[Python] llama3 responding only function call?

I am trying to make Llama3 Instruct able to use function call from tools , it does work but now it is answering only function call! if I ask something like who are you ? or what is apple device ? it answer back function call , I believe it is something in chat template ? or still something is missing in my code ?

from transformers import pipeline, AutoTokenizer, AutoModelForCausalLM
import os
import torch
from huggingface_hub import login

def get_current_temperature(location: str, unit: str) -> float:
"""
Get the current temperature at a location.

Args:
location: The location to get the temperature for, in the format "City, Country"
unit: The unit to return the temperature in. (choices: ["celsius", "fahrenheit"])
Returns:
The current temperature at the specified location in the specified units, as a float.
"""
return 22. # A real function should probably actually get the temperature!

def get_current_wind_speed(location: str) -> float:
"""
Get the current wind speed in km/h at a given location.

Args:
location: The location to get the temperature for, in the format "City, Country"
Returns:
The current wind speed at the given location in km/h, as a float.
"""
return 6. # A real function should probably actually get the wind speed!

tools = [get_current_temperature, get_current_wind_speed]


# Suppress MPS log message (optional)
os.environ["TORCH_MPS_DEVICE"] = "1"

checkpoint = "models/Llama-3.2-1B-Instruct"

messages = [
{"role": "user", "content": "Hey, who are you ?"}
]

tokenizer = AutoTokenizer.from_pretrained(checkpoint)
model = AutoModelForCausalLM.from_pretrained(checkpoint, torch_dtype=torch.bfloat16, device_map="cpu")

inputs = tokenizer.apply_chat_template(messages, tools=tools, add_generation_prompt=True, return_dict=True, return_tensors="pt")
inputs = {k: v.to(model.device) for k, v in inputs.items()}
out = model.generate(**inputs, max_new_tokens=128)
print(tokenizer.decode(out[0][len(inputs["input_ids"][0]):],skip_special_tokens=True))

Continue reading...