Hugging Face Chat Template Tester — Render chat template Hugging Face dan lihat prompt persisnya

<|im_start|>system
You are a helpful assistant.

# Tools

You can call these functions:
<tools>
{"type": "function", "function": {"name": "get_weather", "description": "Get the current weather in a city.", "parameters": {"type": "object", "properties": {"city": {"type": "string", "description": "City name"}}, "required": ["city"]}}}
</tools>

To call one, reply with JSON inside <tool_call></tool_call>.<|im_end|>
<|im_start|>user
What's the weather in Paris?<|im_end|>
<|im_start|>assistant

<tool_call>
{"name": "get_weather", "arguments": {"city": "Paris"}}
</tool_call><|im_end|>
<|im_start|>user
<tool_response>
{"temperature": 22}
</tool_response><|im_end|>
<|im_start|>assistant

Tentang template ini

Variabel yang dibacanya

Diatur oleh apply_chat_template: add_generation_prompt, messages, tools

Token khusus: tidak ada

Lainnya: tidak ada

Memakai {% generation %}

Tidak

Periksa di Python

Jalankan ini untuk membandingkan dengan transformers. Ganti MODEL_ID dengan model Anda, atau berikan template Anda dengan chat_template=.

from transformers import AutoTokenizer

tokenizer = AutoTokenizer.from_pretrained("MODEL_ID")
messages = [
    {'role': 'system', 'content': 'You are a helpful assistant.'},
    {'role': 'user', 'content': "What's the weather in Paris?"},
    {'role': 'assistant', 'content': '', 'tool_calls': [{'type': 'function', 'function': {'name': 'get_weather', 'arguments': {'city': 'Paris'}}}]},
    {'role': 'tool', 'name': 'get_weather', 'content': '{"temperature": 22}'},
]
tools = [
    {'type': 'function', 'function': {'name': 'get_weather', 'description': 'Get the current weather in a city.', 'parameters': {'type': 'object', 'properties': {'city': {'type': 'string', 'description': 'City name'}}, 'required': ['city']}}},
]
text = tokenizer.apply_chat_template(
    messages,
    tools=tools,
    add_generation_prompt=True,
    tokenize=False,
)
print(text)