Open nathan-weinberg opened 1 week ago
Note for this we will need a GPU-enabled runner with the following specs:
Note for this we will need a GPU-enabled runner with the following specs:
- 24GB vram for MT-Bench
This job should be capable:
https://github.com/instructlab/instructlab/pull/1556
I can help get the same thing running on this repo, but it will take some additional repo configuration first.
- 96GB vram for MMLU
do you have an AWS instance type in mind? Ideally the minimal / cheapest type capable of testing this
For the simple flow test, 24GB of vram should work for both. I haven't tried to make it work with less. We've been using g5.4xlarge.
@danmcp has introduced some tests in #9 - we should get testing setup as part of our current CI stack once they are merged in