Instructions to use nvidia/domain-classifier with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use nvidia/domain-classifier with Transformers:
# pip install -U transformers accelerate # Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("nvidia/domain-classifier", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Update README.md
Browse files
README.md
CHANGED
|
@@ -85,7 +85,9 @@ print(predicted_domains)
|
|
| 85 |
# Evaluation Benchmarks
|
| 86 |
|
| 87 |
Evaluation Metric: PR-AUC
|
|
|
|
| 88 |
PR-AUC score on evaluation set with 105k samples - 0.9873
|
|
|
|
| 89 |
PR-AUC score for each domain:
|
| 90 |
| Domain | PR-AUC |
|
| 91 |
|--------------------------|--------|
|
|
@@ -118,8 +120,8 @@ PR-AUC score for each domain:
|
|
| 118 |
| Mean | 0.9873 |
|
| 119 |
|
| 120 |
# References
|
| 121 |
-
https://arxiv.org/abs/2111.09543
|
| 122 |
-
https://github.com/microsoft/DeBERTa
|
| 123 |
# License
|
| 124 |
License to use this model is covered by the Apache 2.0. By downloading the public and release version of the model, you accept the terms and conditions of the Apache License 2.0.
|
| 125 |
This repository contains the code for the domain classifier model.
|
|
|
|
| 85 |
# Evaluation Benchmarks
|
| 86 |
|
| 87 |
Evaluation Metric: PR-AUC
|
| 88 |
+
|
| 89 |
PR-AUC score on evaluation set with 105k samples - 0.9873
|
| 90 |
+
|
| 91 |
PR-AUC score for each domain:
|
| 92 |
| Domain | PR-AUC |
|
| 93 |
|--------------------------|--------|
|
|
|
|
| 120 |
| Mean | 0.9873 |
|
| 121 |
|
| 122 |
# References
|
| 123 |
+
- https://arxiv.org/abs/2111.09543
|
| 124 |
+
- https://github.com/microsoft/DeBERTa
|
| 125 |
# License
|
| 126 |
License to use this model is covered by the Apache 2.0. By downloading the public and release version of the model, you accept the terms and conditions of the Apache License 2.0.
|
| 127 |
This repository contains the code for the domain classifier model.
|