-
Notifications
You must be signed in to change notification settings - Fork 47
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
Fix mixture endpoint #536
base: staging
Are you sure you want to change the base?
Fix mixture endpoint #536
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.
Have you tested whether the response is still instance. Use a query like e.g.
Write a short story about an elephant shrew
with streaming=True. We would expect that streaming only starts after ~10+ seconds seeing that the miners need to generate the initial stories. Is that confirmed to be the case?
Mixture is 2x slower. In the PR description response it's obvious it uses the context of previous responses. |
mixture 46s
23s
|
Changes
Example from live test
Query:
Say 10 random numbers between 1 and 100
withmixture=True
: