qwen3-4b-xlam-function-calling-60k-lora

from peft import PeftModel
from transformers import AutoModelForCausalLM, AutoTokenizer
import torch
import json

base_model_id = "Qwen/Qwen3-4B-Instruct-2507"
adapter_id = "prabhu-nithin/qwen3-4b-xlam-function-calling-60k-lora"

tokenizer = AutoTokenizer.from_pretrained(base_model_id)
base_model = AutoModelForCausalLM.from_pretrained(base_model_id, torch_dtype=torch.bfloat16, device_map="auto")
model = PeftModel.from_pretrained(base_model, adapter_id)

tool_definitions = [
    {
        "name": "get_weather",
        "description": "Get current weather information for a given city.",
        "parameters": {
            "type": "object",
            "properties": {
                "city": {"type": "string", "description": "The city name"},
                "unit": {"type": "string", "enum": ["celsius", "fahrenheit"], "default": "celsius"}
            },
            "required": ["city"]
        }
    }
]

system_prompt = f"""You are a helpful assistant.

# Tools

You may call one or more functions to assist with the user query.

You are provided with function signatures within <tools></tools> XML tags:
<tools>
{json.dumps(tool_definitions, indent=2)}
</tools>

For each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:
<tool_call>
{{"name": "<function-name>", "arguments": <args-json-object>}}
</tool_call>"""

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

text = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
inputs = tokenizer(text, return_tensors="pt").to(model.device)
outputs = model.generate(**inputs, max_new_tokens=512, temperature=0.7, top_p=0.8, top_k=20)
print(tokenizer.decode(outputs[0][inputs.input_ids.shape[1]:], skip_special_tokens=True))