kiddothe2b commited on
Commit
31b062d
1 Parent(s): 95666ab

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +48 -6
README.md CHANGED
@@ -6,7 +6,7 @@ datasets:
6
  metrics:
7
  - accuracy
8
  model-index:
9
- - name: danish-legal-longformer-eurlex
10
  results:
11
  - task:
12
  type: text-classification
@@ -29,15 +29,57 @@ model-index:
29
 
30
  This model is a fine-tuned version of [coastalcph/danish-legal-longformer-base](https://huggingface.co/coastalcph/danish-legal-longformer-base) on the Danish part of [MultiEURLEX](https://huggingface.co/datasets/multi_eurlex) dataset.
31
 
32
- ## Intended uses & limitations
33
-
34
- More information needed
35
-
36
  ## Training and evaluation data
37
 
38
  The Danish part of [MultiEURLEX](https://huggingface.co/datasets/multi_eurlex) dataset.
39
 
40
- ### Framework versions
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
41
 
42
  - Transformers 4.18.0
43
  - Pytorch 1.12.0+cu113
 
6
  metrics:
7
  - accuracy
8
  model-index:
9
+ - name: coastalcph/danish-legal-longformer-eurlex
10
  results:
11
  - task:
12
  type: text-classification
 
29
 
30
  This model is a fine-tuned version of [coastalcph/danish-legal-longformer-base](https://huggingface.co/coastalcph/danish-legal-longformer-base) on the Danish part of [MultiEURLEX](https://huggingface.co/datasets/multi_eurlex) dataset.
31
 
 
 
 
 
32
  ## Training and evaluation data
33
 
34
  The Danish part of [MultiEURLEX](https://huggingface.co/datasets/multi_eurlex) dataset.
35
 
36
+ ## Use of Model
37
+
38
+ ### As a text classifier:
39
+
40
+ ```python
41
+ from transformers import pipeline
42
+ import numpy as np
43
+
44
+ # Init text classification pipeline
45
+ text_cls_pipe = pipeline(task="text-classification",
46
+ model="coastalcph/danish-legal-longformer-eurlex",
47
+ use_auth_token='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')
48
+
49
+ # Encode and Classify document
50
+ predictions = text_cls_pipe("KOMMISSIONENS BESLUTNING\naf 6. marts 2006\nom klassificering af visse byggevarers "
51
+ "ydeevne med hensyn til reaktion ved brand for så vidt angår trægulve samt vægpaneler "
52
+ "og vægbeklædning i massivt træ\n(meddelt under nummer K(2006) 655")
53
+
54
+ # Print prediction
55
+ print(predictions)
56
+ # [{'label': 'building and public works', 'score': 0.9626012444496155}]
57
+ ```
58
+
59
+ ### As a feature extractor (document embedder):
60
+
61
+ ```python
62
+ from transformers import pipeline
63
+ import numpy as np
64
+
65
+ # Init feature extraction pipeline
66
+ feature_extraction_pipe = pipeline(task="feature-extraction",
67
+ model="coastalcph/danish-legal-longformer-eurlex",
68
+ use_auth_token='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')
69
+
70
+ # Encode document
71
+ predictions = feature_extraction_pipe("KOMMISSIONENS BESLUTNING\naf 6. marts 2006\nom klassificering af visse byggevarers "
72
+ "ydeevne med hensyn til reaktion ved brand for så vidt angår trægulve samt vægpaneler "
73
+ "og vægbeklædning i massivt træ\n(meddelt under nummer K(2006) 655")
74
+
75
+ # Use CLS token representation as document embedding
76
+ document_features = token_wise_features[0][0]
77
+
78
+ print(document_features.shape)
79
+ # (768,)
80
+ ```
81
+
82
+ ## Framework versions
83
 
84
  - Transformers 4.18.0
85
  - Pytorch 1.12.0+cu113