Skip to content

Code for finetuning a language model to output SQL querries with inputs in the natural language

Notifications You must be signed in to change notification settings

sunatte-saad/sql-finetuning

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

7 Commits
 
 
 
 
 
 
 
 
 
 

Repository files navigation

SQL-Finetuning

Code for fine-tuning a language model to output SQL queries from natural language inputs.

Instructions

Running on Google Colab

  1. Open sql-finetuning.ipynb.
  2. Change your runtime to GPU.
  3. Run the notebook.

Running Locally

If you prefer to run the notebook locally, follow these steps to set up a virtual environment:

  1. Create a virtual environment:

    python3 -m venv venv
  2. Activate the virtual environment:

    # On macOS and Linux
    source venv/bin/activate
    
    # On Windows
    .\venv\Scripts\activate

Note: You do not need a virtual environment on Google Colab.

Hardware Requirements

Ensure you have access to a GPU, as training will take a long time without one.

Pre-trained Weights

If you don't want to train the model yourself, you can download the pre-trained weights for inference:

Download Pre-trained Weights

About

Code for finetuning a language model to output SQL querries with inputs in the natural language

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published