J'ai essayé Granite.

<|start_of_role|>user<|end_of_role|>Please list one IBM Research laboratory located in the United States. You should only output its name and location.<|end_of_text|>
<|start_of_role|>assistant<|end_of_role|>1. IBM Research - Austin, Texas<|end_of_text|>

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

device = "auto"
model_path = "ibm-granite/granite-3.0-8b-instruct"
tokenizer = AutoTokenizer.from_pretrained(model_path)
model = AutoModelForCausalLM.from_pretrained(model_path, device_map=device)
model.eval()

chat = [
    { "content": "Please list one IBM Research laboratory located in the United States. You should only output its name and location." },
]
chat = tokenizer.apply_chat_template(chat, tokenize=False, add_generation_prompt=True)

input_tokens = tokenizer(chat, add_special_tokens=False, return_tensors="pt").to("cuda")
output = model.generate(**input_tokens, max_new_tokens=100)
generated_text = tokenizer.decode(output[0][input_tokens["input_ids"].shape[1]:], skip_special_tokens=True)
print(generated_text)

1. IBM Almaden Research Center - San Jose, California

import json

def get_current_weather(location: str) -> dict:
    """
    Retrieves current weather information for the specified location (default: San Francisco).
    Args:
        location (str): Name of the city to retrieve weather data for.
    Returns:
        dict: Dictionary containing weather information (temperature, description, humidity).
    """
    print(f"Getting current weather for {location}")

    try:
        weather_description = "sample"
        temperature = "20.0"
        humidity = "80.0"

        return {
            "description": weather_description,
            "temperature": temperature,
            "humidity": humidity
        }
    except Exception as e:
        print(f"Error fetching weather data: {e}")
        return {"weather": "NA"}

functions = [
    {
        "name": "get_current_weather",
        "description": "Get the current weather",
        "parameters": {
            "type": "object",
            "properties": {
                "location": {
                    "type": "string",
                    "description": "The city and country code, e.g. San Francisco, US",
                }
            },
            "required": ["location"],
        },
    },
]
query = "What's the weather like in Boston?"
payload = {
    "functions_str": [json.dumps(x) for x in functions]
}
chat = [
    {"role":"system","content": f"You are a helpful assistant with access to the following function calls. Your task is to produce a sequence of function calls necessary to generate response to the user utterance. Use the following function calls as required.{payload}"},
    {"role": "user", "content": query }
]

instruction_1 = tokenizer.apply_chat_template(chat, tokenize=False, add_generation_prompt=True)
input_tokens = tokenizer(instruction_1, return_tensors="pt").to("cuda")
output = model.generate(**input_tokens, max_new_tokens=1024)
generated_text = tokenizer.decode(output[0][input_tokens["input_ids"].shape[1]:], skip_special_tokens=True)
print(generated_text)

{'name': 'get_current_weather', 'arguments': {'location': 'Boston'}}

prompt = """You are a conversational AI assistant that deepens interactions by alternating between responses and inner thoughts.
<Constraints>
* Record spoken responses after the [UTTERANCE] tag and inner thoughts after the [THINK] tag.
* Use [UTTERANCE] as a start marker to begin outputting an utterance.
* After [THINK], describe your internal reasoning or strategy for the next response. This may include insights on the user's reaction, adjustments to improve interaction, or further goals to deepen the conversation.
* Important: **Use [UTTERANCE] and [THINK] as a start signal without needing a closing tag.**
</Constraints>

Follow these instructions, alternating between [UTTERANCE] and [THINK] formats for responses.
<output example>
example1:
  [UTTERANCE]Hello! How can I assist you today?[THINK]I’ll start with a neutral tone to understand their needs. Preparing to offer specific suggestions based on their response.[UTTERANCE]Thank you! In that case, I have a few methods I can suggest![THINK]Since I now know what they’re looking for, I'll move on to specific suggestions, maintaining a friendly and approachable tone.
...
</output example>

Please respond to the following user_input.
<user_input>
Hello! What can you do?
</user_input>
"""

chat = [
    { "role": "user", "content": prompt },
]
chat = tokenizer.apply_chat_template(chat, tokenize=False, add_generation_prompt=True)

input_tokens = tokenizer(chat, return_tensors="pt").to("cuda")
output = model.generate(**input_tokens, max_new_tokens=1024)
generated_text = tokenizer.decode(output[0][input_tokens["input_ids"].shape[1]:], skip_special_tokens=True)
print(generated_text)

[UTTERANCE]Hello! I'm here to provide information, answer questions, and assist with various tasks. I can help with a wide range of topics, from general knowledge to specific queries. How can I assist you today?
[THINK]I've introduced my capabilities and offered assistance, setting the stage for the user to share their needs or ask questions.