I'm having trouble understanding how to run a model graded eval #1341
Unanswered
mayalinetsky-kryon
asked this question in
Q&A
Replies: 2 comments
-
Hey, I've recently got 2 pull requests approved on this, check out gpt4facts and A is B, B is A pull requests. Something that also helps is to checkout merged pull requests that used modelgraded. There is also some documentation on them and I suggest reading the files on modelgraded to see what it is doing and how it works. |
Beta Was this translation helpful? Give feedback.
0 replies
-
I also have hard time understanding how to use model graded eval, could someone please give a concrete example (like a command)? |
Beta Was this translation helpful? Give feedback.
0 replies
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Uh oh!
There was an error while loading. Please reload this page.
-
Hey,
I've read the documentations about how to run an eval, but I could not figure out how to run the ones under evals/registry/modelgraded (and specifically I want closedqa.yaml).
I'm interested in running a modelgraded eval on gpt-3.5-turbo with a custom system message.
How do I do that?
Where does the system message come in?
Beta Was this translation helpful? Give feedback.
All reactions