Tiny Agent A 3B

🚀 Tiny-Agent-α

Tiny-Agent-α 是 Dria-Agent-a 的擴展，它基於 Qwen2.5-Coder 系列模型進行訓練，可用於邊緣設備。這些模型通過量化感知訓練進行了精細微調，以最大程度減少量化後的性能損失。

Tiny-Agent-α 採用了 Python 函數調用 方式，即大語言模型（LLMs）使用 Python 代碼塊與提供的工具進行交互並輸出操作。這種方法受到了許多先前工作的啟發，包括但不限於 DynaSaur、RLEF、ADAS 和 CAMEL。與傳統的基於 JSON 的函數調用方法相比，這種函數調用方式具有以下優勢：

1. 一次性並行多函數調用：該模型可以在一次對話中利用多個同步進程來找到解決方案，而其他函數調用模型可能需要多次對話才能實現。
2. 自由形式的推理和操作：模型可以自然地以自然語言提供推理過程，並在 ```python ``` 代碼塊中輸出操作，無需特殊提示或調整。這有助於緩解在 Let Me Speak Freely? 中討論的對大語言模型輸出施加特定格式可能導致的性能損失。
3. 即時生成複雜解決方案：模型提供的解決方案本質上是一個 Python 程序，但排除了一些“危險”的內置函數，如 exec、eval 和 compile（完整列表見下面的快速開始部分）。這使得模型能夠通過條件語句和同步管道（在下一個函數的參數中使用前一個函數的輸出）實現自定義的複雜邏輯，而目前基於 JSON 的函數調用方法（據我們所知）無法做到這一點。

🚀 快速開始

你可以使用 dria_agent 包輕鬆使用 Tiny-Agent-α：

pip install dria_agent

這個包可以處理模型、工具、代碼執行和後端（支持 mlx、ollama 和 transformers）。

💻 使用示例

基礎用法

使用 @tool 裝飾器將函數暴露給代理：

from dria_agent import tool

@tool
def check_availability(day: str, start_time: str, end_time: str) -> bool:
    """
    Checks if a given time slot is available.

    :param day: The date in "YYYY-MM-DD" format.
    :param start_time: The start time of the desired slot (HH:MM format, 24-hour).
    :param end_time: The end time of the desired slot (HH:MM format, 24-hour).
    :return: True if the slot is available, otherwise False.
    """
    # Mock implementation
    if start_time == "12:00" and end_time == "13:00":
        return False
    return True

創建一個帶有自定義工具的代理：

from dria_agent import ToolCallingAgent

agent = ToolCallingAgent(
    tools=[check_availability]
)

使用 agent.run(query) 結合工具執行任務：

execution = agent.run("Check my calendar for tomorrow noon", print_results=True)

輸出如下：

let me help you check your availability for a 1-hour meditation session       
starting at noon tomorrow.                                                    
                                                                                
Step-by-step reasoning:                                                       
 1. We need to check availability for a specific time slot (noon)              
 2. The duration is 1 hour, so we'll use the same start and end times          
 3. Since it's tomorrow, we should format the date as "YYYY-MM-DD"             
 4. Use the check_availability() function with these parameters                
                                                                                
Here's the code to check your availability:                                   
                                                                                
```python                                                                     
tomorrow = (datetime.now() + timedelta(days=1)).strftime("%Y-%m-%d")          
start_time = "12:00"  # Noon in 24-hour format                                
end_time = "13:00"   # One hour after noon                                    
                                                                                
availability = check_availability(tomorrow, start_time, end_time)             

The code will:

• Calculate tomorrow's date using datetime and timedelta
• Set the time slot to noon (12:00) for 1 hour duration
• Check if this time slot is available using the check_availability function

The availability variable will contain True if you're available, or False if
not.

如果使用 `dria_agent`，系統提示和工具可以直接使用，無需額外設置。

你也可以直接使用 `transformers` 庫來使用 Tiny-Agent-α-3B：

```python
import json
from typing import Any, Dict, List
from transformers import AutoModelForCausalLM, AutoTokenizer

# Load model and tokenizer
model_name = "driaforall/Tiny-Agent-a-3B"
model = AutoModelForCausalLM.from_pretrained(
    model_name, device_map="auto", torch_dtype="auto", trust_remote_code=True
)
tokenizer = AutoTokenizer.from_pretrained(model_name)

# System prompt for optimal performance
SYSTEM_PROMPT = """
You are an expert AI assistant that specializes in providing Python code to solve the task/problem at hand provided by the user.

You can use Python code freely, including the following available functions:

<|functions_schema|>
{{functions_schema}}
<|end_functions_schema|>

The following dangerous builtins are restricted for security:
- exec
- eval
- execfile
- compile
- importlib
- input
- exit

Think step by step and provide your reasoning, outside of function calls.
You can write Python code and use the available functions. Provide all your Python code in a SINGLE markdown code block.

DO NOT use print() statements AT ALL. Avoid mutating variables whenever possible.
""".strip()

# Example function schema (define the functions available to the model)
FUNCTIONS_SCHEMA = """
def check_availability(day: str, start_time: str, end_time: str) -> bool:
    """
    Checks if a given time slot is available.

    :param day: The date in "YYYY-MM-DD" format.
    :param start_time: The start time of the desired slot (HH:MM format, 24-hour).
    :param end_time: The end time of the desired slot (HH:MM format, 24-hour).
    :return: True if the slot is available, otherwise False.
    """
    pass
"""

# Format system prompt
system_prompt = SYSTEM_PROMPT.replace("{{functions_schema}}", FUNCTIONS_SCHEMA)

# Example user query
USER_QUERY = "Check if I'm available for an hour long meditation at tomorrow noon."

# Format messages for the model
messages = [
    {"role": "system", "content": system_prompt},
    {"role": "user", "content": USER_QUERY},
]

# Prepare input for the model
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True
)
model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

# Generate response
generated_ids = model.generate(
    **model_inputs,
    max_new_tokens=512
)

# Extract new generated tokens
generated_ids = [
    output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
]

# Decode response
response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
print(response)

📊 評估與性能

我們在 Dria-Pythonic-Agent-Benchmark (DPAB) 上對模型進行了評估。這個基準測試是我們通過合成數據生成、基於模型的驗證、過濾和手動選擇精心策劃的，用於評估大語言模型的 Python 函數調用能力，涵蓋了多個場景和任務。更多信息請參閱 博客。

以下是 DPAB 的評估結果：

當前各種模型的基準測試結果（嚴格模式）：

📄 引用

@misc{Dria-Agent-a,
      url={https://huggingface.co/blog/andthattoo/dria-agent-a},
      title={Dria-Agent-a},
      author={"andthattoo", "Atakan Tekparmak"}
}

📄 許可證

本項目採用 qwen-research 許可證。