Update app.py

app.py

@@ -1,14 +1,12 @@
 import gradio as gr
-from transformers import AutoProcessor, AutoModelForImageTextToText
+from transformers import AutoTokenizer, AutoModelForImageTextToText
 import torch
 
+tokenizer = AutoTokenizer.from_pretrained("HuggingFaceTB/SmolVLM2-2.2B-Instruct")
+model = AutoModelForImageTextToText.from_pretrained("HuggingFaceTB/SmolVLM2-2.2B-Instruct")
+
 model_path = "HuggingFaceTB/SmolVLM2-2.2B-Instruct"
 processor = AutoProcessor.from_pretrained(model_path)
-model = AutoModelForImageTextToText.from_pretrained(
-    model_path,
-    torch_dtype=torch.bfloat16,
-    _attn_implementation="flash_attention_2"
-).to("cuda")
 
 def launch(input):
     out = model.generate(**input)