>>> from transformers import AutoTokenizer
>>> tokenizer = AutoTokenizer.from_pretrained("facebook/blenderbot-400M-distill")

>>> chat = [
...    {"role": "user", "content": "Hello, how are you?"},
...    {"role": "assistant", "content": "I'm doing great. How can I help you today?"},
...    {"role": "user", "content": "I'd like to show off how chat templating works!"},
... ]

>>> tokenizer.apply_chat_template(chat, tokenize=False)
" Hello, how are you?  I'm doing great. How can I help you today?   I'd like to show off how chat templating works!</s>"

>>> from transformers import AutoTokenizer
>>> tokenizer = AutoTokenizer.from_pretrained("mistralai/Mistral-7B-Instruct-v0.1")

>>> chat = [
...   {"role": "user", "content": "Hello, how are you?"},
...   {"role": "assistant", "content": "I'm doing great. How can I help you today?"},
...   {"role": "user", "content": "I'd like to show off how chat templating works!"},
... ]

>>> tokenizer.apply_chat_template(chat, tokenize=False)
"<s>[INST] Hello, how are you? [/INST]I'm doing great. How can I help you today?</s> [INST] I'd like to show off how chat templating works! [/INST]"

from transformers import AutoModelForCausalLM, AutoTokenizer

checkpoint = "HuggingFaceH4/zephyr-7b-beta"
tokenizer = AutoTokenizer.from_pretrained(checkpoint)
model = AutoModelForCausalLM.from_pretrained(checkpoint)   # 여기서 bfloat16 사용 및/또는 GPU로 이동할 수 있습니다.


messages = [
    {
        "role": "system",
        "content": "You are a friendly chatbot who always responds in the style of a pirate",
    },
    {"role": "user", "content": "How many helicopters can a human eat in one sitting?"},
 ]
tokenized_chat = tokenizer.apply_chat_template(messages, tokenize=True, add_generation_prompt=True, return_tensors="pt")
print(tokenizer.decode(tokenized_chat[0]))

<|system|>
You are a friendly chatbot who always responds in the style of a pirate</s> 
<|user|>
How many helicopters can a human eat in one sitting?</s> 
<|assistant|>

outputs = model.generate(tokenized_chat, max_new_tokens=128) 
print(tokenizer.decode(outputs[0]))

<|system|>
You are a friendly chatbot who always responds in the style of a pirate</s> 
<|user|>
How many helicopters can a human eat in one sitting?</s> 
<|assistant|>
Matey, I'm afraid I must inform ye that humans cannot eat helicopters. Helicopters are not food, they are flying machines. Food is meant to be eaten, like a hearty plate o' grog, a savory bowl o' stew, or a delicious loaf o' bread. But helicopters, they be for transportin' and movin' around, not for eatin'. So, I'd say none, me hearties. None at all.

from transformers import pipeline

pipe = pipeline("text-generation", "HuggingFaceH4/zephyr-7b-beta")
messages = [
    {
        "role": "system",
        "content": "You are a friendly chatbot who always responds in the style of a pirate",
    },
    {"role": "user", "content": "How many helicopters can a human eat in one sitting?"},
]
print(pipe(messages, max_new_tokens=128)[0]['generated_text'][-1])  # 어시스턴트의 응답을 출력합니다.

{'role': 'assistant', 'content': "Matey, I'm afraid I must inform ye that humans cannot eat helicopters. Helicopters are not food, they are flying machines. Food is meant to be eaten, like a hearty plate o' grog, a savory bowl o' stew, or a delicious loaf o' bread. But helicopters, they be for transportin' and movin' around, not for eatin'. So, I'd say none, me hearties. None at all."}

messages = [
    {"role": "user", "content": "Hi there!"},
    {"role": "assistant", "content": "Nice to meet you!"},
    {"role": "user", "content": "Can I ask a question?"}
]

tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=False)
"""<|im_start|>user
Hi there!<|im_end|>
<|im_start|>assistant
Nice to meet you!<|im_end|>
<|im_start|>user
Can I ask a question?<|im_end|>
"""

tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
"""<|im_start|>user
Hi there!<|im_end|>
<|im_start|>assistant
Nice to meet you!<|im_end|>
<|im_start|>user
Can I ask a question?<|im_end|>
<|im_start|>assistant
"""

