sudeshna5/Text_Classification

1---2license: mit3pipeline_tag: text-classification4---5 6# 🤖 DistilBERT Fine-Tuned on IMDb Movie Reviews for Sentiment Classification7 8[DistilBERT](https://huggingface.co/distilbert-base-uncased) model fine-tuned on the [IMDb dataset](https://huggingface.co/datasets/imdb) for binary sentiment classification (Positive/Negative).9 10---11 12## 🧠 Model Description13 14- **Architecture**: DistilBERT (lighter version of BERT)15- **Task**: Sentiment Analysis / Text Classification16- **Dataset**: IMDb movie reviews (binary sentiment: positive or negative)17- **Base Model**: `distilbert-base-uncased`18- **Fine-tuned using**: Hugging Face Transformers + Trainer API19 20---21 22## 📊 Training Details23 24- **Training Samples**: 5,000 (subset of IMDb train split)25- **Test Samples**: 1,000 (subset of IMDb test split)26- **Epochs**: 227- **Batch Size**: 828- **Optimizer**: AdamW29- **Evaluation Metric**: Accuracy30 31---32 33## 🚀 How to Use34 35You can directly use this model for inference using `transformers` pipeline:36 37```python38from transformers import pipeline39 40classifier = pipeline("sentiment-analysis", model="your-username/distilbert-finetuned-imdb-sentiment")41 42print(classifier("This movie was absolutely amazing!"))43# Output: [{'label': 'POSITIVE', 'score': 0.99}]44