Update README.md

README.md

@@ -26,6 +26,14 @@ GGML files are for CPU inference using [llama.cpp](https://github.com/ggerganov/
 * [4bit and 5bit GGML models for CPU inference](https://huggingface.co/TheBloke/h2ogpt-oasst1-512-30B-GGML).
 * [float16 HF format unquantised model for GPU inference and further conversions](https://huggingface.co/TheBloke/h2ogpt-oasst1-512-30B-HF)
 
+## THESE FILES REQUIRE LATEST LLAMA.CPP (May 12th 2023 - commit b9fd7ee)!
+
+llama.cpp recently made a breaking change to its quantisation methods.
+
+I have quantised the GGML files in this repo with the latest version. Therefore you will require llama.cpp compiled on May 12th or later (commit `b9fd7ee` or later) to use them.
+
+If you are currently unable to update llama.cpp, eg because you use a UI which hasn't updated yet, you can find GGML files for the previous version of llama.cpp in the `previous_llama` branch.
+
 ## Provided files
 | Name | Quant method | Bits | Size | RAM required | Use case |
 | ---- | ---- | ---- | ---- | ---- | ----- |