You are viewing a plain text version of this content. The canonical link for it is here.

Posted to issues@madlib.apache.org by "Frank McQuillan (Jira)" <ji...@apache.org> on 2023/04/23 16:14:00 UTC

[jira] [Created] (MADLIB-1513) Fine tune large language models

Frank McQuillan created MADLIB-1513:
---------------------------------------

             Summary: Fine tune large language models
                 Key: MADLIB-1513
                 URL: https://issues.apache.org/jira/browse/MADLIB-1513
             Project: Apache MADlib
          Issue Type: New Feature
            Reporter: Frank McQuillan


As a follow on to 
https://issues.apache.org/jira/browse/MADLIB-1512

It would be very useful to fine tune LLMs based on data residing in the database. In this way, the MADlib community could start with a foundational model, incorporate new data on top and fine tune, then have a customized model for their specific use case.





--
This message was sent by Atlassian Jira
(v8.20.10#820010)