Update app.py

app.py

@@ -55,7 +55,7 @@ def process_image_and_text(image_pil, num_beams, temperature, seed):
         torch.manual_seed(seed) # Set random seed for reproducibility
 
         with torch.inference_mode():
-            generation = model.generate(**model_inputs, max_new_tokens=200, do_sample=False, num_beams=num_beams, temperature=temperature)
+            generation = model.generate(**model_inputs, max_new_tokens=200, do_sample=True, num_beams=num_beams, temperature=temperature)
             generation = generation[0][input_len:]
             decoded = processor.decode(generation, skip_special_tokens=True)
 
@@ -70,8 +70,8 @@ if __name__ == "__main__":
         fn=process_image_and_text,
         inputs=[
             gr.Image(type="pil", label="Upload an image"),
-            gr.Slider(minimum=1, maximum=10, step=1, value=1, label="Number of Beams"),
-            gr.Slider(minimum=0.1, maximum=2.0, step=0.1, value=1.0, label="Temperature"),
+            gr.Slider(minimum=1, maximum=10, step=1, value=10, label="Number of Beams"),
+            gr.Slider(minimum=0.1, maximum=2.0, step=0.1, value=1.5, label="Temperature"),
             gr.Number(label="Random Seed", value=0, precision=0),
         ],
         outputs=gr.Textbox(label="Generated Text"),