Text2Text Generation
Transformers
PyTorch
Safetensors
mt5
Eval Results
Inference Endpoints
Files changed (1) hide show
  1. README.md +52 -38
README.md CHANGED
@@ -69,7 +69,7 @@ language:
69
  - my
70
  - ne
71
  - nl
72
- - no
73
  - ny
74
  - pa
75
  - pl
@@ -108,28 +108,41 @@ language:
108
  tags:
109
  - text2text-generation
110
  widget:
111
- - text: "Life is beautiful! Translate to Mongolian."
112
- example_title: "mn-en translation"
113
- - text: "Le mot japonais «憂鬱» veut dire quoi en Odia?"
114
- example_title: "jp-or-fr translation"
115
- - text: "Stell mir eine schwierige Quiz Frage bei der es um Astronomie geht. Bitte stell die Frage auf Norwegisch."
116
- example_title: "de-nb quiz"
117
- - text: "一个传奇的开端,一个不灭的神话,这不仅仅是一部电影,而是作为一个走进新时代的标签,永远彪炳史册。Would you rate the previous review as positive, neutral or negative?"
118
- example_title: "zh-en sentiment"
119
- - text: "一个传奇的开端,一个不灭的神话,这不仅仅是一部电影,而是作为一个走进新时代的标签,永远彪炳史册。你认为这句话的立场是赞扬、中立还是批评?"
120
- example_title: "zh-zh sentiment"
121
- - text: "Suggest at least five related search terms to \"Mạng neural nhân tạo\"."
122
- example_title: "vi-en query"
123
- - text: "Proposez au moins cinq mots clés concernant «Réseau de neurones artificiels»."
124
- example_title: "fr-fr query"
125
- - text: "Explain in a sentence in Telugu what is backpropagation in neural networks."
126
- example_title: "te-en qa"
127
- - text: "Why is the sky blue?"
128
- example_title: "en-en qa"
129
- - text: "Write a fairy tale about a troll saving a princess from a dangerous dragon. The fairy tale is a masterpiece that has achieved praise worldwide and its moral is \"Heroes Come in All Shapes and Sizes\". Story (in Spanish):"
130
- example_title: "es-en fable"
131
- - text: "Write a fable about wood elves living in a forest that is suddenly invaded by ogres. The fable is a masterpiece that has achieved praise worldwide and its moral is \"Violence is the last refuge of the incompetent\". Fable (in Hindi):"
132
- example_title: "hi-en fable"
 
 
 
 
 
 
 
 
 
 
 
 
 
