search

defog-ai / sqlcoder

SoTA LLM for converting natural language questions to SQL queries
Apache License 2.0
3.42k stars 218 forks source link

How to fine tune on specific schema? #45

Closed buddyroo30 closed 10 months ago

buddyroo30 commented 1 year ago

In your blog post where you open-sourced sqlcoder, you note that "When fine-tuned on an individual database schema, it matches or outperforms GPT-4 performance." But how exactly do you do this, i.e. fine tune the model to a specific schema? Do you have any documentation how to do this? Do we simply need to generate many many examples for our specific schema (i.e. English language text and corresponding SQL for it) and use that for fine tuning? What specifically should the training data look like? Thanks.

Dev-Force commented 11 months ago

Bump, If anyone has successfully done this before, please give some tips.

github-actions[bot] commented 10 months ago

This issue is stale because it has been open for 30 days with no activity.

github-actions[bot] commented 10 months ago

This issue was closed because it has been inactive for 14 days since being marked as stale.