import argparse

import torch
from openmind import is_torch_npu_available
from openmind import AutoTokenizer, AutoModelForCausalLM


def parse_args():
    parser = argparse.ArgumentParser()
    parser.add_argument(
        "--model_name_or_path",
        type=str,
        help="Path to model",
        default=None,
    )

    args = parser.parse_args()
    return args


def main():
    args = parse_args()
    if args.model_name_or_path:
        model_path = args.model_name_or_path
    else:
        model_path = "../"

    if is_torch_npu_available():
        device = "npu:0"
    else:
        device = "cpu"

    tokenizer = AutoTokenizer.from_pretrained("Rose/SmolLM2-1.7B-Instruct")
    model = AutoModelForCausalLM.from_pretrained("Rose/SmolLM2-1.7B-Instruct")

    input_ids = tokenizer("Gra", return_tensors='pt').to(model.device)["input_ids"]
    output = model.generate(input_ids, max_new_tokens=48, do_sample=True, temperature=0.7)
    print(tokenizer.decode(output[0]))


if __name__ == "__main__":
    main()

pip install transformers

from transformers import AutoModelForCausalLM, AutoTokenizer
checkpoint = "HuggingFaceTB/SmolLM2-1.7B-Instruct"

device = "cuda" # for GPU usage or "cpu" for CPU usage
tokenizer = AutoTokenizer.from_pretrained(checkpoint)
# for multiple GPUs install accelerate and do `model = AutoModelForCausalLM.from_pretrained(checkpoint, device_map="auto")`
model = AutoModelForCausalLM.from_pretrained(checkpoint).to(device)

messages = [{"role": "user", "content": "What is the capital of France."}]
input_text=tokenizer.apply_chat_template(messages, tokenize=False)
inputs = tokenizer.encode(input_text, return_tensors="pt").to(device)
outputs = model.generate(inputs, max_new_tokens=50, temperature=0.2, top_p=0.9, do_sample=True)
print(tokenizer.decode(outputs[0]))

pip install trl
trl chat --model_name_or_path HuggingFaceTB/SmolLM2-1.7B-Instruct --device cpu

system_prompt_rewrite = "You are an AI writing assistant. Your task is to rewrite the user's email to make it more professional and approachable while maintaining its main points and key message. Do not return any text other than the rewritten message."
user_prompt_rewrite = "Rewrite the message below to make it more friendly and approachable while maintaining its main points and key message. Do not add any new information or return any text other than the rewritten message\nThe message:"
messages = [{"role": "system", "content": system_prompt_rewrite}, {"role": "user", "content":f"{user_prompt_rewrite} The CI is failing after your last commit!"}]
input_text=tokenizer.apply_chat_template(messages, tokenize=False)
inputs = tokenizer.encode(input_text, return_tensors="pt").to(device)
outputs = model.generate(inputs, max_new_tokens=50, temperature=0.2, top_p=0.9, do_sample=True)
print(tokenizer.decode(outputs[0]))

Hey there! I noticed that the CI isn't passing after your latest commit. Could you take a look and let me know what's going on? Thanks so much for your help!

system_prompt_summarize = "Provide a concise, objective summary of the input text in up to three sentences, focusing on key actions and intentions without using second or third person pronouns."
messages = [{"role": "system", "content": system_prompt_summarize}, {"role": "user", "content": INSERT_LONG_EMAIL}]
input_text=tokenizer.apply_chat_template(messages, tokenize=False)
inputs = tokenizer.encode(input_text, return_tensors="pt").to(device)
outputs = model.generate(inputs, max_new_tokens=50, temperature=0.2, top_p=0.9, do_sample=True)
print(tokenizer.decode(outputs[0]))

import json
import re
from typing import Optional

from jinja2 import Template
import torch 
from transformers import AutoModelForCausalLM, AutoTokenizer
from transformers.utils import get_json_schema


system_prompt = Template("""You are an expert in composing functions. You are given a question and a set of possible functions. 
Based on the question, you will need to make one or more function/tool calls to achieve the purpose. 
If none of the functions can be used, point it out and refuse to answer. 
If the given question lacks the parameters required by the function, also point it out.

