|
| 7 |
+
"tasks": [
|
| 8 |
+
"translation",
|
| 9 |
+
"classification",
|
| 10 |
+
"language_modeling"
|
| 11 |
+
],
|
| 12 |
+
"parallel": true,
|
| 13 |
+
"base": "FLORES",
|
| 14 |
+
"implemented": true
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"name": "FLEURS",
|
| 18 |
+
"author": "Meta",
|
| 19 |
+
"url": "https://huggingface.co/datasets/google/fleurs",
|
| 20 |
+
"n_languages": 102,
|
| 21 |
+
"tasks": [
|
| 22 |
+
"speech_recognition"
|
| 23 |
+
],
|
| 24 |
+
"parallel": true,
|
| 25 |
+
"base": "FLORES",
|
| 26 |
+
"implemented": true
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"name": "CommonVoice",
|
| 30 |
+
"author": "Mozilla",
|
| 31 |
+
"url": "https://huggingface.co/datasets/mozilla-foundation/common_voice_17_0",
|
| 32 |
+
"n_languages": 124,
|
| 33 |
+
"tasks": [
|
| 34 |
+
"speech_recognition"
|
| 35 |
+
],
|
| 36 |
+
"parallel": null
|
| 37 |
+
},
|
| 38 |
+
{
|
| 39 |
+
"name": "MMMLU",
|
| 40 |
+
"author": "OpenAI",
|
| 41 |
+
"url": "https://huggingface.co/datasets/openai/MMMLU",
|
| 42 |
+
"n_languages": "14",
|
| 43 |
+
"tasks": [
|
| 44 |
+
"question_answering"
|
| 45 |
+
],
|
| 46 |
+
"parallel": true,
|
| 47 |
+
"base": "MMLU"
|
| 48 |
+
},
|
| 49 |
+
{
|
| 50 |
+
"name": "AfriMMLU",
|
| 51 |
+
"author": "Masakhane",
|
| 52 |
+
"url": "https://huggingface.co/datasets/masakhane/afrimmlu",
|
| 53 |
+
"n_languages": "17",
|
| 54 |
+
"tasks": [
|
| 55 |
+
"question_answering"
|
| 56 |
+
],
|
| 57 |
+
"parallel": true,
|
| 58 |
+
"base": "MMLU"
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"name": "Okapi MMLU",
|
| 62 |
+
"author": "Okapi",
|
| 63 |
+
"url": "https://huggingface.co/datasets/jon-tow/okapi_mmlu",
|
| 64 |
+
"n_languages": 16,
|
| 65 |
+
"tasks": [
|
| 66 |
+
"question_answering"
|
| 67 |
+
],
|
| 68 |
+
"parallel": true,
|
| 69 |
+
"base": "MMLU"
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"name": "Global MMLU",
|
| 73 |
+
"author": "Cohere",
|
| 74 |
+
"url": "https://huggingface.co/datasets/CohereForAI/Global-MMLU",
|
| 75 |
+
"n_languages": 42,
|
| 76 |
+
"tasks": [
|
| 77 |
+
"question_answering"
|
| 78 |
+
],
|
| 79 |
+
"parallel": true,
|
| 80 |
+
"base": "MMLU"
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"name": "MGSM",
|
| 84 |
+
"author": "Google",
|
| 85 |
+
"url": "https://huggingface.co/datasets/juletxara/mgsm",
|
| 86 |
+
"n_languages": 10,
|
| 87 |
+
"tasks": [
|
| 88 |
+
"math"
|
| 89 |
+
],
|
| 90 |
+
"parallel": true,
|
| 91 |
+
"base": "MGSM"
|
| 92 |
+
},
|
| 93 |
+
{
|
| 94 |
+
"name": "AfriMGSM",
|
| 95 |
+
"author": "Masakhane",
|
| 96 |
+
"url": "https://huggingface.co/datasets/masakhane/afrimgsm",
|
| 97 |
+
"n_languages": 18,
|
| 98 |
+
"tasks": [
|
| 99 |
+
"math"
|
| 100 |
+
],
|
| 101 |
+
"parallel": true,
|
| 102 |
+
"base": "MGSM"
|
| 103 |
+
},
|
| 104 |
+
{
|
| 105 |
+
"name": "Okapi ARC Challenge",
|
| 106 |
+
"author": "Okapi",
|
| 107 |
+
"url": "https://huggingface.co/datasets/jon-tow/okapi_arc_challenge",
|
| 108 |
+
"n_languages": 31,
|
| 109 |
+
"tasks": [
|
| 110 |
+
"question_answering"
|
| 111 |
+
],
|
| 112 |
+
"parallel": true,
|
| 113 |
+
"base": "AI2 ARC"
|
| 114 |
+
},
|
| 115 |
+
{
|
| 116 |
+
"name": "Uhuru ARC Easy",
|
| 117 |
+
"author": "Masakhane",
|
| 118 |
+
"url": "https://huggingface.co/datasets/masakhane/uhura-arc-easy",
|
| 119 |
+
"n_languages": 6,
|
| 120 |
+
"tasks": [
|
| 121 |
+
"question_answering"
|
| 122 |
+
],
|
| 123 |
+
"parallel": true,
|
| 124 |
+
"base": "AI2 ARC"
|
| 125 |
+
},
|
| 126 |
+
{
|
| 127 |
+
"name": "Okapi TruthfulQA",
|
| 128 |
+
"author": "Okapi",
|
| 129 |
+
"url": "https://huggingface.co/datasets/jon-tow/okapi_truthfulqa/tree/main/data",
|
| 130 |
+
"n_languages": 31,
|
| 131 |
+
"tasks": [
|
| 132 |
+
"question_answering"
|
| 133 |
+
],
|
| 134 |
+
"parallel": true,
|
| 135 |
+
"base": "TruthfulQA"
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"name": "Uhura TruthfulQA",
|
| 139 |
+
"author": "Masakhane",
|
| 140 |
+
"url": "https://huggingface.co/datasets/masakhane/uhura-truthfulqa",
|
| 141 |
+
"n_languages": 6,
|
| 142 |
+
"tasks": [
|
| 143 |
+
"question_answering"
|
| 144 |
+
],
|
| 145 |
+
"parallel": true,
|
| 146 |
+
"base": "TruthfulQA"
|
| 147 |
+
},
|
| 148 |
+
{
|
| 149 |
+
"name": "XNLI",
|
| 150 |
+
"author": "Meta",
|
| 151 |
+
"url": "https://huggingface.co/datasets/facebook/xnli",
|
| 152 |
+
"n_languages": 14,
|
| 153 |
+
"tasks": [
|
| 154 |
+
"classification"
|
| 155 |
+
],
|
| 156 |
+
"parallel": true,
|
| 157 |
+
"base": "XNLI"
|
| 158 |
+
},
|
| 159 |
+
{
|
| 160 |
+
"name": "AfriXNLI",
|
| 161 |
+
"author": "Masakhane",
|
| 162 |
+
"url": "https://huggingface.co/datasets/masakhane/afrixnli",
|
| 163 |
+
"n_languages": 18,
|
| 164 |
+
"tasks": [
|
| 165 |
+
"classification"
|
| 166 |
+
],
|
| 167 |
+
"parallel": true,
|
| 168 |
+
"base": "XNLI"
|
| 169 |
+
},
|
| 170 |
+
{
|
| 171 |
+
"name": "Okapi HellaSwag",
|
| 172 |
+
"author": "Okapi",
|
| 173 |
+
"url": "https://huggingface.co/datasets/jon-tow/okapi_hellaswag",
|
| 174 |
+
"n_languages": 31,
|
| 175 |
+
"tasks": [
|
| 176 |
+
"question_answering"
|
| 177 |
+
],
|
| 178 |
+
"parallel": true,
|
| 179 |
+
"base": "HellaSwag"
|
| 180 |
+
},
|
| 181 |
+
{
|
| 182 |
+
"name": "WikiANN / PAN-X",
|
| 183 |
+
"author": "Academic",
|
| 184 |
+
"url": "https://huggingface.co/datasets/unimelb-nlp/wikiann",
|
| 185 |
+
"n_languages": 176,
|
| 186 |
+
"tasks": [
|
| 187 |
+
"ner"
|
| 188 |
+
],
|
| 189 |
+
"parallel": false
|
| 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": "XTREME",
|
| 224 |
+
"author": "Google",
|
| 225 |
+
"url": "https://huggingface.co/datasets/google/xtreme",
|
| 226 |
+
"n_languages": 40,
|
| 227 |
+
"tasks": [
|
| 228 |
+
"translation",
|
| 229 |
+
"classification",
|
| 230 |
+
"question_answering",
|
| 231 |
+
"ner"
|
| 232 |
+
],
|
| 233 |
+
"parallel": null
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"name": "XGLUE",
|
| 237 |
+
"author": "Microsoft",
|
| 238 |
+
"url": "https://huggingface.co/datasets/microsoft/xglue",
|
| 239 |
+
"n_languages": 18,
|
| 240 |
+
"tasks": [
|
| 241 |
+
"pos"
|
| 242 |
+
],
|
| 243 |
+
"parallel": null,
|
| 244 |
+
"base": "GLUE"
|
| 245 |
+
},
|
| 246 |
+
{
|
| 247 |
+
"name": "IndicGLUE",
|
| 248 |
+
"author": "AI4Bharat",
|
| 249 |
+
"url": "https://huggingface.co/datasets/ai4bharat/indic_glue",
|
| 250 |
+
"n_languages": 11,
|
| 251 |
+
"tasks": [
|
| 252 |
+
"question_answering"
|
| 253 |
+
],
|
| 254 |
+
"parallel": null,
|
| 255 |
+
"base": "GLUE"
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"name": "Opus Gnome",
|
| 259 |
+
"author": "Helsinki NLP",
|
| 260 |
+
"url": "https://huggingface.co/datasets/Helsinki-NLP/opus_gnome",
|
| 261 |
+
"n_languages": 187,
|
| 262 |
+
"tasks": [
|
| 263 |
+
"translation"
|
| 264 |
+
],
|
| 265 |
+
"parallel": true
|
| 266 |
+
},
|
| 267 |
+
{
|
| 268 |
+
"name": "Opus Paracrawl",
|
| 269 |
+
"author": "Helsinki NLP",
|
| 270 |
+
"url": "https://huggingface.co/datasets/Helsinki-NLP/opus_paracrawl",
|
| 271 |
+
"n_languages": 43,
|
| 272 |
+
"tasks": [
|
| 273 |
+
"translation"
|
| 274 |
+
],
|
| 275 |
+
"parallel": false
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"name": "CCAligned",
|
| 279 |
+
"author": "Meta",
|
| 280 |
+
"url": "https://huggingface.co/datasets/ahelk/ccaligned_multilingual",
|
| 281 |
+
"n_languages": 137,
|
| 282 |
+
"tasks": [
|
| 283 |
+
"translation"
|
| 284 |
+
],
|
| 285 |
+
"parallel": false
|
| 286 |
+
},
|
| 287 |
+
{
|
| 288 |
+
"name": "OPUS Collection",
|
| 289 |
+
"author": "Helsinki NLP",
|
| 290 |
+
"url": "https://opus.nlpl.eu/",
|
| 291 |
+
"n_languages": 747,
|
| 292 |
+
"tasks": [
|
| 293 |
+
"translation"
|
| 294 |
+
],
|
| 295 |
+
"parallel": false
|
| 296 |
+
},
|
| 297 |
+
{
|
| 298 |
+
"name": "MasakhaNER",
|
| 299 |
+
"author": "Masakhane",
|
| 300 |
+
"url": "https://huggingface.co/datasets/masakhane/masakhaner",
|
| 301 |
+
"n_languages": 10,
|
| 302 |
+
"tasks": [
|
| 303 |
+
"ner"
|
| 304 |
+
],
|
| 305 |
+
"parallel": null
|
| 306 |
+
},
|
| 307 |
+
{
|
| 308 |
+
"name": "Multilingual Sentiments",
|
| 309 |
+
"url": "https://huggingface.co/datasets/tyqiangz/multilingual-sentiments",
|
| 310 |
+
"n_languages": 12,
|
| 311 |
+
"tasks": [
|
| 312 |
+
"sentiment_analysis"
|
| 313 |
+
],
|
| 314 |
+
"parallel": null
|
| 315 |
+
},
|
| 316 |
+
{
|
| 317 |
+
"name": "CulturaX",
|
| 318 |
+
"author": "Academic",
|
| 319 |
+
"url": "https://huggingface.co/datasets/uonlp/CulturaX",
|
| 320 |
+
"n_languages": 167,
|
| 321 |
+
"tasks": [
|
| 322 |
+
"language_modeling"
|
| 323 |
+
],
|
| 324 |
+
"parallel": false
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"name": "Tülu 3 SFT Mixture",
|
| 328 |
+
"author": "AllenAI",
|
| 329 |
+
"url": "https://huggingface.co/datasets/allenai/tulu-3-sft-mixture",
|
| 330 |
+
"n_languages": 70,
|
| 331 |
+
"tasks": [
|
| 332 |
+
"instruction_following"
|
| 333 |
+
],
|
| 334 |
+
"parallel": false
|
| 335 |
+
},
|
| 336 |
+
{
|
| 337 |
+
"name": "xP3",
|
| 338 |
+
"author": "BigScience",
|
| 339 |
+
"url": "https://huggingface.co/datasets/bigscience/xP3",
|
| 340 |
+
"n_languages": 46,
|
| 341 |
+
"tasks": [
|
| 342 |
+
"instruction_following"
|
| 343 |
+
],
|
| 344 |
+
"parallel": false
|
| 345 |
+
},
|
| 346 |
+
{
|
| 347 |
+
"name": "Aya",
|
| 348 |
+
"author": "Cohere",
|
| 349 |
+
"url": "https://huggingface.co/datasets/CohereForAI/aya_dataset",
|
| 350 |
+
"n_languages": 65,
|
| 351 |
+
"tasks": [
|
| 352 |
+
"instruction_following"
|
| 353 |
+
],
|
| 354 |
+
"parallel": null
|
| 355 |
+
},
|
| 356 |
+
{
|
| 357 |
+
"name": "Lanfrica",
|
| 358 |
+
"author": "Lanfrica",
|
| 359 |
+
"url": "https://lanfrica.com/records?language=yor&task=machine%20translation",
|
| 360 |
+
"n_languages": 2200,
|
| 361 |
+
"tasks": [
|
| 362 |
+
"datasets"
|
| 363 |
+
],
|
| 364 |
+
"parallel": null
|
| 365 |
+
},
|
| 366 |
+
{
|
| 367 |
+
"name": "HuggingFace Languages",
|
| 368 |
+
"author": "HuggingFace",
|
| 369 |
+
"url": "https://huggingface.co/languages",
|
| 370 |
+
"n_languages": 4680,
|
| 371 |
+
"tasks": [
|
| 372 |
+
"datasets",
|
| 373 |
+
"models"
|
| 374 |
+
],
|
| 375 |
+
"parallel": null
|
| 376 |
+
},
|
| 377 |
+
{
|
| 378 |
+
"name": "HuggingFace Multilingual Datasets",
|
| 379 |
+
"author": "HuggingFace",
|
| 380 |
+
"url": "https://huggingface.co/datasets?other=multilinguality:multilingual",
|
| 381 |
+
"n_languages": null,
|
| 382 |
+
"tasks": [
|
| 383 |
+
"datasets"
|
| 384 |
+
],
|
| 385 |
+
"parallel": false
|
| 386 |
+
}
|
| 387 |
+
]
|
datasets.json
ADDED
|
@@ -0,0 +1,387 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
[
|
| 2 |
+
{
|
| 3 |
+
"name": "FLORES+",
|
| 4 |
+
"author": "Meta",
|
| 5 |
+
"url": "https://huggingface.co/datasets/openlanguagedata/flores_plus",
|
| 6 |
+
