|
|
|
|
|
|
by cubefox
95 days ago
|
|
|
I think this approach is not so interesting because it's just quantization of a full precision model. So it speeds up inference (at a quality penalty) but not training. It would be more interesting to train an actually binary model directly, without any floating point multiplication, like in this paper: https://proceedings.neurips.cc/paper_files/paper/2024/hash/7... |
|
|