Update README.md

README.md

@@ -59,7 +59,7 @@ output = model.generate(**inputs, streamer=streamer, use_cache=True, max_new_tok
 output_text = tokenizer.decode(output[0], skip_prompt=True, skip_special_tokens=True)
 ```
 
-Our model can handle >10k input tokens thanks to the rope_scaling option.
+**Our model can handle >10k input tokens thanks to the `rope_scaling` option.**
 
 ## Hardware and Software