133
  model-index:
134
  - name: mt0-xxl-mt
135
  results:
@@ -231,7 +244,7 @@ model-index:
231
  revision: 9dbd830a06fea8b1c49d6e5ef2004a08d9f45094
232
  metrics:
233
  - type: Accuracy
234
- value: 42.0
235
  - task:
236
  type: Natural language inference
237
  dataset:
@@ -435,7 +448,7 @@ model-index:
435
  dataset:
436
  type: story_cloze
437
  name: StoryCloze (2016)
438
- config: "2016"
439
  split: validation
440
  revision: e724c6f8cdf7c7a2fb229d862226e15b023ee4db
441
  metrics:
@@ -451,7 +464,7 @@ model-index:
451
  revision: 9e12063561e7e6c79099feb6d5a493142584e9e2
452
  metrics:
453
  - type: Accuracy
454
- value: 88.0
455
  - task:
456
  type: Sentence completion
457
  dataset:
@@ -462,7 +475,7 @@ model-index:
462
  revision: 37f73c60fb123111fa5af5f9b705d0b3747fd187
463
  metrics:
464
  - type: Accuracy
465
- value: 81.0
466
  - task:
467
  type: Sentence completion
468
  dataset:
@@ -473,7 +486,7 @@ model-index:
473
  revision: 37f73c60fb123111fa5af5f9b705d0b3747fd187
474
  metrics:
475
  - type: Accuracy
476
- value: 79.0
477
  - task:
478
  type: Sentence completion
479
  dataset:
@@ -484,7 +497,7 @@ model-index:
484
  revision: 37f73c60fb123111fa5af5f9b705d0b3747fd187
485
  metrics:
486
  - type: Accuracy
487
- value: 90.0
488
  - task:
489
  type: Sentence completion
490
  dataset:
@@ -495,7 +508,7 @@ model-index:
495
  revision: 37f73c60fb123111fa5af5f9b705d0b3747fd187
496
  metrics:
497
  - type: Accuracy
498
- value: 88.0
499
  - task:
500
  type: Sentence completion
501
  dataset:
@@ -506,7 +519,7 @@ model-index:
506
  revision: 37f73c60fb123111fa5af5f9b705d0b3747fd187
507
  metrics:
508
  - type: Accuracy
509
- value: 56.0
510
  - task:
511
  type: Sentence completion
512
  dataset:
@@ -517,7 +530,7 @@ model-index:
517
  revision: 37f73c60fb123111fa5af5f9b705d0b3747fd187
518
  metrics:
519
  - type: Accuracy
520
- value: 81.0
521
  - task:
522
  type: Sentence completion
523
  dataset:
@@ -528,7 +541,7 @@ model-index:
528
  revision: 37f73c60fb123111fa5af5f9b705d0b3747fd187
529
  metrics:
530
  - type: Accuracy
531
- value: 81.0
532
  - task:
533
  type: Sentence completion
534
  dataset:
@@ -539,7 +552,7 @@ model-index:
539
  revision: 37f73c60fb123111fa5af5f9b705d0b3747fd187
540
  metrics:
541
  - type: Accuracy
542
- value: 76.0
543
  - task:
544
  type: Sentence completion
545
  dataset:
@@ -550,7 +563,7 @@ model-index:
550
  revision: 37f73c60fb123111fa5af5f9b705d0b3747fd187
551
  metrics:
552
  - type: Accuracy
553
- value: 76.0
554
  - task:
555
  type: Sentence completion
556
  dataset:
@@ -561,7 +574,7 @@ model-index:
561
  revision: 37f73c60fb123111fa5af5f9b705d0b3747fd187
562
  metrics:
563
  - type: Accuracy
564
- value: 85.0
565
  - task:
566
  type: Sentence completion
567
  dataset:
@@ -572,7 +585,7 @@ model-index:
572
  revision: 37f73c60fb123111fa5af5f9b705d0b3747fd187
573
  metrics:
574
  - type: Accuracy
575
- value: 87.0
576
  - task:
577
  type: Sentence completion
578
  dataset:
@@ -583,7 +596,7 @@ model-index:
583
  revision: 8bb76e594b68147f1a430e86829d07189622b90d
584
  metrics:
585
  - type: Accuracy
586
- value: 91.0
587
  - task:
588
  type: Sentence completion
589
  dataset:
@@ -683,6 +696,7 @@ model-index:
683
  metrics:
684
  - type: Accuracy
685
  value: 93.05
 
686
  ---
687
 
688
  ![xmtf](https://github.com/bigscience-workshop/xmtf/blob/master/xmtf_banner.png?raw=true)
 
69
  - my
70
  - ne
71
  - nl
72
+ - 'no'
73
  - ny
74
  - pa
75
  - pl
 
108
  tags:
109
  - text2text-generation
110
  widget:
111
+ - text: Life is beautiful! Translate to Mongolian.
112
+ example_title: mn-en translation
113
+ - text: Le mot japonais «憂鬱» veut dire quoi en Odia?
114
+ example_title: jp-or-fr translation
115
+ - text: >-
116
+ Stell mir eine schwierige Quiz Frage bei der es um Astronomie geht. Bitte
117
+ stell die Frage auf Norwegisch.
118
+ example_title: de-nb quiz
119
+ - text: >-
120
+ 一个传奇的开端,一个不灭的神话,这不仅仅是一部电影,而是作为一个走进新时代的标签,永远彪炳史册。Would you rate the previous
121
+ review as positive, neutral or negative?
122
+ example_title: zh-en sentiment
123
+ - text: 一个传奇的开端,一个不灭的神话,这不仅仅是一部电影,而是作为一个走进新时代的标签,永远彪炳史册。你认为这句话的立场是赞扬、中立还是批评?
124
+ example_title: zh-zh sentiment
125
+ - text: Suggest at least five related search terms to "Mạng neural nhân tạo".
126
+ example_title: vi-en query
127
+ - text: >-
128
+ Proposez au moins cinq mots clés concernant «Réseau de neurones
129
+ artificiels».
130
+ example_title: fr-fr query
131
+ - text: Explain in a sentence in Telugu what is backpropagation in neural networks.
132
+ example_title: te-en qa
133
+ - text: Why is the sky blue?
134
+ example_title: en-en qa
135
+ - text: >-
136
+ Write a fairy tale about a troll saving a princess from a dangerous dragon.
137
+ The fairy tale is a masterpiece that has achieved praise worldwide and its
138
+ moral is "Heroes Come in All Shapes and Sizes". Story (in Spanish):
139
+ example_title: es-en fable
140
+ - text: >-
141
+ Write a fable about wood elves living in a forest that is suddenly invaded
142
+ by ogres. The fable is a masterpiece that has achieved praise worldwide and
143
+ its moral is "Violence is the last refuge of the incompetent". Fable (in
144
+ Hindi):
145
+ example_title: hi-en fable
146
  model-index:
147
  - name: mt0-xxl-mt
148
  results:
 
