Hugging Face's logo

MoritzLaurer
/
mDeBERTa-v3-base-xnli-multilingual-nli-2mil7

Zero-Shot Classification Transformers PyTorch ONNX Safetensors
27 languages deberta-v2 text-classification nli Eval Results Inference Endpoints 4 papers
Model card Files Community
8
MoritzLaurer HF staff librarian-bot commited on
Commit
b5113eb
•
1 Parent(s): c969b26

Librarian Bot: Update Hugging Face dataset ID (#8)

Browse files

- Librarian Bot: Update Hugging Face dataset ID (76f767522d40596e46aec1079d86170f2b0b1afb)


Co-authored-by: Librarian Bot (Bot) <librarian-bot@users.noreply.huggingface.co>

Files changed (1) hide show
  1. README.md +64 -76
README.md CHANGED
@@ -1,5 +1,5 @@
1
  ---
2
- language:
3
  - multilingual
4
  - zh
5
  - ja
@@ -27,118 +27,106 @@ language:
27
  - he
28
  - sw
29
  - ps
 
30
  tags:
31
  - zero-shot-classification
32
  - text-classification
33
  - nli
34
  - pytorch
35
- license: mit
36
- metrics:
37
- - accuracy
38
  datasets:
39
  - MoritzLaurer/multilingual-NLI-26lang-2mil7
40
  - xnli
41
  - multi_nli
42
- - anli
43
  - fever
44
  - lingnli
45
  - alisawuffles/WANLI
 
 
46
  pipeline_tag: zero-shot-classification
47
- #- text-classification
48
  widget:
49
- - text: "Angela Merkel ist eine Politikerin in Deutschland und Vorsitzende der CDU"
50
- candidate_labels: "politics, economy, entertainment, environment"
51
-
52
- model-index: # info: https://github.com/huggingface/hub-docs/blame/main/modelcard.md
53
  - name: DeBERTa-v3-base-xnli-multilingual-nli-2mil7
54
  results:
55
  - task:
56
- type: text-classification # Required. Example: automatic-speech-recognition
57
- name: Natural Language Inference # Optional. Example: Speech Recognition
58
  dataset:
59
- type: multi_nli # Required. Example: common_voice. Use dataset id from https://hf.co/datasets
60
- name: MultiNLI-matched # Required. A pretty name for the dataset. Example: Common Voice (French)
61
- split: validation_matched # Optional. Example: test
62
  metrics:
63
- - type: accuracy # Required. Example: wer. Use metric id from https://hf.co/metrics
64
- value: 0,857 # Required. Example: 20.90
65
- #name: # Optional. Example: Test WER
66
- verified: false # Optional. If true, indicates that evaluation was generated by Hugging Face (vs. self-reported).
67
  - task:
68
- type: text-classification # Required. Example: automatic-speech-recognition
69
- name: Natural Language Inference # Optional. Example: Speech Recognition
70
  dataset:
71
- type: multi_nli # Required. Example: common_voice. Use dataset id from https://hf.co/datasets
72
- name: MultiNLI-mismatched # Required. A pretty name for the dataset. Example: Common Voice (French)
73
- split: validation_mismatched # Optional. Example: test
74
  metrics:
75
- - type: accuracy # Required. Example: wer. Use metric id from https://hf.co/metrics
76
- value: 0,856 # Required. Example: 20.90
77
- #name: # Optional. Example: Test WER
78
- verified: false # Optional. If true, indicates that evaluation was generated by Hugging Face (vs. self-reported).
79
  - task:
80
- type: text-classification # Required. Example: automatic-speech-recognition
81
- name: Natural Language Inference # Optional. Example: Speech Recognition
82
  dataset:
83
- type: anli # Required. Example: common_voice. Use dataset id from https://hf.co/datasets
84
- name: ANLI-all # Required. A pretty name for the dataset. Example: Common Voice (French)
85
- split: test_r1+test_r2+test_r3 # Optional. Example: test
86
  metrics:
87
- - type: accuracy # Required. Example: wer. Use metric id from https://hf.co/metrics
88
- value: 0,537 # Required. Example: 20.90
89
- #name: # Optional. Example: Test WER
90
- verified: false # Optional. If true, indicates that evaluation was generated by Hugging Face (vs. self-reported).
91
  - task:
92
- type: text-classification # Required. Example: automatic-speech-recognition
93
- name: Natural Language Inference # Optional. Example: Speech Recognition
94
  dataset:
95
- type: anli # Required. Example: common_voice. Use dataset id from https://hf.co/datasets
96
- name: ANLI-r3 # Required. A pretty name for the dataset. Example: Common Voice (French)
97
- split: test_r3 # Optional. Example: test
98
  metrics:
99
- - type: accuracy # Required. Example: wer. Use metric id from https://hf.co/metrics
100
- value: 0,497 # Required. Example: 20.90
101
- #name: # Optional. Example: Test WER
102
- verified: false # Optional. If true, indicates that evaluation was generated by Hugging Face (vs. self-reported).
103
  - task:
104
- type: text-classification # Required. Example: automatic-speech-recognition
105
- name: Natural Language Inference # Optional. Example: Speech Recognition
106
  dataset:
107
- type: alisawuffles/WANLI # Required. Example: common_voice. Use dataset id from https://hf.co/datasets
108
- name: WANLI # Required. A pretty name for the dataset. Example: Common Voice (French)
109
- split: test # Optional. Example: test
110
  metrics:
111
- - type: accuracy # Required. Example: wer. Use metric id from https://hf.co/metrics
112
- value: 0,732 # Required. Example: 20.90
113
- #name: # Optional. Example: Test WER
114
- verified: false # Optional. If true, indicates that evaluation was generated by Hugging Face (vs. self-reported).
115
  - task:
116
- type: text-classification # Required. Example: automatic-speech-recognition
117
- name: Natural Language Inference # Optional. Example: Speech Recognition
118
  dataset:
119
- type: lingnli # Required. Example: common_voice. Use dataset id from https://hf.co/datasets
120
- name: LingNLI # Required. A pretty name for the dataset. Example: Common Voice (French)
121
- split: test # Optional. Example: test
122
  metrics:
123
- - type: accuracy # Required. Example: wer. Use metric id from https://hf.co/metrics
124
- value: 0,788 # Required. Example: 20.90
125
- #name: # Optional. Example: Test WER
126
- verified: false # Optional. If true, indicates that evaluation was generated by Hugging Face (vs. self-reported).
127
  - task:
128
- type: text-classification # Required. Example: automatic-speech-recognition
129
- name: Natural Language Inference # Optional. Example: Speech Recognition
130
  dataset:
131
- type: fever-nli # Required. Example: common_voice. Use dataset id from https://hf.co/datasets
132
- name: fever-nli # Required. A pretty name for the dataset. Example: Common Voice (French)
133
- split: test # Optional. Example: test
134
  metrics:
135
- - type: accuracy # Required. Example: wer. Use metric id from https://hf.co/metrics
136
- value: 0,761 # Required. Example: 20.90
137
- #name: # Optional. Example: Test WER
138
- verified: false # Optional. If true, indicates that evaluation was generated by Hugging Face (vs. self-reported).
139
-
140
-
141
-
142
  ---
143
  # Model card for mDeBERTa-v3-base-xnli-multilingual-nli-2mil7
144
 
