From 8a01f565ff78cc6c0c5a9fa402787a2f179f2d78 Mon Sep 17 00:00:00 2001
From: Georgi Gerganov <ggerganov@gmail.com>
Date: Fri, 10 Mar 2023 23:53:11 +0200
Subject: [PATCH] Update README.md

---
 README.md | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/README.md b/README.md
index f091909..8103cf2 100644
--- a/README.md
+++ b/README.md
@@ -2,6 +2,9 @@
 
 Inference of [Facebook's LLaMA](https://github.com/facebookresearch/llama) model in pure C/C++
 
+**TEMPORARY NOTICE:**
+If you observe garbage results, make sure to update to latest master. There was a bug and it was fixed here: https://github.com/ggerganov/llama.cpp/commit/70bc0b8b15b98dca23b28f0c8f5e34b27e424cda
+
 ## Description
 
 The main goal is to run the model using 4-bit quantization on a MacBook.