Instructions to use shahrukhx01/bert-multitask-query-classifiers with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use shahrukhx01/bert-multitask-query-classifiers with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="shahrukhx01/bert-multitask-query-classifiers")# Load model directly from transformers import AutoTokenizer, AutoModelForSequenceClassification tokenizer = AutoTokenizer.from_pretrained("shahrukhx01/bert-multitask-query-classifiers") model = AutoModelForSequenceClassification.from_pretrained("shahrukhx01/bert-multitask-query-classifiers") - Notebooks
- Google Colab
- Kaggle
Commit ·
3c91a87
1
Parent(s): efe2834
Update README.md
Browse files
README.md
CHANGED
|
@@ -2,6 +2,14 @@
|
|
| 2 |
* First prediction head classifies between keyword sentences vs statements/questions
|
| 3 |
* Second prediction head corresponds to classifier for statements vs questions
|
| 4 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 5 |
## Article
|
| 6 |
[Medium article](https://medium.com/@shahrukhx01/multi-task-learning-with-transformers-part-1-multi-prediction-heads-b7001cf014bf)
|
| 7 |
## Demo Notebook
|
|
|
|
| 2 |
* First prediction head classifies between keyword sentences vs statements/questions
|
| 3 |
* Second prediction head corresponds to classifier for statements vs questions
|
| 4 |
|
| 5 |
+
## Scores
|
| 6 |
+
Spaadia SQuaD Test acc: 0.9891
|
| 7 |
+
Quora Keyword Pairs Test acc: NA
|
| 8 |
+
|
| 9 |
+
## Datasets:
|
| 10 |
+
Quora Keyword Pairs: https://www.kaggle.com/stefanondisponibile/quora-question-keyword-pairs
|
| 11 |
+
Spaadia SQuaD pairs: https://www.kaggle.com/shahrukhkhan/questions-vs-statementsclassificationdataset
|
| 12 |
+
|
| 13 |
## Article
|
| 14 |
[Medium article](https://medium.com/@shahrukhx01/multi-task-learning-with-transformers-part-1-multi-prediction-heads-b7001cf014bf)
|
| 15 |
## Demo Notebook
|