244
  revision: 9dbd830a06fea8b1c49d6e5ef2004a08d9f45094
245
  metrics:
246
  - type: Accuracy
247
+ value: 42
248
  - task:
249
  type: Natural language inference
250
  dataset:
 
448
  dataset:
449
  type: story_cloze
450
  name: StoryCloze (2016)
451
+ config: '2016'
452
  split: validation
453
  revision: e724c6f8cdf7c7a2fb229d862226e15b023ee4db
454
  metrics:
 
464
  revision: 9e12063561e7e6c79099feb6d5a493142584e9e2
465
  metrics:
466
  - type: Accuracy
467
+ value: 88
468
  - task:
469
  type: Sentence completion
470
  dataset:
 
475
  revision: 37f73c60fb123111fa5af5f9b705d0b3747fd187
476
  metrics:
477
  - type: Accuracy
478
+ value: 81
479
  - task:
480
  type: Sentence completion
481
  dataset:
 
486
  revision: 37f73c60fb123111fa5af5f9b705d0b3747fd187
487
  metrics:
488
  - type: Accuracy
489
+ value: 79
490
  - task:
491
  type: Sentence completion
492
  dataset:
 
497
  revision: 37f73c60fb123111fa5af5f9b705d0b3747fd187
498
  metrics:
499
  - type: Accuracy
500
+ value: 90
501
  - task:
502
  type: Sentence completion
503
  dataset:
 
508
  revision: 37f73c60fb123111fa5af5f9b705d0b3747fd187
509
  metrics:
510
  - type: Accuracy
511
+ value: 88
512
  - task:
513
  type: Sentence completion
514
  dataset:
 
519
  revision: 37f73c60fb123111fa5af5f9b705d0b3747fd187
520
  metrics:
521
  - type: Accuracy
522
+ value: 56
523
  - task:
524
  type: Sentence completion
525
  dataset:
 
530
  revision: 37f73c60fb123111fa5af5f9b705d0b3747fd187
531
  metrics:
532
  - type: Accuracy
533
+ value: 81
534
  - task:
535
  type: Sentence completion
536
  dataset:
 
541
  revision: 37f73c60fb123111fa5af5f9b705d0b3747fd187
542
  metrics:
543
  - type: Accuracy
544
+ value: 81
545
  - task:
546
  type: Sentence completion
547
  dataset:
 
552
  revision: 37f73c60fb123111fa5af5f9b705d0b3747fd187
553
  metrics:
554
  - type: Accuracy
555
+ value: 76
556
  - task:
557
  type: Sentence completion
558
  dataset:
 
563
  revision: 37f73c60fb123111fa5af5f9b705d0b3747fd187
564
  metrics:
565
  - type: Accuracy
566
+ value: 76
567
  - task:
568
  type: Sentence completion
569
  dataset:
 
574
  revision: 37f73c60fb123111fa5af5f9b705d0b3747fd187
575
  metrics:
576
  - type: Accuracy
577
+ value: 85
578
  - task:
579
  type: Sentence completion
580
  dataset:
 
585
  revision: 37f73c60fb123111fa5af5f9b705d0b3747fd187
586
  metrics:
587
  - type: Accuracy
588
+ value: 87
589
  - task:
590
  type: Sentence completion
591
  dataset:
 
596
  revision: 8bb76e594b68147f1a430e86829d07189622b90d
597
  metrics:
598
  - type: Accuracy
599
+ value: 91
600
  - task:
601
  type: Sentence completion
602
  dataset:
 
696
  metrics:
697
  - type: Accuracy
698
  value: 93.05
699
+ pipeline_tag: text2text-generation
700
  ---
701
 
702
  ![xmtf](https://github.com/bigscience-workshop/xmtf/blob/master/xmtf_banner.png?raw=true)