Update README.md with recommended way to move tokenized to GPU

[[Bug] Fix device mismatch in Ministral3 RoPE forward pass #43350](https://github.com/huggingface/transformers/issues/43350)

README.md

@@ -502,8 +502,7 @@ messages = [
 
 tokenized = tokenizer.apply_chat_template(messages, return_tensors="pt", return_dict=True)
 
-tokenized["input_ids"] = tokenized["input_ids"].to(device="cuda")
-tokenized["pixel_values"] = tokenized["pixel_values"].to(dtype=torch.bfloat16, device="cuda")
+tokenized = tokenized.to(device="cuda")
 image_sizes = [tokenized["pixel_values"].shape[-2:]]
 
 output = model.generate(