app.py

import gradio as gr
import torch
from transformers import AutoModelForSequenceClassification, AutoTokenizer

# Load model and tokenizer
model_name = "distilbert-base-uncased-finetuned-sst-2-english"
model = AutoModelForSequenceClassification.from_pretrained(model_name)
tokenizer = AutoTokenizer.from_pretrained(model_name)

# Function to classify text (sentiment analysis)
def analyze_sentiment(text):
    inputs = tokenizer(text, return_tensors='pt')
    outputs = model(**inputs)
    prediction = torch.argmax(outputs.logits)
    # Map prediction to sentiment (0 == Negative, 1 == Positive)
    sentiment = "Positive" if prediction.item() == 1 else "Negative"
    return sentiment

# Create Gradio interface
demo = gr.Interface(
    fn=analyze_sentiment,
    inputs="text",
    outputs="text",
    title="Sentiment Analysis with DistilBERT",
    description="Enter text to analyze its sentiment (Positive/Negative)",
)

# Launch the interface
if __name__ == "__main__":
    demo.launch()