DistilBERT Sentiment Classifier
A fine-tuned DistilBERT model for binary sentiment classification, trained on a custom dataset (with VADER features).
Usage
from transformers import pipeline
classifier = pipeline("sentiment-analysis", model="waseemrazakhan/distilbert-sentiment-classifier")
print(classifier("I really enjoyed this movie!"))
Training & Evaluation
- Base model:
distilbert-base-uncased - Epochs: 3
- Batch size: 8
- Max sequence length: 128
| Metric | Value |
|---|---|
| Accuracy | 0.9512 |
| F1 Score | 0.9526 |
| Precision | 0.9489 |
| Recall | 0.9564 |
Limitations
- English-only
- May not generalize to very different domains
- Downloads last month
- 5