Update README.md

README.md

@@ -21,7 +21,7 @@ Some of the fineunting data is also targeted towards factual retrieval (only ans
 
 I am working on improving the model´s capabilities and will update the model if there is sufficient interest.
 
-A quantized GGML version for use with llama.cpp, kobold.cpp and other GUIs for CPU inference can be found [here](jphme/Llama-2-13b-chat-german-GGML).
+A quantized GGML version for use with llama.cpp, kobold.cpp and other GUIs for CPU inference can be found [here](https://huggingface.co/jphme/Llama-2-13b-chat-german-GGML).
 
 Please note the license of the base model, which is contained in the repo under LICENSE.TXT and see the original model card below for more information.