"n_languages": 185,
|
| 7 |
+
"tasks": [
|
| 8 |
+
"translation",
|
| 9 |
+
"classification",
|
| 10 |
+
"language_modeling"
|
| 11 |
+
],
|
| 12 |
+
"parallel": true,
|
| 13 |
+
"base": "FLORES",
|
| 14 |
+
"implemented": true
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"name": "FLEURS",
|
| 18 |
+
"author": "Meta",
|
| 19 |
+
"url": "https://huggingface.co/datasets/google/fleurs",
|
| 20 |
+
"n_languages": 102,
|
| 21 |
+
"tasks": [
|
| 22 |
+
"speech_recognition"
|
| 23 |
+
],
|
| 24 |
+
"parallel": true,
|
| 25 |
+
"base": "FLORES",
|
| 26 |
+
"implemented": true
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"name": "CommonVoice",
|
| 30 |
+
"author": "Mozilla",
|
| 31 |
+
"url": "https://huggingface.co/datasets/mozilla-foundation/common_voice_1_0",
|
| 32 |
+
"n_languages": 231,
|
| 33 |
+
"tasks": [
|
| 34 |
+
"speech_recognition"
|
| 35 |
+
],
|
| 36 |
+
"parallel": null
|
| 37 |
+
},
|
| 38 |
+
{
|
| 39 |
+
"name": "MMMLU",
|
| 40 |
+
"author": "OpenAI",
|
| 41 |
+
"url": "https://huggingface.co/datasets/openai/MMMLU",
|
| 42 |
+
"n_languages": "14",
|
| 43 |
+
"tasks": [
|
| 44 |
+
"question_answering"
|
| 45 |
+
],
|
| 46 |
+
"parallel": true,
|
| 47 |
+
"base": "MMLU"
|
| 48 |
+
},
|
| 49 |
+
{
|
| 50 |
+
"name": "AfriMMLU",
|
| 51 |
+
"author": "Masakhane",
|
| 52 |
+
"url": "https://huggingface.co/datasets/masakhane/afrimmlu",
|
| 53 |
+
"n_languages": "17",
|
| 54 |
+
"tasks": [
|
| 55 |
+
"question_answering"
|
| 56 |
+
],
|
| 57 |
+
"parallel": true,
|
| 58 |
+
"base": "MMLU"
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"name": "Okapi MMLU",
|
| 62 |
+
"author": "Okapi",
|
| 63 |
+
"url": "https://huggingface.co/datasets/jon-tow/okapi_mmlu",
|
| 64 |
+
"n_languages": 16,
|
| 65 |
+
"tasks": [
|
| 66 |
+
"question_answering"
|
| 67 |
+
],
|
| 68 |
+
"parallel": true,
|
| 69 |
+
"base": "MMLU"
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"name": "Global MMLU",
|
| 73 |
+
"author": "Cohere",
|
| 74 |
+
"url": "https://huggingface.co/datasets/CohereForAI/Global-MMLU",
|
| 75 |
+
"n_languages": 42,
|
| 76 |
+
"tasks": [
|
| 77 |
+
"question_answering"
|
| 78 |
+
],
|
| 79 |
+
"parallel": true,
|
| 80 |
+
"base": "MMLU"
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"name": "MGSM",
|
| 84 |
+
"author": "Google",
|
| 85 |
+
"url": "https://huggingface.co/datasets/juletxara/mgsm",
|
| 86 |
+
"n_languages": 10,
|
| 87 |
+
"tasks": [
|
| 88 |
+
"math"
|
| 89 |
+
],
|
| 90 |
+
"parallel": true,
|
| 91 |
+
"base": "MGSM"
|
| 92 |
+
},
|
| 93 |
+
{
|
| 94 |
+
"name": "AfriMGSM",
|
| 95 |
+
"author": "Masakhane",
|
| 96 |
+
"url": "https://huggingface.co/datasets/masakhane/afrimgsm",
|
| 97 |
+
"n_languages": 18,
|
| 98 |
+
"tasks": [
|
| 99 |
+
"math"
|
| 100 |
+
],
|
| 101 |
+
"parallel": true,
|
| 102 |
+
"base": "MGSM"
|
| 103 |
+
},
|
| 104 |
+
{
|
| 105 |
+
"name": "Okapi ARC Challenge",
|
| 106 |
+
"author": "Okapi",
|
| 107 |
+
"url": "https://huggingface.co/datasets/jon-tow/okapi_arc_challenge",
|
| 108 |
+
"n_languages": 31,
|
| 109 |
+
"tasks": [
|
| 110 |
+
"question_answering"
|
| 111 |
+
],
|
| 112 |
+
"parallel": true,
|
| 113 |
+
"base": "AI2 ARC"
|
| 114 |
+
},
|
| 115 |
+
{
|
| 116 |
+
"name": "Uhuru ARC Easy",
|
| 117 |
+
"author": "Masakhane",
|
| 118 |
+
"url": "https://huggingface.co/datasets/masakhane/uhura-arc-easy",
|
| 119 |
+
"n_languages": 6,
|
| 120 |
+
"tasks": [
|
| 121 |
+
"question_answering"
|
| 122 |
+
],
|
| 123 |
+
"parallel": true,
|
| 124 |
+
"base": "AI2 ARC"
|
| 125 |
+
},
|
| 126 |
+
{
|
| 127 |
+
"name": "Okapi TruthfulQA",
|
| 128 |
+
"author": "Okapi",
|
| 129 |
+
"url": "https://huggingface.co/datasets/jon-tow/okapi_truthfulqa/tree/main/data",
|
| 130 |
+
"n_languages": 31,
|
| 131 |
+
"tasks": [
|
| 132 |
+
"question_answering"
|
| 133 |
+
],
|
| 134 |
+
"parallel": true,
|
| 135 |
+
"base": "TruthfulQA"
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"name": "Uhura TruthfulQA",
|
| 139 |
+
"author": "Masakhane",
|
| 140 |
+
"url": "https://huggingface.co/datasets/masakhane/uhura-truthfulqa",
|
| 141 |
+
"n_languages": 6,
|
| 142 |
+
"tasks": [
|
| 143 |
+
"question_answering"
|
| 144 |
+
],
|
| 145 |
+
"parallel": true,
|
| 146 |
+
"base": "TruthfulQA"
|
| 147 |
+
},
|
| 148 |
+
{
|
| 149 |
+
"name": "XNLI",
|
| 150 |
+
"author": "Meta",
|
| 151 |
+
"url": "https://huggingface.co/datasets/facebook/xnli",
|
| 152 |
+
"n_languages": 14,
|
| 153 |
+
"tasks": [
|
| 154 |
+
"classification"
|
| 155 |
+
],
|
| 156 |
+
"parallel": true,
|
| 157 |
+
"base": "XNLI"
|
| 158 |
+
},
|
| 159 |
+
{
|
| 160 |
+
"name": "AfriXNLI",
|
| 161 |
+
"author": "Masakhane",
|
| 162 |
+
"url": "https://huggingface.co/datasets/masakhane/afrixnli",
|
| 163 |
+
"n_languages": 18,
|
| 164 |
+
"tasks": [
|
| 165 |
+
"classification"
|
| 166 |
+
],
|
| 167 |
+
"parallel": true,
|
| 168 |
+
"base": "XNLI"
|
| 169 |
+
},
|
| 170 |
+
{
|
| 171 |
+
"name": "Okapi HellaSwag",
|
| 172 |
+
"author": "Okapi",
|
| 173 |
+
"url": "https://huggingface.co/datasets/jon-tow/okapi_hellaswag",
|
| 174 |
+
"n_languages": 31,
|
| 175 |
+
"tasks": [
|
| 176 |
+
"question_answering"
|
| 177 |
+
],
|
| 178 |
+
"parallel": true,
|
| 179 |
+
"base": "HellaSwag"
|
| 180 |
+
},
|
| 181 |
+
{
|
| 182 |
+
"name": "WikiANN / PAN-X",
|
| 183 |
+
"author": "Academic",
|
| 184 |
+
"url": "https://huggingface.co/datasets/unimelb-nlp/wikiann",
|
| 185 |
+
