idolezal commited on
Commit
01c6f6b
Β·
1 Parent(s): 387e6ad

Removed contaminated tasks from "tasks_metadata.json"

Browse files
Files changed (1) hide show
  1. tasks_metadata.json +0 -32
tasks_metadata.json CHANGED
@@ -127,14 +127,6 @@
127
  "abbreviation": "S-CSFD",
128
  "metric": "avg_mcauroc"
129
  },
130
- "benczechmark_summarization": {
131
- "name": "SUMECZECH",
132
- "source_url": "https://huggingface.co/datasets/CZLC/sumeczech_downsampled",
133
- "short_name": "Summarization",
134
- "category": "Summarization",
135
- "abbreviation": "SUM",
136
- "metric": "rouge_raw_r2_mid_f"
137
- },
138
  "benczechmark_grammarerrorcorrection": {
139
  "name": "GrammarErrorCorrection",
140
  "source_url": "https://huggingface.co/datasets/CZLC/cs_gec",
@@ -343,14 +335,6 @@
343
  "short_name": "Belebele",
344
  "metric": "acc"
345
  },
346
- "benczechmark_czechnews": {
347
- "name": "CZ-NEWS",
348
- "source_url": "https://huggingface.co/datasets/davidadamczyk/czechbench_czech_news",
349
- "abbreviation": "CZ-NEWS",
350
- "category": "Topic Classification",
351
- "short_name": "Czech News",
352
- "metric": "avg_mcauroc"
353
- },
354
  "benczechmark_subjectivity": {
355
  "name": "Subjectivity",
356
  "source_url": "https://huggingface.co/datasets/davidadamczyk/czechbench_subjectivity",
@@ -375,14 +359,6 @@
375
  "short_name": "CNC – Fiction",
376
  "metric": "word_perplexity"
377
  },
378
- "benczechmark_capek": {
379
- "name": "Czech National Corpus – Karel Čapek",
380
- "source_url": "https://huggingface.co/datasets/CZLC/CNC_Capek",
381
- "abbreviation": "CNC-CAP",
382
- "category": "Language Modeling",
383
- "short_name": "CNC – Čapek",
384
- "metric": "word_perplexity"
385
- },
386
  "benczechmark_correspondence": {
387
  "name": "Czech National Corpus – Correspondence",
388
  "source_url": "https://huggingface.co/datasets/CZLC/CNC_KSK",
@@ -399,14 +375,6 @@
399
  "short_name": "CNC – KHavlicek – HistNews",
400
  "metric": "word_perplexity"
401
  },
402
- "benczechmark_speeches": {
403
- "name": "Czech National Corpus – Speeches",
404
- "source_url": "https://huggingface.co/datasets/CZLC/CNC_PrezPrejavy",
405
- "abbreviation": "CNC-SPCH",
406
- "category": "Language Modeling",
407
- "short_name": "CNC – Speeches",
408
- "metric": "word_perplexity"
409
- },
410
  "benczechmark_spoken": {
411
  "name": "Czech National Corpus – Spoken",
412
  "source_url": "https://huggingface.co/datasets/CZLC/CNC_oral_ortofon",
 
127
  "abbreviation": "S-CSFD",
128
  "metric": "avg_mcauroc"
129
  },
 
 
 
 
 
 
 
 
130
  "benczechmark_grammarerrorcorrection": {
131
  "name": "GrammarErrorCorrection",
132
  "source_url": "https://huggingface.co/datasets/CZLC/cs_gec",
 
335
  "short_name": "Belebele",
336
  "metric": "acc"
337
  },
 
 
 
 
 
 
 
 
338
  "benczechmark_subjectivity": {
339
  "name": "Subjectivity",
340
  "source_url": "https://huggingface.co/datasets/davidadamczyk/czechbench_subjectivity",
 
359
  "short_name": "CNC – Fiction",
360
  "metric": "word_perplexity"
361
  },
 
 
 
 
 
 
 
 
362
  "benczechmark_correspondence": {
363
  "name": "Czech National Corpus – Correspondence",
364
  "source_url": "https://huggingface.co/datasets/CZLC/CNC_KSK",
 
375
  "short_name": "CNC – KHavlicek – HistNews",
376
  "metric": "word_perplexity"
377
  },
 
 
 
 
 
 
 
 
378
  "benczechmark_spoken": {
379
  "name": "Czech National Corpus – Spoken",
380
  "source_url": "https://huggingface.co/datasets/CZLC/CNC_oral_ortofon",