Update README.md

README.md

@@ -58,7 +58,7 @@ Its lightweight architecture enables fast, large-scale extraction of text that c
 
 ## Class token mapping
 
-Because this is a classification model built off the [**Qwen3-0.6B**](https://huggingface.co/Qwen/Qwen3-0.6B), we mapped the `forward-looking` and `not-forward-looking` classes onto tokens. This is the mapping we chose.
+Because this is a classification model built off the [**Qwen3-0.6B**](https://huggingface.co/Qwen/Qwen3-0.6B), we mapped the `forward` and `not-forward` classes onto tokens. This is the mapping we chose.
 
 ```python
 {