"n_languages": 176,
|
| 186 |
+
"tasks": [
|
| 187 |
+
"ner"
|
| 188 |
+
],
|
| 189 |
+
"parallel": false
|
| 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": "XTREME",
|
| 224 |
+
"author": "Google",
|
| 225 |
+
"url": "https://huggingface.co/datasets/google/xtreme",
|
| 226 |
+
"n_languages": 40,
|
| 227 |
+
"tasks": [
|
| 228 |
+
"translation",
|
| 229 |
+
"classification",
|
| 230 |
+
"question_answering",
|
| 231 |
+
"ner"
|
| 232 |
+
],
|
| 233 |
+
"parallel": null
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"name": "XGLUE",
|
| 237 |
+
"author": "Microsoft",
|
| 238 |
+
"url": "https://huggingface.co/datasets/microsoft/xglue",
|
| 239 |
+
"n_languages": 18,
|
| 240 |
+
"tasks": [
|
| 241 |
+
"pos"
|
| 242 |
+
],
|
| 243 |
+
"parallel": null,
|
| 244 |
+
"base": "GLUE"
|
| 245 |
+
},
|
| 246 |
+
{
|
| 247 |
+
"name": "IndicGLUE",
|
| 248 |
+
"author": "AI4Bharat",
|
| 249 |
+
"url": "https://huggingface.co/datasets/ai4bharat/indic_glue",
|
| 250 |
+
"n_languages": 11,
|
| 251 |
+
"tasks": [
|
| 252 |
+
"question_answering"
|
| 253 |
+
],
|
| 254 |
+
"parallel": null,
|
| 255 |
+
"base": "GLUE"
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"name": "Opus Gnome",
|
| 259 |
+
"author": "Helsinki NLP",
|
| 260 |
+
"url": "https://huggingface.co/datasets/Helsinki-NLP/opus_gnome",
|
| 261 |
+
"n_languages": 187,
|
| 262 |
+
"tasks": [
|
| 263 |
+
"translation"
|
| 264 |
+
],
|
| 265 |
+
"parallel": true
|
| 266 |
+
},
|
| 267 |
+
{
|
| 268 |
+
"name": "Opus Paracrawl",
|
| 269 |
+
"author": "Helsinki NLP",
|
| 270 |
+
"url": "https://huggingface.co/datasets/Helsinki-NLP/opus_paracrawl",
|
| 271 |
+
"n_languages": 43,
|
| 272 |
+
"tasks": [
|
| 273 |
+
"translation"
|
| 274 |
+
],
|
| 275 |
+
"parallel": false
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"name": "CCAligned",
|
| 279 |
+
"author": "Meta",
|
| 280 |
+
"url": "https://huggingface.co/datasets/ahelk/ccaligned_multilingual",
|
| 281 |
+
"n_languages": 137,
|
| 282 |
+
"tasks": [
|
| 283 |
+
"translation"
|
| 284 |
+
],
|
| 285 |
+
"parallel": false
|
| 286 |
+
},
|
| 287 |
+
{
|
| 288 |
+
"name": "OPUS Collection",
|
| 289 |
+
"author": "Helsinki NLP",
|
| 290 |
+
"url": "https://opus.nlpl.eu/",
|
| 291 |
+
"n_languages": 747,
|
| 292 |
+
"tasks": [
|
| 293 |
+
"translation"
|
| 294 |
+
],
|
| 295 |
+
"parallel": false
|
| 296 |
+
},
|
| 297 |
+
{
|
| 298 |
+
"name": "MasakhaNER",
|
| 299 |
+
"author": "Masakhane",
|
| 300 |
+
"url": "https://huggingface.co/datasets/masakhane/masakhaner",
|
| 301 |
+
"n_languages": 10,
|
| 302 |
+
"tasks": [
|
| 303 |
+
"ner"
|
| 304 |
+
],
|
| 305 |
+
"parallel": null
|
| 306 |
+
},
|
| 307 |
+
{
|
| 308 |
+
"name": "Multilingual Sentiments",
|
| 309 |
+
"url": "https://huggingface.co/datasets/tyqiangz/multilingual-sentiments",
|
| 310 |
+
"n_languages": 12,
|
| 311 |
+
"tasks": [
|
| 312 |
+
"sentiment_analysis"
|
| 313 |
+
],
|
| 314 |
+
"parallel": null
|
| 315 |
+
},
|
| 316 |
+
{
|
| 317 |
+
"name": "CulturaX",
|
| 318 |
+
"author": "Academic",
|
| 319 |
+
"url": "https://huggingface.co/datasets/uonlp/CulturaX",
|
| 320 |
+
"n_languages": 167,
|
| 321 |
+
"tasks": [
|
| 322 |
+
"language_modeling"
|
| 323 |
+
],
|
| 324 |
+
"parallel": false
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"name": "T\u00fclu 3 SFT Mixture",
|
| 328 |
+
"author": "AllenAI",
|
| 329 |
+
"url": "https://huggingface.co/datasets/allenai/tulu-3-sft-mixture",
|
| 330 |
+
"n_languages": 70,
|
| 331 |
+
"tasks": [
|
| 332 |
+
"instruction_following"
|
| 333 |
+
],
|
| 334 |
+
"parallel": false
|
| 335 |
+
},
|
| 336 |
+
{
|
| 337 |
+
"name": "xP3",
|
| 338 |
+
"author": "BigScience",
|
| 339 |
+
"url": "https://huggingface.co/datasets/bigscience/xP3",
|
| 340 |
+
"n_languages": 46,
|
| 341 |
+
"tasks": [
|
| 342 |
+
"instruction_following"
|
| 343 |
+
],
|
| 344 |
+
"parallel": false
|
| 345 |
+
},
|
| 346 |
+
{
|
| 347 |
+
"name": "Aya",
|
| 348 |
+
"author": "Cohere",
|
| 349 |
+
"url": "https://huggingface.co/datasets/CohereForAI/aya_dataset",
|
| 350 |
+
"n_languages": 65,
|
| 351 |
+
"tasks": [
|
| 352 |
+
"instruction_following"
|
| 353 |
+
],
|
| 354 |
+
"parallel": null
|
| 355 |
+
},
|
| 356 |
+
{
|
| 357 |
+
"name": "Lanfrica",
|
| 358 |
+
"author": "Lanfrica",
|
| 359 |
+
"url": "https://lanfrica.com/records?language=yor&task=machine%20translation",
|
| 360 |
+
"n_languages": 2200,
|
| 361 |
+
"tasks": [
|
| 362 |
+
"datasets"
|
| 363 |
+
],
|
| 364 |
+
"parallel": null
|
| 365 |
+
},
|
| 366 |
+
{
|
| 367 |
+
"name": "HuggingFace Languages",
|
| 368 |
+
"author": "HuggingFace",
|
| 369 |
+
"url": "https://huggingface.co/languages",
|
| 370 |
+
"n_languages": 4680,
|
| 371 |
+
"tasks": [
|
| 372 |
+
"datasets",
|
| 373 |
+
"models"
|
| 374 |
+
],
|
| 375 |
+
"parallel": null
|
| 376 |
+
},
|
| 377 |
+
{
|
| 378 |
+
"name": "HuggingFace Multilingual Datasets",
|
| 379 |
+
"author": "HuggingFace",
|
| 380 |
+
"url": "https://huggingface.co/datasets?other=multilinguality:multilingual",
|
| 381 |
+
"n_languages": null,
|
| 382 |
+
"tasks": [
|
| 383 |
+
"datasets"
|
| 384 |
+
],
|
| 385 |
+
"parallel": false
|
| 386 |
+
}
|
| 387 |
+
]
|
evals/main.py
CHANGED
|
@@ -108,7 +108,6 @@ def make_language_table(df):
|
|
| 108 |
df = df[["language_name", "speakers", "family", "average", "in_benchmark", *task_metrics]]
|
| 109 |
return df
|
| 110 |
|
| 111 |
-
|
| 112 |
async def main():
