prompt model change

app.py

@@ -1,3 +1,9 @@
+import asyncio
+try:
+    asyncio.get_event_loop()
+except RuntimeError:
+    asyncio.set_event_loop(asyncio.new_event_loop())
+
 import gradio as gr
 import torch
 from transformers import (
@@ -11,6 +17,7 @@ from transformers import (
 cls_model_name = "Aalaa/Fine_tuned_Vit_trash_classification"
 feature_extractor = AutoFeatureExtractor.from_pretrained(cls_model_name)
 cls_model = AutoModelForImageClassification.from_pretrained(cls_model_name)
+
 id2label = cls_model.config.id2label
 
 
@@ -20,9 +27,10 @@ def classify_image(image):
     with torch.no_grad():
         outputs = cls_model(**inputs)
 
-    probs = torch.nn.functional.softmax(outputs.logits, dim=-1)[0]
-    top3 = probs.topk(3).indices.tolist()
+    logits = outputs.logits
+    probs = torch.nn.functional.softmax(logits, dim=-1)[0]
 
+    top3 = probs.topk(3).indices.tolist()
     return {id2label[i]: float(probs[i]) for i in top3}
 
 
@@ -32,9 +40,7 @@ tiny_model = "TinyLlama/TinyLlama-1.1B-Chat-v1.0"
 tokenizer = AutoTokenizer.from_pretrained(tiny_model)
 chat_model = AutoModelForCausalLM.from_pretrained(
     tiny_model,
-    torch_dtype=torch.float32
-)
-
+    torch_dtype=torch.float32)
 
 def explain_recycling(label):
     prompt = f"""
@@ -64,25 +70,38 @@ Item: {label}
 
     return tokenizer.decode(outputs[0], skip_special_tokens=True)
 
-
 # ------------------ PIPELINE ------------------
 def full_pipeline(image):
-    preds = classify_image(image)
-    label = max(preds, key=preds.get)
-    explanation = explain_recycling(label)
-    return preds, explanation
+    predictions = classify_image(image)
+    top_label = max(predictions, key=predictions.get)
+    explanation = explain_recycling(top_label)
+    return predictions, explanation
 
 
 # ------------------ GRADIO UI ------------------
 with gr.Blocks() as demo:
-    gr.Markdown("## ♻️ Waste Classifier + TinyLlama Advisor")
+    gr.Markdown("<h1 style='text-align:center;'>♻️ AI Waste Classifier + Eco Advisor</h1>")
+
+    with gr.Row():
+        img_input = gr.Image(type="pil", label="Upload waste image")
+
+    cls_output = gr.Label(num_top_classes=3, label="Classifier Prediction")
 
-    img = gr.Image(type="pil")
-    preds = gr.Label(num_top_classes=3, label="Classifier")
-    advice = gr.Textbox(lines=6, label="Recycling Advice")
+    explain_output = gr.Textbox(
+        label="Detailed Recycling & Disposal Advice",
+        elem_id="explainbox",
+        lines=4
+    )
 
-    btn = gr.Button("Analyze")
+    analyze_btn = gr.Button("Analyze", variant="primary")
 
-    btn.click(full_pipeline, inputs=img, outputs=[preds, advice])
+    analyze_btn.click(
+        full_pipeline,
+        inputs=img_input,
+        outputs=[cls_output, explain_output]
+    )
 
-demo.launch()
+demo.launch(
+    theme=gr.themes.Soft(primary_hue="green"),
+    css="#explainbox {height: 330px; font-size: 15px;}"
+)