fix: readme llama.cpp link

README.md

@@ -19,7 +19,7 @@ _Llama.cpp imatrix quantization of deepseek-ai/DeepSeek-V2-Lite-Chat_
 
 Original Model: [deepseek-ai/DeepSeek-V2-Lite-Chat](https://huggingface.co/deepseek-ai/DeepSeek-V2-Lite-Chat)  
 Original dtype: `BF16` (`bfloat16`)  
-Quantized by: llama.cpp [https://github.com/fairydreaming/llama.cpp/tree/deepseek-v2](https://github.com/ggerganov/llama.cpp/releases/tag/https://github.com/fairydreaming/llama.cpp/tree/deepseek-v2)  
+Quantized by: llama.cpp fork [PR 7519](https://github.com/ggerganov/llama.cpp/pull/7519)  
 IMatrix dataset: [here](https://gist.githubusercontent.com/legraphista/d6d93f1a254bcfc58e0af3777eaec41e/raw/d380e7002cea4a51c33fffd47db851942754e7cc/imatrix.calibration.medium.raw)  
 
 ## Files