Update README.md

README.md

@@ -6,7 +6,7 @@ license: llama2
 
 ## Model description
 
-Sampling-based watermark distilled Llama 2 7B using the KTH \\(k=1\\) watermarking strategy in the paper [On the Learnability of Watermarks for Language Models](https://arxiv.org/abs/2312.04469).
+Sampling-based watermark distilled Llama 2 7B using the KTH \\(s=1\\) watermarking strategy in the paper [On the Learnability of Watermarks for Language Models](https://arxiv.org/abs/2312.04469).
 
 ### Training hyperparameters