Update app.py

app.py

@@ -1,5 +1,5 @@
 import gradio as gr
-from transformers import AutoProcessor, AutoModelForVision2Seq, TextIteratorStreamer
+from transformers import AutoProcessor, AutoModelForImageTextToText, TextIteratorStreamer
 from threading import Thread
 import re
 import time
@@ -11,7 +11,7 @@ subprocess.run('pip install flash-attn --no-build-isolation', env={'FLASH_ATTENT
 from io import BytesIO
 
 processor = AutoProcessor.from_pretrained("HuggingFaceTB/SmolVLM2-2.2B-Instruct")
-model = AutoModelForVision2Seq.from_pretrained("HuggingFaceTB/SmolVLM2-2.2B-Instruct", 
+model = AutoModelForImageTextToText.from_pretrained("HuggingFaceTB/SmolVLM2-2.2B-Instruct", 
                                                _attn_implementation="flash_attention_2",
                                                torch_dtype=torch.bfloat16).to("cuda:0")