Update app.py

app.py

@@ -12,12 +12,12 @@ import spaces
 import torch
 from loguru import logger
 from PIL import Image
-from transformers import AutoProcessor, Gemma3ForConditionalGeneration, TextIteratorStreamer
+from transformers import AutoProcessor, AutoModelForImageTextToText, TextIteratorStreamer
 
 model_id = os.getenv("MODEL_ID", "google/medgemma-4b-it")
-processor = AutoProcessor.from_pretrained(model_id, padding_side="left")
-model = Gemma3ForConditionalGeneration.from_pretrained(
-    model_id, device_map="auto", torch_dtype=torch.bfloat16, attn_implementation="eager"
+processor = AutoProcessor.from_pretrained(model_id)
+model = AutoModelForImageTextToText.from_pretrained(
+    model_id, device_map="auto", torch_dtype=torch.bfloat16
 )
 
 MAX_NUM_IMAGES = int(os.getenv("MAX_NUM_IMAGES", "5"))
@@ -214,7 +214,7 @@ demo = gr.ChatInterface(
     textbox=gr.MultimodalTextbox(file_types=["image", ".mp4"], file_count="multiple", autofocus=True),
     multimodal=True,
     additional_inputs=[
-        gr.Textbox(label="System Prompt", value=""),
+        gr.Textbox(label="System Prompt", value="You are a helpful medical expert."),
         gr.Slider(label="Max New Tokens", minimum=100, maximum=8192, step=10, value=2048),
     ],
     stop_btn=False,