22429ea536
Feat: added classification methods
0ad182f2b9
Feat: added classification for all data, including non-mdm, as a
7e1f45f466
Chore: removing old files and some experiments
0762c02b31
Feat: implemented attention layer in equinox
a817fe16cc
Feat: increased learning rate for effective large batch size learning
aca80720c8
Feat: t5_jax_simple_parallel implements a working example of fsdp
429e1742ab
Feat: flax pjit example
f169e18ea3
Feat: added up to dep6-3
31772fec80
Bug: fixed korean empty string issue
32363c9d7b
Feat: implement i18n support
2e29c70d17
Fix: remove bug causing clicking on text linking to first box
39b3570e11
Feat: changed benchmark procedure to use parallel
7b875ba141
Feat: added graph generation for barabasi-albert and regular
803274cb80
Feat: benchmarked north, rome and steinlib
b05b8410d3
Feat: added 3 approaches to get MPS: planarity test, exact via ILP, and
850255fab2
Chore: re-organized to only have folders relevant to benchmarking
aa3c3e3b20
Feat: merge with read_once branch
e35462ef2d
Feat: remove random mutation and introduce mutation point as argument