Update README.md

diff --git a/README.md b/README.md
index e64517229b19d38e927a5b8c1b1421dc8fab2f54..2486d4dca3ee235e17e8fdb388540f15d82aef88 100644 (file)
--- a/README.md
+++ b/README.md
@@ -2,7 +2,7 @@
 
 Inference of [Facebook's LLaMA](https://github.com/facebookresearch/llama) model in pure C/C++
 
-**!!! IMPORTANT!!!**
+**!!! IMPORTANT !!!**
 
 Commit [007a8f6f459c6eb56678fdee4c09219ddb85b640](https://github.com/ggerganov/llama.cpp/commit/007a8f6f459c6eb56678fdee4c09219ddb85b640) added support for all LLaMA models, but introduced breaking changes. If you generated any models before that commit, you must regenerate them after updating to latest master.