Skip to content

Instantly share code, notes, and snippets.

@mkeywood1

mkeywood1/Fine tune SQL LLM.ipynb

Last active September 16, 2025 10:31
Show Gist options

  • Select an option

    Learn more about clone URLs
  • Save mkeywood1/9e8411aef44cf18009aa3e4776501c08 to your computer and use it in GitHub Desktop.

Select an option

Learn more about clone URLs
Save mkeywood1/9e8411aef44cf18009aa3e4776501c08 to your computer and use it in GitHub Desktop.
Download ZIP
Jupyter notebook for fine tuning a T5 small model to generate SQL from natural language
Display the source blob
Display the rendered blob
Raw
Fine tune SQL LLM.ipynb
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
@ss-gonda
Copy link

ss-gonda commented Mar 3, 2025

I repeated all the steps here. For the sample schema and complex sample question it gives expected answer but for multiple other simple questions on same schema it does all wrong answers:
List all departments and the name of their managers (if any).
Find the average salary of all employees in the 'IT_PROG' job.
Show the history of jobs (job titles) held by a specific employee (e.g., EMPLOYEE_ID = 101).

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment