Comment by littlestymaar
6 months ago
If what you refer to by “on demand training ” is fine tuning, it's going to be much more efficient on a small model than a big one.
6 months ago
If what you refer to by “on demand training ” is fine tuning, it's going to be much more efficient on a small model than a big one.
LoRA can work with big models. But I mean sample-efficient RL.