Update README.md

README.md

@@ -125,8 +125,8 @@ text = tokenizer.apply_chat_template(
 
 SmolLM3 supports tool calling!
 Just pass your list of tools:
-- either under the argument `xml_tools` for standard tool-calling: these tools will be called as JSON blobs within XML tags, like `<tool_call>{"name": "get_weather", "arguments": {"city": "Copenhagen"}}</tool_call>`
-- or under `python_tools`: then the model will call these tools like python functions in a `<code>` snippet, like `<code>get_weather(city="Copenhagen")</code>`
+- Under the argument `xml_tools` for standard tool-calling: these tools will be called as JSON blobs within XML tags, like `<tool_call>{"name": "get_weather", "arguments": {"city": "Copenhagen"}}</tool_call>`
+- Or under `python_tools`: then the model will call tools like python functions in a `<code>` snippet, like `<code>get_weather(city="Copenhagen")</code>`
 
 ```python
 from transformers import AutoModelForCausalLM, AutoTokenizer