Update README.md

README.md

@@ -6,6 +6,8 @@ GGUF [llama.cpp](https://github.com/ggerganov/llama.cpp) quantized version of:
 - Model creator: [Meta](https://huggingface.co/meta-llama)
 - [License](https://github.com/meta-llama/llama-models/blob/main/models/llama3_1/LICENSE)
 
+<span style="color: red">Update(24/07/27):</span> Latest fixes to use the full 128k context window are included in -ropefix versions. **Requirement** to run them and used version: [b3472](https://github.com/ggerganov/llama.cpp/releases/tag/b3472)
+
 <span style="color: red">Update:</span> Use the -imatrix versions (they use [imatrix](https://github.com/ggerganov/llama.cpp/discussions/5263#discussioncomment-8395384) and the **bpe-llama tokenizer** which should theoretically improve the output)
 
 ## Recommended Prompt Format (Llama3)