-
Notifications
You must be signed in to change notification settings - Fork 39
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
[sharktank] Evaluation - Add Perplexity test #286
Conversation
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.
The diff between the original and this PR looks good to make progress while keeping the other CI builds working.
I would like to see my other comments addressed at some point though:
- Have the test download/cache the input gguf/json files instead of assume that they exist at some
/data/extra/models/
path on the CI runner, so developers can also run these tests themselves. - Organize
requirements.txt
intosharktank/requirements-tests.txt
so we can track what each subproject needs for devs/users/tests at a fine granularity.
Co-authored-by: Scott Todd <[email protected]>
…tform into perplexity-test
…tform into perplexity-test
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.
Some minor comments that could be done in a follow up PR
@@ -0,0 +1,213 @@ | |||
{ |
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.
can we just store these values in a npy file or something and retrieve from sharkblobs?
Add Perplexity test for LLM evaluation