1
  ---
2
+ language:
3
  - multilingual
4
  - zh
5
  - ja
27
  - he
28
  - sw
29
  - ps
30
+ license: mit
31
  tags:
32
  - zero-shot-classification
33
  - text-classification
34
  - nli
35
  - pytorch
 
 
 
36
  datasets:
37
  - MoritzLaurer/multilingual-NLI-26lang-2mil7
38
  - xnli
39
  - multi_nli
40
+ - facebook/anli
41
  - fever
42
  - lingnli
43
  - alisawuffles/WANLI
44
+ metrics:
45
+ - accuracy
46
  pipeline_tag: zero-shot-classification
 
47
  widget:
48
+ - text: Angela Merkel ist eine Politikerin in Deutschland und Vorsitzende der CDU
49
+ candidate_labels: politics, economy, entertainment, environment
50
+ model-index:
 
51
  - name: DeBERTa-v3-base-xnli-multilingual-nli-2mil7
52
  results:
53
  - task:
54
+ type: text-classification
55
+ name: Natural Language Inference
56
  dataset:
57
+ name: MultiNLI-matched
58
+ type: multi_nli
59
+ split: validation_matched
60
  metrics:
61
+ - type: accuracy
62
+ value: 0,857
63
+ verified: false
 
64
  - task:
65
+ type: text-classification
66
+ name: Natural Language Inference
67
  dataset:
68
+ name: MultiNLI-mismatched
69
+ type: multi_nli
70
+ split: validation_mismatched
71
  metrics:
72
+ - type: accuracy
73
+ value: 0,856
74
+ verified: false
 
75
  - task:
76
+ type: text-classification
77
+ name: Natural Language Inference
78
  dataset:
79
+ name: ANLI-all
80
+ type: anli
81
+ split: test_r1+test_r2+test_r3
82
  metrics:
83
+ - type: accuracy
84
+ value: 0,537
85
+ verified: false
 
86
  - task:
87
+ type: text-classification
88
+ name: Natural Language Inference
89
  dataset:
90
+ name: ANLI-r3
91
+ type: anli
92
+ split: test_r3
93
  metrics:
94
+ - type: accuracy
95
+ value: 0,497
96
+ verified: false
 
97
  - task:
98
+ type: text-classification
99
+ name: Natural Language Inference
100
  dataset:
101
+ name: WANLI
102
+ type: alisawuffles/WANLI
103
+ split: test
104
  metrics:
105
+ - type: accuracy
106
+ value: 0,732
107
+ verified: false
 
108
  - task:
109
+ type: text-classification
110
+ name: Natural Language Inference
111
  dataset:
112
+ name: LingNLI
113
+ type: lingnli
114
+ split: test
115
  metrics:
116
+ - type: accuracy
117
+ value: 0,788
118
+ verified: false
 
119
  - task:
120
+ type: text-classification
121
+ name: Natural Language Inference
122
  dataset:
123
+ name: fever-nli
124
+ type: fever-nli
125
+ split: test
126
  metrics:
127
+ - type: accuracy
128
+ value: 0,761
129
+ verified: false
 
 
 
 
130
  ---
131
  # Model card for mDeBERTa-v3-base-xnli-multilingual-nli-2mil7
132