richardr1126/spider-natsql-wizard-coder-merged

Spider NatSQL Wizard Coder Summary

• This model was created by finetuning WizardLM/WizardCoder-15B-V1.0 on a NatSQL enhanced Spider context training dataset: richardr1126/spider-natsql-context-instruct.
• Finetuning was performed using QLoRa on a single RTX6000 48GB.
• If you want just the QLoRa/LoRA adapter: richardr1126/spider-natsql-wizard-coder-qlora

Running the GGML model

• The best way to run this model is to use the GGML version on koboldcpp, with CuBlas support.

Spider Dataset

Spider is a large-scale complex and cross-domain semantic parsing and text-to-SQL dataset annotated by 11 Yale students The goal of the Spider challenge is to develop natural language interfaces to cross-domain databases.

This dataset was used to finetune this model.

NatSQL

NatSQL is an intermediate representation for SQL that simplifies the queries and reduces the mismatch between natural language and SQL. NatSQL preserves the core functionalities of SQL, but removes some clauses and keywords that are hard to infer from natural language descriptions. NatSQL also makes schema linking easier by reducing the number of schema items to predict. NatSQL can be easily converted to executable SQL queries and can improve the performance of text-to-SQL models.

Citations

@misc{luo2023wizardcoder,
      title={WizardCoder: Empowering Code Large Language Models with Evol-Instruct}, 
      author={Ziyang Luo and Can Xu and Pu Zhao and Qingfeng Sun and Xiubo Geng and Wenxiang Hu and Chongyang Tao and Jing Ma and Qingwei Lin and Daxin Jiang},
      year={2023},
}

@article{yu2018spider,
  title={Spider: A large-scale human-labeled dataset for complex and cross-domain semantic parsing and text-to-sql task},
  author={Yu, Tao and Zhang, Rui and Yang, Kai and Yasunaga, Michihiro and Wang, Dongxu and Li, Zifan and Ma, James and Li, Irene and Yao, Qingning and Roman, Shanelle and others},
  journal={arXiv preprint arXiv:1809.08887},
  year={2018}
}

@inproceedings{gan-etal-2021-natural-sql,
    title = "Natural {SQL}: Making {SQL} Easier to Infer from Natural Language Specifications",
    author = "Gan, Yujian  and
      Chen, Xinyun  and
      Xie, Jinxia  and
      Purver, Matthew  and
      Woodward, John R.  and
      Drake, John  and
      Zhang, Qiaofu",
    booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2021",
    month = nov,
    year = "2021",
    address = "Punta Cana, Dominican Republic",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2021.findings-emnlp.174",
    doi = "10.18653/v1/2021.findings-emnlp.174",
    pages = "2030--2042",
}

@article{dettmers2023qlora,
  title={QLoRA: Efficient Finetuning of Quantized LLMs},
  author={Dettmers, Tim and Pagnoni, Artidoro and Holtzman, Ari and Zettlemoyer, Luke},
  journal={arXiv preprint arXiv:2305.14314},
  year={2023}
}

Disclaimer

The resources, including code, data, and model weights, associated with this project are restricted for academic research purposes only and cannot be used for commercial purposes. The content produced by any version of WizardCoder is influenced by uncontrollable variables such as randomness, and therefore, the accuracy of the output cannot be guaranteed by this project. This project does not accept any legal liability for the content of the model output, nor does it assume responsibility for any losses incurred due to the use of associated resources and output results.