Downloads · 30 days
5
10% of all-time downloads
mnli_model_deberta_3_labels_combined_dataset
Josef0801/mnli_model_deberta_3_labels_combined_dataset
mnli_model_deberta_3_labels_combined_dataset is a text classification model from Josef0801. Use it when you need a label for a piece of text. It is set up for transformers.
Based on svenbl80/deberta-v3-Base-finetuned-mnli finetuned on a synthetic dataset (3 labels, real-estate + berechtigungsmanagement)
All-time downloads
49
Public
Repo size
740 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.h5738 MB · 99%
At a glance
- Task
- Text Classification
- Library
- transformers
- Model type
- deberta-v2
- Access
- Public
- Created
- Jan 24, 2024
- Updated
- Jan 24, 2024
- SHA
- 9ee7747d
Try a prompt
Model card
From the Hugging Face model README
Based on svenbl80/deberta-v3-Base-finetuned-mnli finetuned on a synthetic dataset (3 labels, real-estate + berechtigungsmanagement)
Performance on test dataset:
precision recall f1-score support
0 1.00 0.93 0.96 42
1 0.94 0.97 0.95 76
2 0.98 0.98 0.98 114
accuracy 0.97 232
macro avg 0.97 0.96 0.97 232
weighted avg 0.97 0.97 0.97 232
Performance on real estate test dataset alone: precision recall f1-score support
0 1.00 0.83 0.91 18
1 0.73 1.00 0.85 11
2 1.00 0.94 0.97 16
accuracy 0.91 45
macro avg 0.91 0.92 0.91 45
weighted avg 0.93 0.91 0.91 45
- Task
- Text Classification
- Library
- transformers
- Type
- deberta-v2
- Created
- Jan 24, 2024
- Updated
- Jan 24, 2024