Update README.md

README.md

@@ -13,5 +13,5 @@ This is a quantized GGUF version of Microsoft Phi-2 to 4_0, 8_0 bits and the con
 
 (link to the original model : https://huggingface.co/microsoft/phi-2)
 
-*Disclamer* : It won't work unless you use this fork with those modofication (https://github.com/mrgraycode/llama.cpp/commit/12cc80cb8975aea3bc9f39d3c9b84f7001ab94c5#diff-150dc86746a90bad4fc2c3334aeb9b5887b3adad3cc1459446717638605348efR6239) of llamacpp : https://github.com/mrgraycode/llama.cpp as the model's architecture is different.
+*Disclamer* : make sure to have the latest version of llama.cpp after commit b9e74f9bca5fdf7d0a22ed25e7a9626335fdfa48