-
Notifications
You must be signed in to change notification settings - Fork 5k
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Ability to fine tune custom model on conversable agents #1787
Conversation
Codecov ReportAll modified and coverable lines are covered by tests ✅
Additional details and impacted files@@ Coverage Diff @@
## main #1787 +/- ##
=======================================
Coverage 37.33% 37.33%
=======================================
Files 64 64
Lines 6913 6913
Branches 1519 1519
=======================================
Hits 2581 2581
Misses 4109 4109
Partials 223 223
Flags with carried forward coverage won't be shown. Click here to find out more. ☔ View full report in Codecov by Sentry. |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Thanks so much for this PR. Very needed!
I think we may want to add a very brief working example here. Let's brainstorm together.
samples/tools/finetuning/finetuning/conversable_agent_update_model.py
Outdated
Show resolved
Hide resolved
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Consider subclassing the core lib instead of modifying it so changes in this tool can move fast by itself.
samples/tools/finetuning/tests/test_conversable_agent_update_model.py
Outdated
Show resolved
Hide resolved
samples/tools/finetuning/tests/test_conversable_agent_update_model.py
Outdated
Show resolved
Hide resolved
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
I think we can remove the skips for the tests as all of them do not require OpenAI.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
LGTM. Thanks for the hard work!
* uAbility to update_model on conversable agents * formatting * formatting * move code from conversable agent into samples/tools and add testing and README * forgot install step * fix * leave core lib unchanged and move everything to samples/tools * remove skip openai --------- Co-authored-by: Eric Zhu <ekzhu@users.noreply.github.com>
Why are these changes needed?
Agent's with custom models should be able to accept feedback and fine tune their underlying models.
Related issue number
Checks