Update README.md

README.md

@@ -41,7 +41,7 @@ You can find the experiment on W&B at [this address](https://wandb.ai/dryanfurma
 
 <details>
 
-<summary>Setup</summary>
+### <summary>Setup</summary>
 
 ```python
 !pip install -qU transformers accelerate bitsandbytes
@@ -82,10 +82,13 @@ pipeline = transformers.pipeline(
 
 </details>
 
-Run
+### Run
 
 ```python
-messages = [{"role": "user", "content": "What is a large language model?"}]
+messages = [
+    {"role": "system", "content": "You are a helpful assistant."},
+    {"role": "user", "content": "What is a large language model?"},
+]
 prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
 print("***Prompt:\n", prompt)
 
@@ -93,6 +96,6 @@ outputs = pipeline(prompt, max_new_tokens=256, do_sample=True, temperature=0.7,
 print("***Generation:\n", outputs[0]["generated_text"])
 ```
 
-Output
+### Output
 
 coming