You have access to the following tools:
<tools>{{ tools }}</tools>

The output MUST strictly adhere to the following format, and NO other text MUST be included.
The example format is as follows. Please make sure the parameter type is correct. If no function call is needed, please make the tool calls an empty list '[]'.
<tool_call>[
{"name": "func_name1", "arguments": {"argument1": "value1", "argument2": "value2"}},
... (more tool calls as required)
]</tool_call>""")


def prepare_messages(
    query: str,
    tools: Optional[dict[str, any]] = None,
    history: Optional[list[dict[str, str]]] = None
) -> list[dict[str, str]]:
    """Prepare the system and user messages for the given query and tools.
    
    Args:
        query: The query to be answered.
        tools: The tools available to the user. Defaults to None, in which case if a
            list without content will be passed to the model.
        history: Exchange of messages, including the system_prompt from
            the first query. Defaults to None, the first message in a conversation.
    """
    if tools is None:
        tools = []
    if history:
        messages = history.copy()
        messages.append({"role": "user", "content": query})
    else:
        messages = [
            {"role": "system", "content": system_prompt.render(tools=json.dumps(tools))},
            {"role": "user", "content": query}
        ]
    return messages


def parse_response(text: str) -> str | dict[str, any]:
    """Parses a response from the model, returning either the
    parsed list with the tool calls parsed, or the
    model thought or response if couldn't generate one.

    Args:
        text: Response from the model.
    """
    pattern = r"<tool_call>(.*?)</tool_call>"
    matches = re.findall(pattern, text, re.DOTALL)
    if matches:
        return json.loads(matches[0])
    return text


model_name_smollm = "HuggingFaceTB/SmolLM2-1.7B-Instruct"
model = AutoModelForCausalLM.from_pretrained(model_name_smollm, device_map="auto", torch_dtype="auto", trust_remote_code=True)
tokenizer = AutoTokenizer.from_pretrained(model_name_smollm)

from datetime import datetime
import random

def get_current_time() -> str:
    """Returns the current time in 24-hour format.

    Returns:
        str: Current time in HH:MM:SS format.
    """
    return datetime.now().strftime("%H:%M:%S")


def get_random_number_between(min: int, max: int) -> int:
    """
    Gets a random number between min and max.

    Args:
        min: The minimum number.
        max: The maximum number.

    Returns:
        A random number between min and max.
    """
    return random.randint(min, max)


tools = [get_json_schema(get_random_number_between), get_json_schema(get_current_time)]

toolbox = {"get_random_number_between": get_random_number_between, "get_current_time": get_current_time}

query = "Give me a number between 1 and 300"

messages = prepare_messages(query, tools=tools)

inputs = tokenizer.apply_chat_template(messages, add_generation_prompt=True, return_tensors="pt").to(model.device)
outputs = model.generate(inputs, max_new_tokens=512, do_sample=False, num_return_sequences=1, eos_token_id=tokenizer.eos_token_id)
result = tokenizer.decode(outputs[0][len(inputs[0]):], skip_special_tokens=True)

tool_calls = parse_response(result)
# [{'name': 'get_random_number_between', 'arguments': {'min': 1, 'max': 300}}

# Get tool responses
tool_responses = [toolbox.get(tc["name"])(*tc["arguments"].values()) for tc in tool_calls]
# [63]

# For the second turn, rebuild the history of messages:
history = messages.copy()
# Add the "parsed response"
history.append({"role": "assistant", "content": result})
query = "Can you give me the hour?"
history.append({"role": "user", "content": query})

inputs = tokenizer.apply_chat_template(history, add_generation_prompt=True, return_tensors="pt").to(model.device)
outputs = model.generate(inputs, max_new_tokens=512, do_sample=False, num_return_sequences=1, eos_token_id=tokenizer.eos_token_id)
result = tokenizer.decode(outputs[0][len(inputs[0]):], skip_special_tokens=True)

tool_calls = parse_response(result)
tool_responses = [toolbox.get(tc["name"])(*tc["arguments"].values()) for tc in tool_calls]
# ['07:57:25']

@misc{allal2024SmolLM2,
      title={SmolLM2 - with great data, comes great performance}, 
      author={Loubna Ben Allal and Anton Lozhkov and Elie Bakouch and Gabriel Martín Blázquez and Lewis Tunstall and Agustín Piqueres and Andres Marafioti and Cyril Zakka and Leandro von Werra and Thomas Wolf},
      year={2024},
}