Update app.py

app.py

@@ -18,8 +18,7 @@ torch_dtype = torch.float16 if torch.cuda.is_available() else torch.float32
 model = AutoModelForCausalLM.from_pretrained(
     model_name,
     torch_dtype=torch_dtype,
-    trust_remote_code=True,
-    use_flash_attention=False  # Disable flash attention
+    trust_remote_code=True
 ).to(device)
 processor = AutoProcessor.from_pretrained(model_name, trust_remote_code=True)