diff --git a/README.md b/README.md
index cade609..b8cc9a9 100644
--- a/README.md
+++ b/README.md
@@ -207,7 +207,7 @@ For me, with 7Gb for 3070ti, for 7B model, this works at the same speed as pure
 python hf-inference-cuda-example.py
 ```
 
-### "How to fine-tune LLaMA for Stable Diffusion prompting" example
+### How to fine-tune LLaMA for Stable Diffusion prompting
 
 Modify hf-training-example.py, also feel free to use more or less lines of SD prompts examples in csv file: