Update app.py

app.py

@@ -1,16 +1,16 @@
 import gradio as gr
+import spaces
 import torch
 from transformers import AutoTokenizer, AutoModelForSequenceClassification
 
-# Initialize device - force CPU usage
-device = "cpu"
+# Initialize device
+device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
 print(f"Using device: {device}")
 
 # Load model and tokenizer
 model_name = "tabularisai/robust-sentiment-analysis"
 tokenizer = AutoTokenizer.from_pretrained(model_name)
-model = AutoModelForSequenceClassification.from_pretrained(model_name)  # Remove .to(device)
-model.eval()  # Set model to evaluation mode
+model = AutoModelForSequenceClassification.from_pretrained(model_name).to(device)
 
 # Define sentiment mapping
 SENTIMENT_MAP = {
@@ -21,21 +21,22 @@ SENTIMENT_MAP = {
     4: "Very Positive"
 }
 
+@spaces.GPU
 def analyze_sentiment(text, show_probabilities=False):
     """
-    Analyzes the sentiment of the input text with preprocessing.
+    Analyzes the sentiment of the input text.
     """
     try:
         # Preprocess text - convert to lowercase
         text = text.lower()
         
         # Tokenize and prepare input
-        inputs = tokenizer(text, return_tensors="pt", truncation=True, padding=True, max_length=512)
+        inputs = tokenizer(text, return_tensors="pt", truncation=True, padding=True, max_length=512).to(device)
 
         with torch.no_grad():
             outputs = model(**inputs)
 
-        probabilities = torch.nn.functional.softmax(outputs.logits, dim=-1).numpy()[0]
+        probabilities = torch.nn.functional.softmax(outputs.logits, dim=-1).cpu().numpy()[0]
         predicted_class = probabilities.argmax()
         predicted_sentiment = SENTIMENT_MAP[predicted_class]
         confidence = probabilities[predicted_class]
@@ -49,8 +50,8 @@ def analyze_sentiment(text, show_probabilities=False):
             "Very Positive": "🤩"
         }
 
-        result = f"## {sentiment_emojis[predicted_sentiment]} Overall Sentiment: {predicted_sentiment}\n"
-        result += f"### Confidence: {confidence:.2%}\n\n"
+        result = f"**{sentiment_emojis[predicted_sentiment]} Overall Sentiment: {predicted_sentiment}**\n"
+        result += f"Confidence: {confidence:.2%}\n\n"
 
         if show_probabilities:
             result += "### Detailed Analysis:\n"
@@ -62,15 +63,12 @@ def analyze_sentiment(text, show_probabilities=False):
     except Exception as e:
         return f"An error occurred during sentiment analysis: {str(e)}"
 
-# Create Gradio interface using Blocks
+# Create Gradio interface using Blocks for better layout control
 with gr.Blocks(theme=gr.themes.Soft()) as demo:
+    gr.Markdown("# 🎭 Sentiment Analysis Wizard")
     gr.Markdown(
         """
-        # 🎭 Sentiment Analysis Wizard
-        
-        <div style='text-align: center; padding: 1rem; background: rgba(255, 255, 255, 0.5); border-radius: 1rem; margin: 1rem 0;'>
-            Discover the emotional tone behind any text with our advanced AI model! Let our wizard analyze your text and reveal its true sentiment.
-        </div>
+        Discover the emotional tone behind any text with our advanced AI model! This app uses a state-of-the-art language model to analyze the sentiment of your text, classifying it into one of five categories: **Very Negative**, **Negative**, **Neutral**, **Positive**, or **Very Positive**.
         """
     )
 
@@ -78,13 +76,12 @@ with gr.Blocks(theme=gr.themes.Soft()) as demo:
         with gr.Column(scale=2):
             input_text = gr.Textbox(
                 lines=10,
-                placeholder="Enter your text here to uncover its emotional essence...",
-                label="✍️ Input Text",
-                show_label=True
+                placeholder="Enter text for sentiment analysis...",
+                label="✍️ Input Text"
             )
             with gr.Row():
                 show_probs = gr.Checkbox(
-                    label="🎯 Show detailed probabilities",
+                    label="🎯 Show probabilities for each class",
                     value=False
                 )
                 analyze_button = gr.Button("✨ Analyze Sentiment", variant="primary")
@@ -92,7 +89,7 @@ with gr.Blocks(theme=gr.themes.Soft()) as demo:
         with gr.Column(scale=1):
             output = gr.Markdown(label="Result")
 
-    with gr.Accordion("📚 Example Texts", open=False):
+    with gr.Accordion("📚 Examples", open=False):
         examples = [
             ["I absolutely loved this movie! The acting was superb and the plot was engaging.", True],
             ["The service at this restaurant was terrible. I'll never go back.", False],
@@ -114,9 +111,8 @@ with gr.Blocks(theme=gr.themes.Soft()) as demo:
 
     gr.Markdown(
         """
-        <div style='text-align: center; padding: 1rem; margin-top: 2rem; font-size: 0.9em; color: #666;'>
-            Developed with ❤️ using Gradio and Transformers by Hugging Face
-        </div>
+        ---
+        **Developed with ❤️ using Gradio and Transformers by Hugging Face**
         """
     )