openbmb

/

MiniCPM3-4B

like 380

Follow

OpenBMB 339

from transformers import AutoTokenizer

tokenizer = AutoTokenizer.from_pretrained("openbmb/MiniCPM3-4B", trust_remote_code=True)
messages = [{"role": "user", "content": "What is the weather like in Boston?."}]
tools = [
    {
        "type": "function",
        "function": {
            "name": "get_current_weather",
            "description": "Get the current weather in a given location",
            "parameters": {
                "type": "object",
                "properties": {
                    "location": {
                        "type": "string",
                        "description": "The city and state, e.g. San Francisco, CA",
                    },
                    "date": {
                        "type": "string",
                        "description": "The date for which to get the weather, e.g. 2022-01-01",
                        "pattern": "^([1-9] |1[0-9]| 2[0-9]|3[0-1])(.|-)([1-9] |1[0-2])(.|-|)20[0-9][0-9]$",
                    },
                    "unit": {
                        "type": "string",
                        "enum": ["celsius", "fahrenheit"],
                        "default": "celcius",
                    },
                },
                "required": ["location"],
            },
        },
    }
]


prompt = tokenizer.apply_chat_template(
    messages, tools=tools, tokenize=False, add_generation_start=True
)
print(prompt)

<|im_start|>system
# Functions
Here is a list of functions that you can invoke:
```python
from enum import Enum
from typing import List, Dict, Optional
from pydantic import BaseModel, Field

class Unit(Enum):
    celsius = 'celsius'
    fahrenheit = 'fahrenheit'


def get_current_weather(location, date=None, unit='celcius'):
    """
    Get the current weather in a given location
    Args:

    location: str = Field(..., description='The city and state, e.g. San Francisco, CA')
    date: Optional[str] = Field(
        None,
        description='The date for which to get the weather, e.g. 2022-01-01',
        regex='^([1-9] |1[0-9]| 2[0-9]|3[0-1])(.|-)([1-9] |1[0-2])(.|-|)20[0-9][0-9]$',
    )
    unit: Optional[Unit] = 'celcius'
    """

```

# Function Call Rule and Output Format
- If the user's question can be answered without calling any function, please answer the user's question directly. In this situation, you should return your thought and answer the user's question directly.
- If the user cannot be answered without calling any function, and the user does not provide enough information to call functions, please ask the user for more information. In this situation, you should return your thought and ask the user for more information.
- If the user's question cannot be answered without calling any function, and the user has provided enough information to call functions to solve it, you should call the functions. In this situation, the assistant should return your thought and call the functions.
- Use default parameters unless the user has specified otherwise.
- You should answer in the following format:

<|thought_start|>
{explain why the user's question can be answered without calling a function or why you should ask the user for more information or why you should call one or more functions and your plan to solve the user's question.}
<|thought_end|>
<|tool_call_start|>
```python
func1(params_name=params_value, params_name2=params_value2...)
func2(params)
```
<|tool_call_end|>
{answer the user's question directly or ask the user for more information}<|im_end|>
<|im_start|>user
What is the weather like in Boston?.<|im_end|>

from transformers import AutoTokenizer


tokenizer = AutoTokenizer.from_pretrained("openbmb/MiniCPM3-4B", trust_remote_code=True)
messages = [{"role": "user", "content": "What is the weather like in Boston?."}]


prompt = tokenizer.apply_chat_template(
    messages, tokenize=False, add_generation_start=True
)
print(prompt)

<|im_start|>user
What is the weather like in Boston?.<|im_end|>

#!/usr/bin/env python
# encoding: utf-8
from transformers import AutoTokenizer


tokenizer = AutoTokenizer.from_pretrained("openbmb/MiniCPM3-4B", trust_remote_code=True)
messages = [{"role": "user", "content": "hello"}]

tools = [
    {
        "type": "function",
        "function": {
            "name": "create_user",
            "description": "creates a user",
            "parameters": {
                "type": "object",
                "properties": {
                    "user": {
                        "title": "User",
                        "type": "object",
                        "properties": {
                            "user_id": {
                                "title": "User Id",
                                "description": "The unique identifier for a user",
                                "default": 0,
                                "type": "integer",
                            },
                            "name": {
                                "title": "Name",
                                "description": "The name of the user",
                                "type": "string",
                            },
                            "age": {
                                "title": "Age",
                                "description": "The age of the user",
                                "default": 25,
                                "type": "integer",
                            },
                            "email": {
                                "title": "Email",
                                "description": "The email address of the user",
                                "type": "string",
                            },
                            "friends": {
                                "title": "Friends",
                                "description": "List of friends of the user",
                                "type": "array",
                                "items": {"type": "string"},
                            },
                        },
                        "required": ["name", "email"],
                    },
                },
                "required": ["user"],
                "definitions": {},
            },
        },
    },
]

prompt = tokenizer.apply_chat_template(
    messages, tools=tools, tokenize=False, add_generation_start=True
)
print(prompt)

# Functions
Here is a list of functions that you can invoke:
```python
from enum import Enum
from typing import List, Dict, Optional
from pydantic import BaseModel, Field



class User(BaseModel):
    user_id: Optional[int] = Field(
        0, description='The unique identifier for a user', title='User Id'
    )
    name: str = Field(..., description='The name of the user', title='Name')
    age: Optional[int] = Field(25, description='The age of the user', title='Age')
    email: str = Field(..., description='The email address of the user', title='Email')
    friends: Optional[List[str]] = Field(
        None, description='List of friends of the user', title='Friends'
    )


def create_user(user):
    """
    creates a user
    Args:

    user: User = Field(..., title='User')

    """

```

# Function Call Rule and Output Format
- If the user's question can be answered without calling any function, please answer the user's question directly. In this situation, you should return your thought and answer the user's question directly.
- If the user cannot be answered without calling any function, and the user does not provide enough information to call functions, please ask the user for more information. In this situation, you should return your thought and ask the user for more information.
- If the user's question cannot be answered without calling any function, and the user has provided enough information to call functions to solve it, you should call the functions. In this situation, the assistant should return your thought and call the functions.
- Use default parameters unless the user has specified otherwise.
- You should answer in the following format:

<|thought_start|>
{explain why the user's question can be answered without calling a function or why you should ask the user for more information or why you should call one or more functions and your plan to solve the user's question.}
<|thought_end|>
<|tool_call_start|>
```python
func1(params_name=params_value, params_name2=params_value2...)
func2(params)
```
<|tool_call_end|>
{answer the user's question directly or ask the user for more information}<|im_end|>
<|im_start|>user
hello<|im_end|>