stanfordnlp/imdb
Viewer • Updated • 100k • 177k • 370
This model is a fine-tuned version of distilbert-base-uncased on the IMDB dataset, trained for sentiment analysis of movie reviews.
Evaluation on a balanced test set of 100 examples (50 positive, 50 negative):
| Metric | Value |
|---|---|
| Accuracy | 84.00% |
| F1 Score | 0.8462 |
| Precision | 81.48% |
| Recall | 88.00% |
| Inference Time | ~3.30 ms/example |
This model can be used directly for sentiment analysis of text, particularly movie reviews.