Update app.py

app.py

@@ -14,28 +14,23 @@ model = AutoModelForCausalLM.from_pretrained("meta-llama/Llama-3.2-1B")
 # Load the processor
 processor = AutoProcessor.from_pretrained(model_id)
 
-# Define an image URL
-url = "https://huggingface.co/datasets/huggingface/documentation-images/resolve/0052a70beed5bf71b92610a43a52df6d286cd5f3/diffusers/rabbit.jpg"
 
-# Fetch the image using requests
-image = Image.open(requests.get(url, stream=True).raw)
-
-# Define the messages in a format the model understands (adjust as needed)
-messages = [
-    {"role": "user", "content": [
-        {"type": "image"},  # This indicates that the input contains an image
-        {"type": "text", "text": "Can you please describe this image in one sentence?"}
-    ]}
-]
-
-# Generate input text with the processor
-input_text = processor.apply_chat_template(messages, add_generation_prompt=True)
-
-# Process the image and input text, prepare them for the model
-inputs = processor(image, input_text, return_tensors="pt").to(model.device)
-
-# Run the model to generate a response
-output = model.generate(**inputs, max_new_tokens=70)
-
-# Decode and print the output
-print(processor.decode(output[0][inputs["input_ids"].shape[-1]:]))
+# Define the function to generate text based on input prompt
+def generate_text(prompt):
+    if llm_pipeline is None:
+        return "Error: Model not loaded."
+    result = llm_pipeline(prompt, max_length=100, num_return_sequences=1)
+    return result[0]['generated_text']
+
+# Create the Gradio interface
+interface = gr.Interface(
+    fn=generate_text,
+    inputs=gr.Textbox(lines=7, label="Input Prompt"),
+    outputs="text",
+    title="Large Language Model Text Generation",
+    description="Enter a prompt to generate text using a large language model."
+)
+
+print("Launching the Gradio interface...")
+# Launch the interface
+interface.launch()