--- library_name: transformers license: cc-by-nc-4.0 pipeline_tag: text-generation tags: - text-to-sql - reinforcement-learning --- # SLM-SQL: An Exploration of Small Language Models for Text-to-SQL ### Important Links 📖[Arxiv Paper](https://arxiv.org/abs/2507.22478) | 🤗[HuggingFace Collection](https://huggingface.co/collections/cycloneboy/slm-sql-688b02f99f958d7a417658dc) | 🤖[ModelScope Collection](https://modelscope.cn/collections/SLM-SQL-624bb6a60e9643) | 📚[GitHub Repository](https://github.com/CycloneBoy/slm_sql) ## News + `July 31, 2025`: Upload model to modelscope and huggingface. + `July 30, 2025`: Publish the paper to arxiv ## Introduction > Large language models (LLMs) have demonstrated strong performance in translating natural language questions into SQL > queries (Text-to-SQL). In contrast, small language models (SLMs) ranging from 0.5B to 1.5B parameters currently > underperform on Text-to-SQL tasks due to their limited logical reasoning capabilities. However, SLMs offer inherent > advantages in inference speed and suitability for edge deployment. To explore their potential in Text-to-SQL > applications, we leverage recent advancements in post-training techniques. Specifically, we used the open-source > SynSQL-2.5M dataset to construct two derived datasets: SynSQL-Think-916K for SQL generation and > SynSQL-Merge-Think-310K > for SQL merge revision. We then applied supervised fine-tuning and reinforcement learning-based post-training to the > SLM, followed by inference using a corrective self-consistency approach. Experimental results validate the > effectiveness > and generalizability of our method, SLM-SQL. On the BIRD development set, the five evaluated models achieved an > average > improvement of 31.4 points. Notably, the 0.5B model reached 56.87\% execution accuracy (EX), while the 1.5B model > achieved 67.08\% EX. We will release our dataset, model, and code to github: https://github.com/CycloneBoy/slm_sql. ### Framework slmsql_framework ### Main Results slm_sql_result slmsql_bird_main slmsql_spider_main Performance Comparison of different Text-to-SQL methods on BIRD dev and test dataset. slmsql_ablation_study ## Usage This model can be loaded and used directly with the Hugging Face `transformers` library. Below is a basic example for Text-to-SQL generation. ```python from transformers import AutoTokenizer, AutoModelForCausalLM import torch # Load the tokenizer and model model_name = "cycloneboy/SLM-SQL-0.5B" # You can replace with other models from the table below tokenizer = AutoTokenizer.from_pretrained(model_name) model = AutoModelForCausalLM.from_pretrained(model_name, device_map="auto", torch_dtype=torch.bfloat16) # Example text-to-SQL query # For Text-to-SQL, you might also need to provide schema information depending on the model's training. prompt = "Give me the SQL query for customers who placed orders in New York." # For chat models like Qwen2.5-Coder-0.5B-Instruct, it's often best to use the chat template: messages = [ {"role": "user", "content": prompt} ] chat_input = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True) # Tokenize input input_ids = tokenizer(chat_input, return_tensors="pt").input_ids.to(model.device) # Generate SQL query # Adjust generation parameters as needed. Common ones include max_new_tokens, do_sample, temperature, top_p, num_beams generated_ids = model.generate(input_ids, max_new_tokens=100, num_beams=1, do_sample=False) # Decode and print the generated SQL # Set skip_special_tokens=True to remove special tokens from the output. generated_text = tokenizer.decode(generated_ids[0], skip_special_tokens=True) print(generated_text) ``` ## Model | **Model** | Base Model | Train Method | Modelscope | HuggingFace | |------------------------------------------|------------------------------|--------------|---------------------------------------------------------------------------------------------------|----------------------------------------------------------------------------------------------| | SLM-SQL-Base-0.5B | Qwen2.5-Coder-0.5B-Instruct | SFT | [🤖 Modelscope](https://modelscope.cn/models/cycloneboy/SLM-SQL-Base-0.5B) | [🤗 HuggingFace](https://huggingface.co/cycloneboy/SLM-SQL-Base-0.5B) | | SLM-SQL-0.5B | Qwen2.5-Coder-0.5B-Instruct | SFT + GRPO | [🤖 Modelscope](https://modelscope.cn/models/cycloneboy/SLM-SQL-0.5B) | [🤗 HuggingFace](https://huggingface.co/cycloneboy/SLM-SQL-0.5B) | | CscSQL-Merge-Qwen2.5-Coder-0.5B-Instruct | Qwen2.5-Coder-0.5B-Instruct | SFT + GRPO | [🤖 Modelscope](https://modelscope.cn/models/cycloneboy/CscSQL-Merge-Qwen2.5-Coder-0.5B-Instruct) | [🤗 HuggingFace](https://huggingface.co/cycloneboy/CscSQL-Merge-Qwen2.5-Coder-0.5B-Instruct) | | SLM-SQL-Base-1.5B | Qwen2.5-Coder-1.5B-Instruct | SFT | [🤖 Modelscope](https://modelscope.cn/models/cycloneboy/SLM-SQL-Base-1.5B) | [🤗 HuggingFace](https://huggingface.co/cycloneboy/SLM-SQL-Base-1.5B) | | SLM-SQL-1.5B | Qwen2.5-Coder-1.5B-Instruct | SFT + GRPO | [🤖 Modelscope](https://modelscope.cn/models/cycloneboy/SLM-SQL-1.5B) | [🤗 HuggingFace](https://huggingface.co/cycloneboy/SLM-SQL-1.5B) | | CscSQL-Merge-Qwen2.5-Coder-1.5B-Instruct | Qwen2.5-Coder-1.5B-Instruct | SFT + GRPO | [🤖 Modelscope](https://modelscope.cn/models/cycloneboy/CscSQL-Merge-Qwen2.5-Coder-1.5B-Instruct) | [🤗 HuggingFace](https://huggingface.co/cycloneboy/CscSQL-Merge-Qwen2.5-Coder-1.5B-Instruct) | | SLM-SQL-Base-0.6B | Qwen3-0.6B | SFT | [🤖 Modelscope](https://modelscope.cn/models/cycloneboy/SLM-SQL-Base-0.6B) | [🤗 HuggingFace](https://huggingface.co/cycloneboy/SLM-SQL-Base-0.6B) | | SLM-SQL-0.6B | Qwen3-0.6B | SFT + GRPO | [🤖 Modelscope](https://modelscope.cn/models/cycloneboy/SLM-SQL-0.6B) | [🤗 HuggingFace](https://huggingface.co/cycloneboy/SLM-SQL-0.6B) | | SLM-SQL-Base-1.3B | deepseek-coder-1.3b-instruct | SFT | [🤖 Modelscope](https://modelscope.cn/models/cycloneboy/SLM-SQL-Base-1.3B ) | [🤗 HuggingFace](https://huggingface.co/cycloneboy/SLM-SQL-Base-1.3B ) | | SLM-SQL-1.3B | deepseek-coder-1.3b-instruct | SFT + GRPO | [🤖 Modelscope](https://modelscope.cn/models/cycloneboy/SLM-SQL-1.3B ) | [🤗 HuggingFace](https://huggingface.co/cycloneboy/SLM-SQL-1.3B ) | | SLM-SQL-Base-1B | Llama-3.2-1B-Instruct | SFT | [🤖 Modelscope](https://modelscope.cn/models/cycloneboy/SLM-SQL-Base-1B ) | [🤗 HuggingFace](https://huggingface.co/cycloneboy/SLM-SQL-Base-1B ) | ## Dataset | **Dataset** | Modelscope | HuggingFace | |----------------------------|------------------------------------------------------------------------------------|--------------------------------------------------------------------------------------| | SynsQL-Think-916k | [🤖 Modelscope](https://modelscope.cn/datasets/cycloneboy/SynsQL-Think-916k) | [🤗 HuggingFace](https://huggingface.co/datasets/cycloneboy/SynsQL-Think-916k) | | SynsQL-Merge-Think-310k | [🤖 Modelscope](https://modelscope.cn/datasets/cycloneboy/SynsQL-Merge-Think-310k) | [🤗 HuggingFace](https://huggingface.co/datasets/cycloneboy/SynsQL-Merge-Think-310k) | | bird train and dev dataset | [🤖 Modelscope](https://modelscope.cn/datasets/cycloneboy/bird_train) | [🤗 HuggingFace](https://huggingface.co/datasets/cycloneboy/bird_train) | ## TODO - [ ] Release inference code - [ ] Upload Model - [ ] Release training code - [ ] Fix bug - [ ] Update doc ## Thanks to the following projects - [csc_sql](https://github.com/CycloneBoy/csc_sql) - [open-r1](https://github.com/huggingface/open-r1) - [OmniSQL](https://github.com/RUCKBReasoning/OmniSQL) ## Citation ```bibtex @misc{sheng2025slmsqlexplorationsmalllanguage, title={SLM-SQL: An Exploration of Small Language Models for Text-to-SQL}, author={Lei Sheng and Shuai-Shuai Xu}, year={2025}, eprint={2507.22478}, archivePrefix={arXiv}, primaryClass={cs.CL}, url={https://arxiv.org/abs/2507.22478}, } @misc{sheng2025cscsqlcorrectiveselfconsistencytexttosql, title={CSC-SQL: Corrective Self-Consistency in Text-to-SQL via Reinforcement Learning}, author={Lei Sheng and Shuai-Shuai Xu}, year={2025}, eprint={2505.13271}, archivePrefix={arXiv}, primaryClass={cs.CL}, url={https://arxiv.org/abs/2505.13271}, } ```