| --- |
| base_model: Qwen/Qwen2.5-Coder-7B-Instruct |
| datasets: simone-papicchio/bird |
| library_name: transformers |
| tags: |
| - generated_from_trainer |
| - open-r1 |
| - Text2SQL |
| - Reasoning |
| licence: apache-2.0 |
| --- |
| |
| # Model Information |
|
|
| This model is the reasoning model for Text2SQL task introduced in [Think2SQL: Reinforce LLM Reasoning Capabilities for Text2SQL](https://arxiv.org/abs/2504.15077) |
|
|
|
|
| This model is a fine-tuned version of [Qwen/Qwen2.5-Coder-7B-Instruct](https://huggingface.co/Qwen/Qwen2.5-Coder-7B-Instruct) on the [simone-papicchio/bird](https://huggingface.co/datasets/simone-papicchio/bird) dataset. |
| It has been trained using [TRL](https://github.com/huggingface/trl). |
|
|
|
|
|
|
| ## Quick start |
|
|
| The best model performance are given with its System and User prompt. |
| The model is intended to use with three input: question, evidence and the database schema. |
|
|
|
|
| Starting with `transformers >= 4.43.0` onward, you can run conversational inference using the Transformers `pipeline` abstraction or by leveraging the Auto classes with the `generate()` function. |
|
|
| Make sure to update your transformers installation via `pip install --upgrade transformers`. |
|
|
| ```python |
| 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]) |
| ``` |
|
|
| ## Training procedure |
|
|
| [<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/spapicchio-politecnico-di-torino/deep-thinking/runs/d93m41pq) |
|
|
|
|
| This model was trained with GRPO, a method introduced in [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://huggingface.co/papers/2402.03300). |
|
|
| ### Framework versions |
|
|
| - TRL: 0.17.0.dev0 |
| - Transformers: 4.51.0 |
| - Pytorch: 2.5.1 |
| - Datasets: 3.5.0 |
| - Tokenizers: 0.21.1 |
|
|
| ## Citations |
|
|
| ```bibtex |
| @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}, |
| } |
| ``` |
|
|
| ```bibtex |
| @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} |
| } |
| ``` |
|
|
