Review Recognizer
A fine-tuned version of distilbert-base-uncased for binary sentiment classification (positive/negative) on movie reviews.
Training details
- Base model: distilbert-base-uncased
- Dataset: IMDb movie reviews (stanfordnlp/imdb)
- Training subset: 2,000 examples
- Evaluation subset: 500 examples
- Epochs: 2
Results
| Metric | Score |
|---|---|
| Accuracy | 0.888 |
| F1 | 0.889763779527559 |
Usage
from transformers import pipeline
classifier = pipeline("sentiment-analysis", model="authoy6788/review-recognizer")
result = classifier("This movie was fantastic!")
print(result)
Limitations
This model was trained on a small subset of English-language movie reviews. It may perform poorly on out-of-domain text (e.g., other languages, non-review text, or very different writing styles).
- Downloads last month
- -
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support
Model tree for authoy6788/review-recognizer
Base model
distilbert/distilbert-base-uncased