π¬ IMDb Sentiment Classifier
This is a fine-tuned DistilBERT model for analyzing sentiment in IMDb movie reviews.
π Dataset
- Source: IMDb dataset from Hugging Face Datasets
- Task: Binary classification (Positive / Negative)
π Training Details
- Model:
distilbert-base-uncased
- Learning rate:
2e-5
- Batch size:
4
- Epochs:
1
- Loss function: CrossEntropyLoss
π Evaluation Results
Metric | Score |
---|---|
Accuracy | 92.5% |
F1-score | 92.6% |
Precision | 92.9% |
Recall | 92.3% |
π How to Use
from transformers import pipeline
classifier = pipeline("text-classification", model="Camilla9000/imdb-sentiment-classifier")
print(classifier("This movie was amazing!"))
- Downloads last month
- 1
Inference Providers
NEW
This model is not currently available via any of the supported Inference Providers.