Fixing an issue in README

README.md

@@ -31,7 +31,7 @@ python generate_openelm.py --model apple/OpenELM-450M --hf_access_token [HF_ACCE
 Alternatively, model-wise speculative generation with an [assistive model](https://huggingface.co/blog/assisted-generation) can be also tried by passing a smaller model model through the `assistant_model` argument, for example:
 ```
 python generate_openelm.py --model apple/OpenELM-450M --hf_access_token [HF_ACCESS_TOKEN] --prompt 'Once upon a time there was' --generate_kwargs repetition_penalty=1.2 --assistant_model [SMALLER_MODEL]
-
+```
 
 ## Main Results