Update README.md

README.md

@@ -28,6 +28,6 @@ language:
 library_name: adapter-transformers
 ---
 
-Note: If you previously used the q4_0 model before April 26th, 2023, you are using an outdated model. I suggest redownloading for a better experience. Check https://github.com/ggerganov/llama.cpp#quantization for details on the different quantization types.
+Legacy is for llama.cpp setups older than https://github.com/ggerganov/llama.cpp/pull/1405, the regular is faster but does not work on old versions.
 
 This is a ggml version of vicuna 7b and 13b. This is the censored model, a similar 1.0 uncensored 13b model can be found at https://huggingface.co/eachadea/ggml-vicuna-13b-1.1.