|
| 113 |
results = await evaluate()
|
| 114 |
results, lang_results, model_results, task_results = aggregate(results)
|
|
@@ -121,9 +120,11 @@ async def main():
|
|
| 121 |
with open("results.json", "w") as f:
|
| 122 |
json.dump(all_results, f, indent=2, ensure_ascii=False)
|
| 123 |
|
|
|
|
| 124 |
all_tables = {
|
| 125 |
"model_table": serialize(make_model_table(model_results)),
|
| 126 |
"language_table": serialize(make_language_table(lang_results)),
|
|
|
|
| 127 |
}
|
| 128 |
with open("frontend/public/results.json", "w") as f:
|
| 129 |
json.dump(all_tables, f, indent=2, ensure_ascii=False)
|
|
|
|
| 108 |
df = df[["language_name", "speakers", "family", "average", "in_benchmark", *task_metrics]]
|
| 109 |
return df
|
| 110 |
|
|
|
|
| 111 |
async def main():
|
| 112 |
results = await evaluate()
|
| 113 |
results, lang_results, model_results, task_results = aggregate(results)
|
|
|
|
| 120 |
with open("results.json", "w") as f:
|
| 121 |
json.dump(all_results, f, indent=2, ensure_ascii=False)
|
| 122 |
|
| 123 |
+
datasets_df = pd.read_json("data/datasets.json")
|
| 124 |
all_tables = {
|
| 125 |
"model_table": serialize(make_model_table(model_results)),
|
| 126 |
"language_table": serialize(make_language_table(lang_results)),
|
| 127 |
+
"dataset_table": serialize(datasets_df),
|
| 128 |
}
|
| 129 |
with open("frontend/public/results.json", "w") as f:
|
| 130 |
json.dump(all_tables, f, indent=2, ensure_ascii=False)
|
frontend/public/results.json
CHANGED
|
@@ -8318,5 +8318,445 @@
|
|
| 8318 |
"translation_bleu": 0.0,
|
| 8319 |
"translation_chrf": 0.0
|
| 8320 |
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 8321 |
]
|
| 8322 |
}
|
|
|
|
| 8318 |
"translation_bleu": 0.0,
|
| 8319 |
"translation_chrf": 0.0
|
| 8320 |
}
|
| 8321 |
+
],
|
| 8322 |
+
"dataset_table": [
|
| 8323 |
+
{
|
| 8324 |
+
"name": "FLORES+",
|
| 8325 |
+
"author": "Meta",
|
| 8326 |
+
"url": "https://huggingface.co/datasets/openlanguagedata/flores_plus",
|
| 8327 |
+
"n_languages": 200.0,
|
| 8328 |
+
"tasks": [
|
| 8329 |
+
"translation",
|
| 8330 |
+
"classification",
|
| 8331 |
+
"language_modeling"
|
| 8332 |
+
],
|
| 8333 |
+
"parallel": 1.0,
|
| 8334 |
+
"base": "FLORES",
|
| 8335 |
+
"implemented": 1.0
|
| 8336 |
+
},
|
| 8337 |
+
{
|
| 8338 |
+
"name": "FLEURS",
|
| 8339 |
+
"author": "Meta",
|
| 8340 |
+
"url": "https://huggingface.co/datasets/google/fleurs",
|
| 8341 |
+
"n_languages": 102.0,
|
| 8342 |
+
"tasks": [
|
| 8343 |
+
"speech_recognition"
|
| 8344 |
+
],
|
| 8345 |
+
"parallel": 1.0,
|
| 8346 |
+
"base": "FLORES",
|
| 8347 |
+
"implemented": 1.0
|
| 8348 |
+
},
|
| 8349 |
+
{
|
| 8350 |
+
"name": "CommonVoice",
|
| 8351 |
+
"author": "Mozilla",
|
| 8352 |
+
"url": "https://huggingface.co/datasets/mozilla-foundation/common_voice_17_0",
|
| 8353 |
+
"n_languages": 124.0,
|
| 8354 |
+
"tasks": [
|
| 8355 |
+
"speech_recognition"
|
| 8356 |
+
],
|
| 8357 |
+
"parallel": null,
|
| 8358 |
+
"base": null,
|
| 8359 |
+
"implemented": null
|
| 8360 |
+
},
|
| 8361 |
+
{
|
| 8362 |
+
"name": "MMMLU",
|
| 8363 |
+
"author": "OpenAI",
|
| 8364 |
+
"url": "https://huggingface.co/datasets/openai/MMMLU",
|
| 8365 |
+
"n_languages": 14.0,
|
| 8366 |
+
"tasks": [
|
| 8367 |
+
"question_answering"
|
| 8368 |
+
],
|
| 8369 |
+
"parallel": 1.0,
|
| 8370 |
+
"base": "MMLU",
|
| 8371 |
+
"implemented": null
|
| 8372 |
+
},
|
| 8373 |
+
{
|
| 8374 |
+
"name": "AfriMMLU",
|
| 8375 |
+
"author": "Masakhane",
|
| 8376 |
+
"url": "https://huggingface.co/datasets/masakhane/afrimmlu",
|
| 8377 |
+
"n_languages": 17.0,
|
| 8378 |
+
"tasks": [
|
| 8379 |
+
"question_answering"
|
| 8380 |
+
],
|
| 8381 |
+
"parallel": 1.0,
|
| 8382 |
+
"base": "MMLU",
|
| 8383 |
+
"implemented": null
|
| 8384 |
+
},
|
| 8385 |
+
{
|
| 8386 |
+
"name": "Okapi MMLU",
|
| 8387 |
+
"author": "Okapi",
|
| 8388 |
+
"url": "https://huggingface.co/datasets/jon-tow/okapi_mmlu",
|
| 8389 |
+
"n_languages": 16.0,
|
| 8390 |
+
"tasks": [
|
| 8391 |
+
"question_answering"
|
| 8392 |
+
],
|
| 8393 |
+
"parallel": 1.0,
|
| 8394 |
+
"base": "MMLU",
|
| 8395 |
+
"implemented": null
|
| 8396 |
+
},
|
| 8397 |
+
{
|
| 8398 |
+
"name": "Global MMLU",
|
| 8399 |
+
"author": "Cohere",
|
| 8400 |
+
"url": "https://huggingface.co/datasets/CohereForAI/Global-MMLU",
|
| 8401 |
+
"n_languages": 42.0,
|
| 8402 |
+
"tasks": [
|
| 8403 |
+
"question_answering"
|
| 8404 |
+
],
|
| 8405 |
+
"parallel": 1.0,
|
| 8406 |
+
"base": "MMLU",
|
| 8407 |
+
"implemented": null
|
| 8408 |
+
},
|
| 8409 |
+
{
|
| 8410 |
+
"name": "MGSM",
|
| 8411 |
+
"author": "Google",
|
| 8412 |
+
"url": "https://huggingface.co/datasets/juletxara/mgsm",
|
| 8413 |
+
"n_languages": 10.0,
|
| 8414 |
+
"tasks": [
|
| 8415 |
+
"math"
|
| 8416 |
+
],
|
| 8417 |
+
"parallel": 1.0,
|
| 8418 |
+
"base": "MGSM",
|
| 8419 |
+
"implemented": null
|
| 8420 |
+
},
|
| 8421 |
+
{
|
| 8422 |
+
"name": "AfriMGSM",
|
| 8423 |
+
"author": "Masakhane",
|
| 8424 |
+
"url": "https://huggingface.co/datasets/masakhane/afrimgsm",
|
| 8425 |
+
"n_languages": 18.0,
|
| 8426 |
+
"tasks": [
|
| 8427 |
+
"math"
|
| 8428 |
+
],
|
| 8429 |
+
"parallel": 1.0,
|
| 8430 |
+
"base": "MGSM",
|
| 8431 |
+
"implemented": null
|
| 8432 |
+
},
|
| 8433 |
+
{
|
| 8434 |
+
"name": "Okapi ARC Challenge",
|
| 8435 |
+
"author": "Okapi",
|
| 8436 |
+
"url": "https://huggingface.co/datasets/jon-tow/okapi_arc_challenge",
|
