tvetus

joined 1 year ago
[โ€“] tvetus@alien.top 1 points 11 months ago

at full precision

Full precision is not as useful as you think. Even at 4bit, the losses are not that large.

70B

What is your motivation for such large models? You're sacrificing a lot of speed for the larger model.

[โ€“] tvetus@alien.top 1 points 1 year ago

Can be hard to rent if all the capacity is bought out. But if it's just 1 DGX then they might be better off renting.