Update README.md

README.md

@@ -27,7 +27,7 @@ The training dataset was a private collection of around 2000 jokes. This model h
 
 See the example in the inference widget or How to use section for what constitues a narrative-style joke.
 
-For a more accurate model (2.4% more) that is slower at inference, see the [Roberta model](Reggie/muppet-roberta-base-joke_detector). For a still more accurate model (2.9% more) that is much slower at inference, see the [Deberta-v3 model](https://huggingface.co/Reggie/DeBERTa-v3-base-joke_detector).
+For a more accurate model (2.4% more) that is slower at inference, see the [Roberta model](https://huggingface.co/Reggie/muppet-roberta-base-joke_detector). For a still more accurate model (2.9% more) that is much slower at inference, see the [Deberta-v3 model](https://huggingface.co/Reggie/DeBERTa-v3-base-joke_detector).
 
 
 ### Install these first