ChrisLalk commited on
Commit
2cc1a3a
1 Parent(s): 69f8e68

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +39 -15
README.md CHANGED
@@ -1,28 +1,52 @@
1
  ---
2
  license: apache-2.0
3
  datasets:
4
- - google-research-datasets/go_emotions
 
5
  language:
6
- - de
7
  metrics:
8
- - accuracy value: 0.27
9
- - f1 value: 0.382
10
- - roc_auc value: 0.658
11
  pipeline_tag: text-classification
12
  tags:
13
- - medical
 
 
 
 
 
 
 
 
 
 
14
  ---
15
- This is basically the German translation of arpanghoshal/EmoRoBERTa. We used the go_emotions dataset, translated it into German and fine-tuned the intfloat/multilingual-e5-large model.
16
 
17
- **Hyperparameters**
18
- - Epochs: 10
19
- - learning_rate: 1e-5
20
- - weight_decay: 0.01
21
 
22
- **Model Performance**
23
- - accuracy: 0.27
24
- - f1: 0.382
25
- - roc_auc: 0.658
26
 
 
27
 
28
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
  ---
2
  license: apache-2.0
3
  datasets:
4
+ - google-research-datasets/go_emotions
5
+ base_model: intfloat/multilingual-e5-large
6
  language:
7
+ - de
8
  metrics:
9
+ - roc_auc value: 0.658
10
+ - f1: 0.382
11
+ - accuracy: 0.27
12
  pipeline_tag: text-classification
13
  tags:
14
+ - medical
15
+ model_description: >-
16
+ This is basically the German translation of arpanghoshal/EmoRoBERTa. We used
17
+ the go_emotions dataset, translated it into German and fine-tuned the
18
+ intfloat/multilingual-e5-large model. So this model allows the classification
19
+ of 28 emotions in German Transcripts ('admiration', 'amusement', 'anger',
20
+ 'annoyance', 'approval', 'caring', 'confusion', 'curiosity', 'desire',
21
+ 'disappointment', 'disapproval', 'disgust', 'embarrassment', 'excitement',
22
+ 'fear', 'gratitude', 'grief', 'joy', 'love', 'nervousness', 'optimism',
23
+ 'pride', 'realization', 'relief', 'remorse', 'sadness', 'surprise',
24
+ 'neutral'). A paper will be published soonish...
25
  ---
26
+ # Model Card for G-E5-rman-Emotions
27
 
28
+ This is basically the German translation of arpanghoshal/EmoRoBERTa. We used the go_emotions dataset, translated it into German and fine-tuned the intfloat/multilingual-e5-large model. So this model allows the classification of 28 emotions in German Transcripts ('admiration', 'amusement', 'anger', 'annoyance', 'approval', 'caring', 'confusion', 'curiosity', 'desire', 'disappointment', 'disapproval', 'disgust', 'embarrassment', 'excitement', 'fear', 'gratitude', 'grief', 'joy', 'love', 'nervousness', 'optimism', 'pride', 'realization', 'relief', 'remorse', 'sadness', 'surprise', 'neutral'). A paper will be published soonish...
 
 
 
29
 
 
 
 
 
30
 
31
+ ## Model Details
32
 
33
 
34
+ - **Model type:** text-classification
35
+ - **Language(s) (NLP):** German
36
+ - **License:** apache-2.0
37
+ - **Finetuned from model:** intfloat/multilingual-e5-large
38
+ - **Hyperparameters:**
39
+ - Epochs: 10
40
+ - learning_rate: 1e-5
41
+ - weight_decay: 0.01
42
+ - **Metrics:**
43
+ - accuracy: 0.27
44
+ - f1: 0.382
45
+ - roc_auc: 0.658
46
+ ---
47
+
48
+
49
+ ## How to Get Started with the Model
50
+
51
+ Use the code below to get started with the model.
52
+