kaixkhazaki commited on
Commit
4a44019
·
verified ·
1 Parent(s): c41bb4e

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +51 -1
README.md CHANGED
@@ -4,6 +4,7 @@ license: mit
4
  base_model: deepset/gbert-large
5
  tags:
6
  - generated_from_trainer
 
7
  metrics:
8
  - accuracy
9
  - f1
@@ -12,6 +13,11 @@ metrics:
12
  model-index:
13
  - name: german-zeroshot
14
  results: []
 
 
 
 
 
15
  ---
16
 
17
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -26,6 +32,50 @@ It achieves the following results on the evaluation set:
26
  - F1: 0.8487
27
  - Precision: 0.8505
28
  - Recall: 0.8486
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
29
 
30
  ## Model description
31
 
@@ -82,4 +132,4 @@ The following hyperparameters were used during training:
82
  - Transformers 4.48.0.dev0
83
  - Pytorch 2.4.1+cu121
84
  - Datasets 3.1.0
85
- - Tokenizers 0.21.0
 
4
  base_model: deepset/gbert-large
5
  tags:
6
  - generated_from_trainer
7
+ - german
8
  metrics:
9
  - accuracy
10
  - f1
 
13
  model-index:
14
  - name: german-zeroshot
15
  results: []
16
+ datasets:
17
+ - facebook/xnli
18
+ language:
19
+ - de
20
+ pipeline_tag: zero-shot-classification
21
  ---
22
 
23
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 
32
  - F1: 0.8487
33
  - Precision: 0.8505
34
  - Recall: 0.8486
35
+ -
36
+ ## Usage
37
+
38
+ ```python
39
+ # Use a pipeline as a high-level helper
40
+
41
+ pipe = pipeline(
42
+ "zero-shot-classification",
43
+ model="kaixkhazaki/german-zeroshot",
44
+ tokenizer="kaixkhazaki/german-zeroshot",
45
+ device=0 if torch.cuda.is_available() else -1 # Use GPU if available
46
+ )
47
+
48
+ #Enter your text and possible candidates of classification
49
+ sequence = "Können Sie mir die Schritte zur Konfiguration eines VPN auf einem Linux-Server erklären?"
50
+ candidate_labels = [
51
+ "Technische Dokumentation",
52
+ "IT-Support",
53
+ "Netzwerkadministration",
54
+ "Linux-Konfiguration",
55
+ "VPN-Setup"
56
+ ]
57
+ pipe(sequence,candidate_labels)
58
+ >>
59
+ {'sequence': 'Können Sie mir die Schritte zur Konfiguration eines VPN auf einem Linux-Server erklären?',
60
+ 'labels': ['VPN-Setup', 'Linux-Konfiguration', 'Netzwerkadministration', 'IT-Support', 'Technische Dokumentation'],
61
+ 'scores': [0.3245040476322174, 0.32373329997062683, 0.16423103213310242, 0.09850211441516876, 0.08902951329946518]}
62
+
63
+ #example 2
64
+ sequence = "Können Sie mir die Schritte zur Konfiguration eines VPN auf einem Linux-Server erklären?"
65
+ candidate_labels = [
66
+ "Technische Dokumentation",
67
+ "IT-Support",
68
+ "Netzwerkadministration",
69
+ "Linux-Konfiguration",
70
+ "VPN-Setup"
71
+ ]
72
+ pipe(sequence,candidate_labels)
73
+ >>
74
+ {'sequence': 'Wie lautet die Garantiezeit für dieses Produkt?',
75
+ 'labels': ['Garantiebedingungen', 'Produktdetails', 'Reklamation', 'Kundendienst', 'Kaufberatung'],
76
+ 'scores': [0.4313304126262665, 0.2905466556549072, 0.10058070719242096, 0.09384352713823318, 0.08369863778352737]}
77
+
78
+ ```
79
 
80
  ## Model description
81
 
 
132
  - Transformers 4.48.0.dev0
133
  - Pytorch 2.4.1+cu121
134
  - Datasets 3.1.0
135
+ - Tokenizers 0.21.0