Update README.md

README.md

@@ -190,7 +190,7 @@ quantized_by: bartowski
 
 ## Llamacpp iMatrix Quantizations of Meta-Llama-3-8B-Instruct
 
-<b>Warning: This conversion is based on the merged Llama 3 support in llama.cpp (release b6710), and you will need to update your inference tool to be on at least version 6710 of llama.cpp, this will vary across tools</b>
+<b>Warning: This conversion is based on the merged Llama 3 support in llama.cpp (release b6710), and you will need to update your inference tool to be on at least version 6710 of llama.cpp, this will vary across tools. Until then, you can use the older style with <|eot_id|> special = false [here](https://huggingface.co/bartowski/Meta-Llama-3-8B-Instruct-GGUF-old)</b>
 
 Using <a href="https://github.com/ggerganov/llama.cpp/">llama.cpp</a> release <a href="https://github.com/ggerganov/llama.cpp/releases/tag/b2710">b2710</a> for quantization.