Spaces:
Running
on
CPU Upgrade
Running
on
CPU Upgrade
Leaderbord NOT up to date.
#93
by
hilmi1
- opened
There came a lot of new models such as ROBIN V2 and GPlatty-30B, they both perform 20 - 35 % better than Falcon, why are they not on the leaderbord? Robin V2 got released like 3 weeks ago, this is not good for open-source..
Hi! Feel free to submit new models to the queue!
However, we are at the moment re-running all the leaderboard after the MMLU discoveries and Harness update - we want to make sure all displayed scores are correct
I keep getting an error when I try to submit to the queue
What is the error you are getting?
Hi @ariellee could you try again and tell me if you still get an error?
Hi @ariellee could you try again and tell me if you still get an error?
It works now! Thank you so much 🤗
clefourrier
changed discussion status to
closed