from transformers import AutoTokenizer
from datasets import Dataset

tokenizer = AutoTokenizer.from_pretrained("HuggingFaceH4/zephyr-7b-beta")

chat1 = [
    {"role": "user", "content": "Which is bigger, the moon or the sun?"},
    {"role": "assistant", "content": "The sun."}
]
chat2 = [
    {"role": "user", "content": "Which is bigger, a virus or a bacterium?"},
    {"role": "assistant", "content": "A bacterium."}
]

dataset = Dataset.from_dict({"chat": [chat1, chat2]})
dataset = dataset.map(lambda x: {"formatted_chat": tokenizer.apply_chat_template(x["chat"], tokenize=False, add_generation_prompt=False)})
print(dataset['formatted_chat'][0])

<|user|>
Which is bigger, the moon or the sun?</s>
<|assistant|>
The sun.</s>

import datetime

def current_time():
    """현재 현지 시간을 문자열로 가져옵니다."""
    return str(datetime.now())

def multiply(a: float, b: float):
    """
    두 숫자를 곱하는 함수
    
    인수:
        a: 곱할 첫 번째 숫자
        b: 곱할 두 번째 숫자
    """
    return a * b

tools = [current_time, multiply]

model_input = tokenizer.apply_chat_template(
    messages,
    tools=tools
)

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

checkpoint = "NousResearch/Hermes-2-Pro-Llama-3-8B"

tokenizer = AutoTokenizer.from_pretrained(checkpoint, revision="pr/13")
model = AutoModelForCausalLM.from_pretrained(checkpoint, torch_dtype=torch.bfloat16, device_map="auto")

def get_current_temperature(location: str, unit: str) -> float:
    """
    특정 위치의 현재 온도를 가져옵니다.
    
    인수:
        위치: 온도를 가져올 위치, "도시, 국가" 형식
        단위: 온도 단위 (선택지: ["celsius", "fahrenheit"])
    반환값:
        지정된 위치의 현재 온도를 지정된 단위로 반환, float 형식.
    """
    return 22.  # 이 함수는 실제로 온도를 가져와야 할 것입니다!

def get_current_wind_speed(location: str) -> float:
    """
    주어진 위치의 현재 풍속을 km/h 단위로 가져옵니다.
    
    인수:
        위치(location): 풍속을 가져올 위치, "도시, 국가" 형식
    반환값:
        주어진 위치의 현재 풍속을 km/h 단위로 반환, float 형식.
    """
    return 6.  # 이 함수는 실제로 풍속을 가져와야 할 것입니다!

tools = [get_current_temperature, get_current_wind_speed]

messages = [
  {"role": "system", "content": "You are a bot that responds to weather queries. You should reply with the unit used in the queried location."},
  {"role": "user", "content": "Hey, what's the temperature in Paris right now?"}
]

inputs = tokenizer.apply_chat_template(messages, chat_template="tool_use", 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]):]))

<tool_call>
{"arguments": {"location": "Paris, France", "unit": "celsius"}, "name": "get_current_temperature"}
</tool_call><|im_end|>

tool_call_id = "vAHdf3"  # 임의의 ID, 각 도구 호출마다 고유해야 함
tool_call = {"name": "get_current_temperature", "arguments": {"location": "Paris, France", "unit": "celsius"}}
messages.append({"role": "assistant", "tool_calls": [{"id": tool_call_id, "type": "function", "function": tool_call}]})

messages.append({"role": "tool", "tool_call_id": tool_call_id, "name": "get_current_temperature", "content": "22.0"})

inputs = tokenizer.apply_chat_template(messages, chat_template="tool_use", 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]):]))

The current temperature in Paris, France is 22.0 ° Celsius.<|im_end|>

from transformers.utils import get_json_schema

def multiply(a: float, b: float):
    """
    두 숫자를 곱하는 함수
    
    인수:
        a: 곱할 첫 번째 숫자
        b: 곱할 두 번째 숫자
    """
    return a * b

schema = get_json_schema(multiply)
print(schema)

{
  "type": "function", 
  "function": {
    "name": "multiply", 
    "description": "A function that multiplies two numbers", 
    "parameters": {
      "type": "object", 
      "properties": {
        "a": {
          "type": "number", 
          "description": "The first number to multiply"
        }, 
        "b": {
          "type": "number",
          "description": "The second number to multiply"
        }
      }, 
      "required": ["a", "b"]
    }
  }
}

