added ", add_generation_prompt=True"

README.md

@@ -115,7 +115,7 @@ and then apply the chat template to get a formatted prompt:
 ```
 tokenizer = AutoTokenizer.from_pretrained('Trelis/Meta-Llama-3-8B-Instruct-function-calling', trust_remote_code=True)
 
-prompt = tokenizer.apply_chat_template(prompt, tokenize=False)
+prompt = tokenizer.apply_chat_template(prompt, tokenize=False, add_generation_prompt=True)
 ```
 If you are using a gated model, you need to first run:
 ```