Update README.md

README.md

@@ -18,12 +18,11 @@ license: llama3.1
 
 ---
 
-GGUF quantized version using llama.cpp
+GGUF quantized version using [llama.cpp 5e2727f](https://github.com/ggerganov/llama.cpp/commit/5e2727fe0321c38d1664d26173c654fa1801dc5f)
 
-While it works, it still needs proper [RoPE support](https://github.com/ggerganov/llama.cpp/issues/8650)
-I will requant once merged
+Update 24/07 - requantized with [fixed tokenizer ](https://huggingface.co/meta-llama/Meta-Llama-3.1-8B-Instruct/discussions/28/files)
 
-Update 24/07 - requanted with [fixed tokenizer ](https://huggingface.co/meta-llama/Meta-Llama-3.1-8B-Instruct/discussions/28/files)
+Update 28/07 - requantized with the [RoPE fix](https://github.com/ggerganov/llama.cpp/pull/8676), it should now be fully supported. You need to run [llama.cpp 5e2727f](https://github.com/ggerganov/llama.cpp/commit/5e2727fe0321c38d1664d26173c654fa1801dc5f) or higher
 
 ## Model Information