Upload app.py with huggingface_hub

app.py

@@ -0,0 +1,49 @@
+import gradio as gr
+from transformers import AutoTokenizer, AutoModelForSeq2SeqLM
+
+# Load model and tokenizer
+model_name = "usef310/flan-t5-small-sentiment"
+tokenizer = AutoTokenizer.from_pretrained(model_name)
+model = AutoModelForSeq2SeqLM.from_pretrained(model_name)
+
+def predict_sentiment(text):
+    '''Predict sentiment of input text'''
+    if not text.strip():
+        return "Please enter some text!"
+    
+    # Prepare input
+    inputs = tokenizer("sentiment: " + text, return_tensors="pt", max_length=256, truncation=True)
+    
+    # Generate prediction
+    outputs = model.generate(**inputs, max_length=8)
+    prediction = tokenizer.decode(outputs[0], skip_special_tokens=True)
+    
+    # Format output
+    sentiment = prediction.upper()
+    emoji = "😊" if "positive" in prediction.lower() else "😞"
+    
+    return f"{emoji} {sentiment}"
+
+# Create Gradio interface
+demo = gr.Interface(
+    fn=predict_sentiment,
+    inputs=gr.Textbox(
+        lines=5,
+        placeholder="Enter a movie review or any text...",
+        label="Text Input"
+    ),
+    outputs=gr.Textbox(label="Sentiment Prediction"),
+    title="🎬 FLAN-T5 Sentiment Analysis",
+    description="Fine-tuned FLAN-T5-Small for sentiment classification. Enter any text to get positive/negative prediction!",
+    examples=[
+        ["This movie was absolutely fantastic! I loved every minute of it."],
+        ["Terrible film. Complete waste of time and money."],
+        ["The acting was superb and the plot kept me engaged throughout."],
+        ["I didn't enjoy this movie at all. Very disappointing."],
+        ["An incredible masterpiece that everyone should watch!"]
+    ],
+    theme="soft"
+)
+
+if __name__ == "__main__":
+    demo.launch()