| 8437 |
+
"n_languages": 31.0,
|
| 8438 |
+
"tasks": [
|
| 8439 |
+
"question_answering"
|
| 8440 |
+
],
|
| 8441 |
+
"parallel": 1.0,
|
| 8442 |
+
"base": "AI2 ARC",
|
| 8443 |
+
"implemented": null
|
| 8444 |
+
},
|
| 8445 |
+
{
|
| 8446 |
+
"name": "Uhuru ARC Easy",
|
| 8447 |
+
"author": "Masakhane",
|
| 8448 |
+
"url": "https://huggingface.co/datasets/masakhane/uhura-arc-easy",
|
| 8449 |
+
"n_languages": 6.0,
|
| 8450 |
+
"tasks": [
|
| 8451 |
+
"question_answering"
|
| 8452 |
+
],
|
| 8453 |
+
"parallel": 1.0,
|
| 8454 |
+
"base": "AI2 ARC",
|
| 8455 |
+
"implemented": null
|
| 8456 |
+
},
|
| 8457 |
+
{
|
| 8458 |
+
"name": "Okapi TruthfulQA",
|
| 8459 |
+
"author": "Okapi",
|
| 8460 |
+
"url": "https://huggingface.co/datasets/jon-tow/okapi_truthfulqa/tree/main/data",
|
| 8461 |
+
"n_languages": 31.0,
|
| 8462 |
+
"tasks": [
|
| 8463 |
+
"question_answering"
|
| 8464 |
+
],
|
| 8465 |
+
"parallel": 1.0,
|
| 8466 |
+
"base": "TruthfulQA",
|
| 8467 |
+
"implemented": null
|
| 8468 |
+
},
|
| 8469 |
+
{
|
| 8470 |
+
"name": "Uhura TruthfulQA",
|
| 8471 |
+
"author": "Masakhane",
|
| 8472 |
+
"url": "https://huggingface.co/datasets/masakhane/uhura-truthfulqa",
|
| 8473 |
+
"n_languages": 6.0,
|
| 8474 |
+
"tasks": [
|
| 8475 |
+
"question_answering"
|
| 8476 |
+
],
|
| 8477 |
+
"parallel": 1.0,
|
| 8478 |
+
"base": "TruthfulQA",
|
| 8479 |
+
"implemented": null
|
| 8480 |
+
},
|
| 8481 |
+
{
|
| 8482 |
+
"name": "XNLI",
|
| 8483 |
+
"author": "Meta",
|
| 8484 |
+
"url": "https://huggingface.co/datasets/facebook/xnli",
|
| 8485 |
+
"n_languages": 14.0,
|
| 8486 |
+
"tasks": [
|
| 8487 |
+
"classification"
|
| 8488 |
+
],
|
| 8489 |
+
"parallel": 1.0,
|
| 8490 |
+
"base": "XNLI",
|
| 8491 |
+
"implemented": null
|
| 8492 |
+
},
|
| 8493 |
+
{
|
| 8494 |
+
"name": "AfriXNLI",
|
| 8495 |
+
"author": "Masakhane",
|
| 8496 |
+
"url": "https://huggingface.co/datasets/masakhane/afrixnli",
|
| 8497 |
+
"n_languages": 18.0,
|
| 8498 |
+
"tasks": [
|
| 8499 |
+
"classification"
|
| 8500 |
+
],
|
| 8501 |
+
"parallel": 1.0,
|
| 8502 |
+
"base": "XNLI",
|
| 8503 |
+
"implemented": null
|
| 8504 |
+
},
|
| 8505 |
+
{
|
| 8506 |
+
"name": "Okapi HellaSwag",
|
| 8507 |
+
"author": "Okapi",
|
| 8508 |
+
"url": "https://huggingface.co/datasets/jon-tow/okapi_hellaswag",
|
| 8509 |
+
"n_languages": 31.0,
|
| 8510 |
+
"tasks": [
|
| 8511 |
+
"question_answering"
|
| 8512 |
+
],
|
| 8513 |
+
"parallel": 1.0,
|
| 8514 |
+
"base": "HellaSwag",
|
| 8515 |
+
"implemented": null
|
| 8516 |
+
},
|
| 8517 |
+
{
|
| 8518 |
+
"name": "WikiANN / PAN-X",
|
| 8519 |
+
"author": "Academic",
|
| 8520 |
+
"url": "https://huggingface.co/datasets/unimelb-nlp/wikiann",
|
| 8521 |
+
"n_languages": 176.0,
|
| 8522 |
+
"tasks": [
|
| 8523 |
+
"ner"
|
| 8524 |
+
],
|
| 8525 |
+
"parallel": 0.0,
|
| 8526 |
+
"base": null,
|
| 8527 |
+
"implemented": null
|
| 8528 |
+
},
|
| 8529 |
+
{
|
| 8530 |
+
"name": "MSVAMP",
|
| 8531 |
+
"author": "Microsoft",
|
| 8532 |
+
"url": "https://huggingface.co/datasets/Mathoctopus/MSVAMP",
|
| 8533 |
+
"n_languages": 10.0,
|
| 8534 |
+
"tasks": [
|
| 8535 |
+
"math"
|
| 8536 |
+
],
|
| 8537 |
+
"parallel": 1.0,
|
| 8538 |
+
"base": null,
|
| 8539 |
+
"implemented": null
|
| 8540 |
+
},
|
| 8541 |
+
{
|
| 8542 |
+
"name": "XLSUM",
|
| 8543 |
+
"author": "Academic",
|
| 8544 |
+
"url": "https://huggingface.co/datasets/csebuetnlp/xlsum",
|
| 8545 |
+
"n_languages": 45.0,
|
| 8546 |
+
"tasks": [
|
| 8547 |
+
"summarization"
|
| 8548 |
+
],
|
| 8549 |
+
"parallel": 1.0,
|
| 8550 |
+
"base": null,
|
| 8551 |
+
"implemented": null
|
| 8552 |
+
},
|
| 8553 |
+
{
|
| 8554 |
+
"name": "SEA-IFEVAL",
|
| 8555 |
+
"author": "AI Singapore",
|
| 8556 |
+
"url": "https://huggingface.co/datasets/aisingapore/instruction_following-ifeval",
|
| 8557 |
+
"n_languages": 7.0,
|
| 8558 |
+
"tasks": [
|
| 8559 |
+
"instruction_following"
|
| 8560 |
+
],
|
| 8561 |
+
"parallel": 1.0,
|
| 8562 |
+
"base": "IFEVAL",
|
| 8563 |
+
"implemented": null
|
| 8564 |
+
},
|
| 8565 |
+
{
|
| 8566 |
+
"name": "XTREME",
|
| 8567 |
+
"author": "Google",
|
| 8568 |
+
"url": "https://huggingface.co/datasets/google/xtreme",
|
| 8569 |
+
"n_languages": 40.0,
|
| 8570 |
+
"tasks": [
|
| 8571 |
+
"translation",
|
| 8572 |
+
"classification",
|
| 8573 |
+
"question_answering",
|
| 8574 |
+
"ner"
|
| 8575 |
+
],
|
| 8576 |
+
"parallel": null,
|
| 8577 |
+
"base": null,
|
| 8578 |
+
"implemented": null
|
| 8579 |
+
},
|
| 8580 |
+
{
|
| 8581 |
+
"name": "XGLUE",
|
| 8582 |
+
"author": "Microsoft",
|
| 8583 |
+
"url": "https://huggingface.co/datasets/microsoft/xglue",
|
| 8584 |
+
"n_languages": 18.0,
|
| 8585 |
+
"tasks": [
|
| 8586 |
+
"pos"
|
| 8587 |
+
],
|
| 8588 |
+
"parallel": null,
|
| 8589 |
+
"base": "GLUE",
|
| 8590 |
+
"implemented": null
|
| 8591 |
+
},
|
| 8592 |
+
{
|
| 8593 |
+
"name": "IndicGLUE",
|
| 8594 |
+
"author": "AI4Bharat",
|
| 8595 |
+
"url": "https://huggingface.co/datasets/ai4bharat/indic_glue",
|
| 8596 |
+
"n_languages": 11.0,
|
| 8597 |
+
"tasks": [
|
| 8598 |
+
"question_answering"
|
| 8599 |
+
],
|
| 8600 |
+
"parallel": null,
|
| 8601 |
+
"base": "GLUE",
|
| 8602 |
+
"implemented": null
|
| 8603 |
+
},
|
| 8604 |
+
{
|
| 8605 |
+
"name": "Opus Gnome",
|
| 8606 |
+
"author": "Helsinki NLP",
|
| 8607 |
+
"url": "https://huggingface.co/datasets/Helsinki-NLP/opus_gnome",
|
| 8608 |
+
"n_languages": 187.0,
|
