Update README.md

ValueError: `.to` is not supported for `4-bit` or `8-bit` bitsandbytes models. Please use the model as it is, since the model has already been set to the correct devices and casted to the correct `dtype`.

README.md

@@ -339,7 +339,7 @@ model = AutoModelForVision2Seq.from_pretrained(
     "HuggingFaceM4/idefics2-8b",
 +    torch_dtype=torch.float16,    
 +    quantization_config=quantization_config,
-).to(DEVICE)
+)
 ```
 
 </details>