Qwen3-VL-4B-tool-calling-ft

tools = [
    {
        "name": "get_weather",
        "description": "Get current weather for a location",
        "parameters": {
            "type": "object",
            "properties": {
                "location": {"type": "string", "description": "City name"},
                "unit": {"type": "string", "enum": ["celsius", "fahrenheit"]}
            },
            "required": ["location"]
        }
    }
]

messages = [
    {"role": "user", "content": "What's the weather like in Istanbul?"}
]

text = tokenizer.apply_chat_template(
    messages,
    tools=tools,
    tokenize=False,
    add_generation_prompt=True
)

inputs = tokenizer(text, return_tensors="pt").to(model.device)
outputs = model.generate(**inputs, max_new_tokens=256, temperature=0.1)
response = tokenizer.decode(outputs[0][inputs["input_ids"].shape[1]:], skip_special_tokens=True)
print(response)
# Expected: <tool_call>
# {"name": "get_weather", "arguments": {"location": "Istanbul", "unit": "celsius"}}
# </tool_call>

<tool_call>
{"name": "function_name", "arguments": {"param1": "value1"}}
</tool_call>