Think2sql 7B

🚀 Think2SQL-7B 推理模型

Think2SQL-7B 是一個用於 Text2SQL 任務的推理模型，能基於給定問題、證據和數據庫模式生成 SQL 腳本。

🚀 快速開始

該模型在搭配特定的系統提示和用戶提示時能達到最佳性能。此模型設計用於接收三個輸入：問題、證據和數據庫模式。

從 transformers >= 4.43.0 版本開始，你可以使用 Transformers 的 pipeline 抽象方法，或者藉助 generate() 函數的 Auto 類來進行對話式推理。

請確保通過 pip install --upgrade transformers 命令更新你的 transformers 庫。

import transformers
import torch
model_id = "simone-papicchio/Think2SQL-7B"
pipeline = transformers.pipeline(
    "text-generation",
    model=model_id,
    model_kwargs={"torch_dtype": torch.bfloat16},
    device_map="auto",
)

system_message = (
    "You are a helpful AI Assistant that provides well-reasoned and detailed responses. "
    "You first think about the reasoning process as an internal monologue and then provide the user with the answer. "
    "Respond in the following format: <think>\n...\n</think>\n<answer>\n...\n</answer>"
).strip()

user_message = (
    "Answer the following question with the SQL code. Use the piece of evidence and base your answer on the database schema. "
    "Given the question, the evidence and the database schema, return in the <answer> tags only the SQL script that addresses the question.\n"
    "Question:\n{question}\n\n"
    "Evidence:\n{evidence}\n\n"
    "Database Schema:\n{schema}\n\n"
    "Return only the SQL script enclosed in <answer> tags."
).strip()

messages = [
    {"role": "system", "content": system_message},
    {"role": "user", "content": user_message},
]

outputs = pipeline(
    messages,
    max_new_tokens=30_000,
    temperature=0.7,
    top_p=0.95
)
print(outputs[0]["generated_text"][-1])

✨ 主要特性

此模型是在論文 Think2SQL: Reinforce LLM Reasoning Capabilities for Text2SQL 中介紹的用於 Text2SQL 任務的推理模型。

該模型是 Qwen/Qwen2.5-Coder-7B-Instruct 在 simone-papicchio/bird 數據集上的微調版本，使用 TRL 進行訓練。

🔧 技術細節

訓練過程

該模型使用 GRPO 方法進行訓練，此方法在論文 DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models 中被提出。

框架版本

• TRL: 0.17.0.dev0
• Transformers: 4.51.0
• Pytorch: 2.5.1
• Datasets: 3.5.0
• Tokenizers: 0.21.1

📚 詳細文檔

模型信息

引用信息

@misc{papicchio2025think2sqlreinforcellmreasoning,
      title={Think2SQL: Reinforce LLM Reasoning Capabilities for Text2SQL}, 
      author={Simone Papicchio and Simone Rossi and Luca Cagliero and Paolo Papotti},
      year={2025},
      eprint={2504.15077},
      archivePrefix={arXiv},
      primaryClass={cs.LG},
      url={https://arxiv.org/abs/2504.15077}, 
}

@inproceedings{papicchio2023qatch,
  title={QATCH: benchmarking SQL-centric tasks with table representation learning models on your data},
  author={Papicchio, Simone and Papotti, Paolo and Cagliero, Luca},
  booktitle={Proceedings of the 37th International Conference on Neural Information Processing Systems},
  pages={30898--30917},
  year={2023}
}

📄 許可證

本項目採用 Apache-2.0 許可證。