Update app.py

app.py

@@ -1,5 +1,5 @@
 import gradio as gr
-from transformers import AutoProcessor, AutoModelForVision2Seq, AutoModelForImageTextToText, TextIteratorStreamer
+from transformers import AutoProcessor, AutoModelForVision2Seq, TextIteratorStreamer
 from threading import Thread
 import re
 import time
@@ -7,12 +7,10 @@ from PIL import Image
 import torch
 import spaces
 
-# Load processor and model
-processor = AutoProcessor.from_pretrained("HuggingFaceTB/SmolVLM2-2.2B-Instruct")
-model = AutoModelForImageTextToText.from_pretrained(
-    "HuggingFaceTB/SmolVLM2-2.2B-Instruct", 
-    torch_dtype=torch.bfloat16,
-).to("cuda")
+processor = AutoProcessor.from_pretrained("HuggingFaceTB/SmolVLM-Instruct")
+model = AutoModelForVision2Seq.from_pretrained("HuggingFaceTB/SmolVLM-Instruct", 
+        torch_dtype=torch.bfloat16,
+        ).to("cuda")
 
 @spaces.GPU
 def model_inference(
@@ -80,8 +78,7 @@ def model_inference(
 # Define the ChatInterface without examples.
 demo = gr.ChatInterface(
     fn=model_inference,
-    title="SmolVLM: Small yet Mighty 💫",
-    description="Play with [HuggingFaceTB/SmolVLM-Instruct](https://huggingface.co/HuggingFaceTB/SmolVLM-Instruct) in this demo. To get started, upload an image and text.",
+    description="# **SmolVLM Video Infer**",
     textbox=gr.MultimodalTextbox(label="Query Input", file_types=["image"], file_count="multiple"),
     stop_btn="Stop Generation",
     multimodal=True,