# 인수를 받지 않는 간단한 함수
current_time = {
  "type": "function", 
  "function": {
    "name": "current_time",
    "description": "Get the current local time as a string.",
    "parameters": {
      'type': 'object',
      'properties': {}
    }
  }
}

# 두 개의 숫자 인수를 받는 더 완전한 함수
multiply = {
  'type': 'function',
  'function': {
    'name': 'multiply',
    'description': 'A function that multiplies two numbers', 
    'parameters': {
      'type': 'object', 
      'properties': {
        'a': {
          'type': 'number',
          'description': 'The first number to multiply'
        }, 
        'b': {
          'type': 'number', 'description': 'The second number to multiply'
        }
      }, 
      'required': ['a', 'b']
    }
  }
}

model_input = tokenizer.apply_chat_template(
    messages,
    tools = [current_time, multiply]
)

document1 = {
    "title": "The Moon: Our Age-Old Foe",
    "contents": "Man has always dreamed of destroying the moon. In this essay, I shall..."
}

document2 = {
    "title": "The Sun: Our Age-Old Friend",
    "contents": "Although often underappreciated, the sun provides several notable benefits..."
}

model_input = tokenizer.apply_chat_template(
    messages,
    documents=[document1, document2]
)

>>> from transformers import AutoTokenizer
>>> tokenizer = AutoTokenizer.from_pretrained("facebook/blenderbot-400M-distill")

>>> tokenizer.chat_template
"{% for message in messages %}{% if message['role'] == 'user' %}{{ ' ' }}{% endif %}{{ message['content'] }}{% if not loop.last %}{{ '  ' }}{% endif %}{% endfor %}{{ eos_token }}"

{%- for message in messages %}
    {%- if message['role'] == 'user' %}
        {{- ' ' }}
    {%- endif %}
    {{- message['content'] }}
    {%- if not loop.last %}
        {{- '  ' }}
    {%- endif %}
{%- endfor %}
{{- eos_token }}

for idx, message in enumerate(messages):
    if message['role'] == 'user':
        print(' ')
    print(message['content'])
    if not idx == len(messages) - 1:  # Check for the last message in the conversation
        print('  ')
print(eos_token)

{%- for message in messages %}
    {%- if message['role'] == 'user' %}
        {{- bos_token + '[INST] ' + message['content'] + ' [/INST]' }}
    {%- elif message['role'] == 'system' %}
        {{- '<<SYS>>\\n' + message['content'] + '\\n<</SYS>>\\n\\n' }}
    {%- elif message['role'] == 'assistant' %}
        {{- ' '  + message['content'] + ' ' + eos_token }}
    {%- endif %}
{%- endfor %}

{%- for message in messages %}
    {%- if message['role'] == 'user' %}
        {{- bos_token + '[INST] ' + message['content'].strip() + ' [/INST]' }}
    {%- elif message['role'] == 'system' %}
        {{- '<<SYS>>\\n' + message['content'].strip() + '\\n<</SYS>>\\n\\n' }}
    {%- elif message['role'] == 'assistant' %}
        {{- '[ASST] '  + message['content'] + ' [/ASST]' + eos_token }}
    {%- endif %}
{%- endfor %}

template = tokenizer.chat_template
template = template.replace("SYS", "SYSTEM")  # 시스템 토큰 변경
tokenizer.chat_template = template  # 새 템플릿 설정
tokenizer.push_to_hub("model_name")  # 새 템플릿을 허브에 업로드!

{%- for message in messages %}
    {{- '<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n' }}
{%- endfor %}

tokenizer.chat_template = "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}"

<|im_start|>system
You are a helpful chatbot that will do its best not to say anything so stupid that people tweet about it.<|im_end|>
<|im_start|>user
How are you?<|im_end|>
<|im_start|>assistant
I'm doing great!<|im_end|>

{%- for message in messages %}
    {{- message['role'] + message['content'] }}
{%- endfor %}

{% for message in messages %}
    {{ message['role'] + message['content'] }}
{% endfor %}

{%- for message in messages %}
    {{- message['content'] }}
{%- endfor %}

{%- if message['role'] == 'user' %}
    {{- message['content'] }}
{%- endif %}

{%- if loop.last and add_generation_prompt %}
    {{- bos_token + 'Assistant:\n' }}
{%- endif %}