| 8609 |
+
"tasks": [
|
| 8610 |
+
"translation"
|
| 8611 |
+
],
|
| 8612 |
+
"parallel": 1.0,
|
| 8613 |
+
"base": null,
|
| 8614 |
+
"implemented": null
|
| 8615 |
+
},
|
| 8616 |
+
{
|
| 8617 |
+
"name": "Opus Paracrawl",
|
| 8618 |
+
"author": "Helsinki NLP",
|
| 8619 |
+
"url": "https://huggingface.co/datasets/Helsinki-NLP/opus_paracrawl",
|
| 8620 |
+
"n_languages": 43.0,
|
| 8621 |
+
"tasks": [
|
| 8622 |
+
"translation"
|
| 8623 |
+
],
|
| 8624 |
+
"parallel": 0.0,
|
| 8625 |
+
"base": null,
|
| 8626 |
+
"implemented": null
|
| 8627 |
+
},
|
| 8628 |
+
{
|
| 8629 |
+
"name": "CCAligned",
|
| 8630 |
+
"author": "Meta",
|
| 8631 |
+
"url": "https://huggingface.co/datasets/ahelk/ccaligned_multilingual",
|
| 8632 |
+
"n_languages": 137.0,
|
| 8633 |
+
"tasks": [
|
| 8634 |
+
"translation"
|
| 8635 |
+
],
|
| 8636 |
+
"parallel": 0.0,
|
| 8637 |
+
"base": null,
|
| 8638 |
+
"implemented": null
|
| 8639 |
+
},
|
| 8640 |
+
{
|
| 8641 |
+
"name": "OPUS Collection",
|
| 8642 |
+
"author": "Helsinki NLP",
|
| 8643 |
+
"url": "https://opus.nlpl.eu/",
|
| 8644 |
+
"n_languages": 747.0,
|
| 8645 |
+
"tasks": [
|
| 8646 |
+
"translation"
|
| 8647 |
+
],
|
| 8648 |
+
"parallel": 0.0,
|
| 8649 |
+
"base": null,
|
| 8650 |
+
"implemented": null
|
| 8651 |
+
},
|
| 8652 |
+
{
|
| 8653 |
+
"name": "MasakhaNER",
|
| 8654 |
+
"author": "Masakhane",
|
| 8655 |
+
"url": "https://huggingface.co/datasets/masakhane/masakhaner",
|
| 8656 |
+
"n_languages": 10.0,
|
| 8657 |
+
"tasks": [
|
| 8658 |
+
"ner"
|
| 8659 |
+
],
|
| 8660 |
+
"parallel": null,
|
| 8661 |
+
"base": null,
|
| 8662 |
+
"implemented": null
|
| 8663 |
+
},
|
| 8664 |
+
{
|
| 8665 |
+
"name": "Multilingual Sentiments",
|
| 8666 |
+
"author": null,
|
| 8667 |
+
"url": "https://huggingface.co/datasets/tyqiangz/multilingual-sentiments",
|
| 8668 |
+
"n_languages": 12.0,
|
| 8669 |
+
"tasks": [
|
| 8670 |
+
"sentiment_analysis"
|
| 8671 |
+
],
|
| 8672 |
+
"parallel": null,
|
| 8673 |
+
"base": null,
|
| 8674 |
+
"implemented": null
|
| 8675 |
+
},
|
| 8676 |
+
{
|
| 8677 |
+
"name": "CulturaX",
|
| 8678 |
+
"author": "Academic",
|
| 8679 |
+
"url": "https://huggingface.co/datasets/uonlp/CulturaX",
|
| 8680 |
+
"n_languages": 167.0,
|
| 8681 |
+
"tasks": [
|
| 8682 |
+
"language_modeling"
|
| 8683 |
+
],
|
| 8684 |
+
"parallel": 0.0,
|
| 8685 |
+
"base": null,
|
| 8686 |
+
"implemented": null
|
| 8687 |
+
},
|
| 8688 |
+
{
|
| 8689 |
+
"name": "Tülu 3 SFT Mixture",
|
| 8690 |
+
"author": "AllenAI",
|
| 8691 |
+
"url": "https://huggingface.co/datasets/allenai/tulu-3-sft-mixture",
|
| 8692 |
+
"n_languages": 70.0,
|
| 8693 |
+
"tasks": [
|
| 8694 |
+
"instruction_following"
|
| 8695 |
+
],
|
| 8696 |
+
"parallel": 0.0,
|
| 8697 |
+
"base": null,
|
| 8698 |
+
"implemented": null
|
| 8699 |
+
},
|
| 8700 |
+
{
|
| 8701 |
+
"name": "xP3",
|
| 8702 |
+
"author": "BigScience",
|
| 8703 |
+
"url": "https://huggingface.co/datasets/bigscience/xP3",
|
| 8704 |
+
"n_languages": 46.0,
|
| 8705 |
+
"tasks": [
|
| 8706 |
+
"instruction_following"
|
| 8707 |
+
],
|
| 8708 |
+
"parallel": 0.0,
|
| 8709 |
+
"base": null,
|
| 8710 |
+
"implemented": null
|
| 8711 |
+
},
|
| 8712 |
+
{
|
| 8713 |
+
"name": "Aya",
|
| 8714 |
+
"author": "Cohere",
|
| 8715 |
+
"url": "https://huggingface.co/datasets/CohereForAI/aya_dataset",
|
| 8716 |
+
"n_languages": 65.0,
|
| 8717 |
+
"tasks": [
|
| 8718 |
+
"instruction_following"
|
| 8719 |
+
],
|
| 8720 |
+
"parallel": null,
|
| 8721 |
+
"base": null,
|
| 8722 |
+
"implemented": null
|
| 8723 |
+
},
|
| 8724 |
+
{
|
| 8725 |
+
"name": "Lanfrica",
|
| 8726 |
+
"author": "Lanfrica",
|
| 8727 |
+
"url": "https://lanfrica.com/records?language=yor&task=machine%20translation",
|
| 8728 |
+
"n_languages": 2200.0,
|
| 8729 |
+
"tasks": [
|
| 8730 |
+
"datasets"
|
| 8731 |
+
],
|
| 8732 |
+
"parallel": null,
|
| 8733 |
+
"base": null,
|
| 8734 |
+
"implemented": null
|
| 8735 |
+
},
|
| 8736 |
+
{
|
| 8737 |
+
"name": "HuggingFace Languages",
|
| 8738 |
+
"author": "HuggingFace",
|
| 8739 |
+
"url": "https://huggingface.co/languages",
|
| 8740 |
+
"n_languages": 4680.0,
|
| 8741 |
+
"tasks": [
|
| 8742 |
+
"datasets",
|
| 8743 |
+
"models"
|
| 8744 |
+
],
|
| 8745 |
+
"parallel": null,
|
| 8746 |
+
"base": null,
|
| 8747 |
+
"implemented": null
|
| 8748 |
+
},
|
| 8749 |
+
{
|
| 8750 |
+
"name": "HuggingFace Multilingual Datasets",
|
| 8751 |
+
"author": "HuggingFace",
|
| 8752 |
+
"url": "https://huggingface.co/datasets?other=multilinguality:multilingual",
|
| 8753 |
+
"n_languages": null,
|
| 8754 |
+
"tasks": [
|
| 8755 |
+
"datasets"
|
| 8756 |
+
],
|
| 8757 |
+
"parallel": 0.0,
|
| 8758 |
+
"base": null,
|
| 8759 |
+
"implemented": null
|
| 8760 |
+
}
|
| 8761 |
]
|
| 8762 |
}
|
frontend/src/App.css
CHANGED
|
@@ -37,3 +37,7 @@ p {
|
|
| 37 |
color: #555;
|
| 38 |
margin-top: 0;
|
| 39 |
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 37 |
color: #555;
|
| 38 |
margin-top: 0;
|
| 39 |
}
|
| 40 |
+
|
| 41 |
+
* {
|
| 42 |
+
font-size: 10pt;
|
| 43 |
+
}
|
frontend/src/App.js
CHANGED
|
@@ -4,7 +4,7 @@ import { PrimeReactProvider } from 'primereact/api'
|
|
| 4 |
import 'primereact/resources/themes/lara-light-cyan/theme.css'
|
| 5 |
import ModelTable from './components/ModelTable'
|
| 6 |
import LanguageTable from './components/LanguageTable'
|
| 7 |
-
|
| 8 |
function App () {
|
| 9 |
const [data, setData] = useState(null)
