diff --git a/docs/inference.md b/docs/inference.md
index 144431bb2c6e22a6541bd0bd2ab1e97815137ce0..475251aee3e773e7c25792df72bef11755c084fd 100644
--- a/docs/inference.md
+++ b/docs/inference.md
@@ -31,7 +31,7 @@ inference/samsum_prompt.txt
 The inference folder also includes a chat completion example, that adds built-in safety features in fine-tuned models to the prompt tokens. To run the example:
 
 ```bash
-python chat_completion.py --model_name "PATH/TO/MODEL/7B/" --prompt_file chats.json  --quantization --use_auditnlg
+python inference/chat_completion.py --model_name "PATH/TO/MODEL/7B/" --prompt_file chats.json  --quantization --use_auditnlg
 
 ```