Fix dtype processing in README example (#5)

- Fix dtype processing in README example (5e12bdc378a11643e58065dada60fce07beee680)


Co-authored-by: Orr Zohar <[email protected]>

README.md

@@ -173,7 +173,7 @@ inputs = processor.apply_chat_template(
     tokenize=True,
     return_dict=True,
     return_tensors="pt",
-).to(model.device)
+).to(model.device, dtype=torch.bfloat16)
 
 generated_ids = model.generate(**inputs, do_sample=False, max_new_tokens=64)
 generated_texts = processor.batch_decode(