|
| 10 |
const [loading, setLoading] = useState(true)
|
|
@@ -48,9 +48,12 @@ function App () {
|
|
| 48 |
{loading && <p>...</p>}
|
| 49 |
{error && <p>Error: {error}</p>}
|
| 50 |
{data && (
|
| 51 |
-
<div style={{ display: 'flex', flexDirection: '
|
| 52 |
-
<
|
| 53 |
-
|
|
|
|
|
|
|
|
|
|
| 54 |
</div>
|
| 55 |
)}
|
| 56 |
</PrimeReactProvider>
|
|
|
|
| 4 |
import 'primereact/resources/themes/lara-light-cyan/theme.css'
|
| 5 |
import ModelTable from './components/ModelTable'
|
| 6 |
import LanguageTable from './components/LanguageTable'
|
| 7 |
+
import DatasetTable from './components/DatasetTable'
|
| 8 |
function App () {
|
| 9 |
const [data, setData] = useState(null)
|
| 10 |
const [loading, setLoading] = useState(true)
|
|
|
|
| 48 |
{loading && <p>...</p>}
|
| 49 |
{error && <p>Error: {error}</p>}
|
| 50 |
{data && (
|
| 51 |
+
<div style={{ display: 'flex', flexDirection: 'column', gap: '2rem', alignItems: 'center', width: '100%' }}>
|
| 52 |
+
<div style={{ display: 'flex', flexDirection: 'row', gap: '2rem' }}>
|
| 53 |
+
<ModelTable data={data} />
|
| 54 |
+
<LanguageTable data={data} />
|
| 55 |
+
</div>
|
| 56 |
+
<DatasetTable data={data} />
|
| 57 |
</div>
|
| 58 |
)}
|
| 59 |
</PrimeReactProvider>
|
frontend/src/components/DatasetTable.js
ADDED
|
@@ -0,0 +1,72 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
import { DataTable } from 'primereact/datatable'
|
| 2 |
+
import { Column } from 'primereact/column'
|
| 3 |
+
import { FilterMatchMode } from 'primereact/api'
|
| 4 |
+
import { useState } from 'react'
|
| 5 |
+
|
| 6 |
+
const DatasetTable = ({ data }) => {
|
| 7 |
+
const [filters, setFilters] = useState({
|
| 8 |
+
name: { value: null, matchMode: FilterMatchMode.CONTAINS },
|
| 9 |
+
author: { value: null, matchMode: FilterMatchMode.IN },
|
| 10 |
+
n_languages: { value: null, matchMode: FilterMatchMode.BETWEEN },
|
| 11 |
+
tasks: { value: null, matchMode: FilterMatchMode.IN },
|
| 12 |
+
parallel: { value: null, matchMode: FilterMatchMode.EQUALS },
|
| 13 |
+
base: { value: null, matchMode: FilterMatchMode.IN },
|
| 14 |
+
implemented: { value: null, matchMode: FilterMatchMode.EQUALS },
|
| 15 |
+
})
|
| 16 |
+
const table = data.dataset_table
|
| 17 |
+
|
| 18 |
+
const nameBodyTemplate = rowData => {
|
| 19 |
+
return <div style={{ fontWeight: 'bold' }}>{rowData.name}</div>
|
| 20 |
+
}
|
| 21 |
+
|
| 22 |
+
|
| 23 |
+
return (
|
| 24 |
+
<DataTable
|
| 25 |
+
value={table}
|
| 26 |
+
header={<>Datasets</>}
|
| 27 |
+
removableSort
|
| 28 |
+
filters={filters}
|
| 29 |
+
filterDisplay='menu'
|
| 30 |
+
scrollable
|
| 31 |
+
scrollHeight='500px'
|
| 32 |
+
style={{ minWidth: '200px', width: "50%" }}
|
| 33 |
+
>
|
| 34 |
+
{/* <Column
|
| 35 |
+
field='implemented'
|
| 36 |
+
header='Implemented'
|
| 37 |
+
filter
|
| 38 |
+
style={{ minWidth: '5rem' }}
|
| 39 |
+
/> */}
|
| 40 |
+
<Column
|
| 41 |
+
field='author'
|
| 42 |
+
header='Author'
|
| 43 |
+
filter
|
| 44 |
+
showFilterMatchModes={false}
|
| 45 |
+
style={{ minWidth: '5rem' }}
|
| 46 |
+
/>
|
| 47 |
+
<Column
|
| 48 |
+
field='name'
|
| 49 |
+
header='Name'
|
| 50 |
+
body={nameBodyTemplate}
|
| 51 |
+
filter
|
| 52 |
+
style={{ minWidth: '5rem' }}
|
| 53 |
+
frozen
|
| 54 |
+
/>
|
| 55 |
+
<Column
|
| 56 |
+
field='tasks'
|
| 57 |
+
header='Tasks'
|
| 58 |
+
filter
|
| 59 |
+
style={{ minWidth: '5rem', maxWidth: '10rem' }}
|
| 60 |
+
/>
|
| 61 |
+
<Column
|
| 62 |
+
field='n_languages'
|
| 63 |
+
header='#Languages'
|
| 64 |
+
filter
|
| 65 |
+
sortable
|
| 66 |
+
style={{ minWidth: '10rem' }}
|
| 67 |
+
/>
|
| 68 |
+
</DataTable>
|
| 69 |
+
)
|
| 70 |
+
}
|
| 71 |
+
|
| 72 |
+
export default DatasetTable
|
frontend/src/components/LanguageTable.js
CHANGED
|
@@ -157,7 +157,7 @@ const LanguageTable = ({ data }) => {
|
|
| 157 |
field='average'
|
| 158 |
header='Average'
|
| 159 |
sortable
|
| 160 |
-
body={scoreBodyTemplate('average', { minScore: 0.
|
| 161 |
style={{ minWidth: '5rem', maxWidth: '10rem' }}
|
| 162 |
/>
|
| 163 |
<Column
|
|
@@ -165,8 +165,8 @@ const LanguageTable = ({ data }) => {
|
|
| 165 |
header='Translation'
|
| 166 |
sortable
|
| 167 |
body={scoreBodyTemplate('translation_chrf', {
|
| 168 |
-
minScore: 0.
|
| 169 |
-
maxScore: 0.
|
| 170 |
})}
|
| 171 |
style={{ minWidth: '5rem', maxWidth: '10rem' }}
|
| 172 |
/>
|
|
@@ -175,8 +175,8 @@ const LanguageTable = ({ data }) => {
|
|
| 175 |
header='Classification'
|
| 176 |
sortable
|
| 177 |
body={scoreBodyTemplate('classification_accuracy', {
|
| 178 |
-
minScore: 0.
|
| 179 |
-
maxScore:
|
| 180 |
})}
|
| 181 |
style={{ minWidth: '5rem', maxWidth: '10rem' }}
|
| 182 |
/>
|
|
|
|
| 157 |
field='average'
|
| 158 |
header='Average'
|
| 159 |
sortable
|
| 160 |
+
body={scoreBodyTemplate('average', { minScore: 0.2, maxScore: 0.5 })}
|
| 161 |
style={{ minWidth: '5rem', maxWidth: '10rem' }}
|
| 162 |
/>
|
| 163 |
<Column
|
|
|
|
| 165 |
header='Translation'
|
| 166 |
sortable
|
| 167 |
body={scoreBodyTemplate('translation_chrf', {
|
| 168 |
+
minScore: 0.3,
|
| 169 |
+
maxScore: 0.6
|
| 170 |
})}
|
| 171 |
style={{ minWidth: '5rem', maxWidth: '10rem' }}
|
| 172 |
/>
|
|
|
|
| 175 |
header='Classification'
|
| 176 |
sortable
|
| 177 |
body={scoreBodyTemplate('classification_accuracy', {
|
| 178 |
+
minScore: 0.3,
|
| 179 |
+
maxScore: 0.7
|
| 180 |
})}
|
| 181 |
style={{ minWidth: '5rem', maxWidth: '10rem' }}
|
| 182 |
/>
|