Update app.py

app.py

@@ -15,8 +15,8 @@ device = "cuda" if torch.cuda.is_available() else "cpu"
 
 torch.set_grad_enabled(False)
 vlm_pipe = ModularPipeline.from_pretrained("briaai/FIBO-VLM-prompt-to-JSON", trust_remote_code=True).to(device)
-pipe = BriaFiboPipeline.from_pretrained("briaai/FIBO", trust_remote_code=True, dtype=dtype).to(device)
-
+pipe = BriaFiboPipeline.from_pretrained("briaai/FIBO", trust_remote_code=True, torch_dtype=dtype).to(device)
+pipe.enable_model_cpu_offload()
 
 @spaces.GPU(duration=300)
 def infer(