predict_text

app.py

@@ -55,11 +55,29 @@ def predict(image, text):
     response = processor.decode(outputs[0], skip_special_tokens=True)
     return response
 
+def predict_text(text):
+    # Prepare the input messages
+    messages = [{"role": "user", "content": [{"type": "text", "text": txt}]}]
+    
+    # Create the input text using the processor's chat template
+    input_text = processor.apply_chat_template(messages, add_generation_prompt=True)
+    
+    # Process the inputs and move to the appropriate device
+    # inputs = processor(image, input_text, return_tensors="pt").to(device)
+    inputs = processor(text=text, return_tensors="pt").to("cuda")
+    # Generate a response from the model
+    outputs = model.generate(**inputs, max_new_tokens=250)
+    
+    # Decode the output to return the final response
+    response = processor.decode(outputs[0], skip_special_tokens=True)
+    return response
+
+
 # Define the Gradio interface
 interface = gr.Interface(
-    fn=predict,
+    fn=predict_text,
     inputs=[
-        gr.Image(type="pil", label="Image Input"),  # Image input with label
+        # gr.Image(type="pil", label="Image Input"),  # Image input with label
         gr.Textbox(label="Text Input")  # Textbox input with label
     ],
     outputs=gr.Textbox(label="Generated Response"),  # Output with a more descriptive label