Henry Ndubuaku
|
ffb1c5144c
|
Update simple_attention_networks.md
|
2026-07-01 07:26:23 -07:00 |
|
Jakub Mroz
|
34861f39ae
|
Add finetune data format docs and per-tool warning; align tool schema across codebase (#26)
Signed-off-by: jakmro <kubamroz124@gmail.com>
|
2026-05-15 09:17:24 -07:00 |
|
HenryNdubuaku
|
b4a4d5bcd3
|
update configs
|
2026-05-13 10:42:05 +01:00 |
|
HenryNdubuaku
|
6df3884354
|
Fix naming
|
2026-05-12 18:04:49 +01:00 |
|
HenryNdubuaku
|
1807b1d230
|
updates
|
2026-05-12 17:02:15 +01:00 |
|
HenryNdubuaku
|
ddf80e0852
|
cleanup
|
2026-03-15 02:09:06 +00:00 |
|
Noah Cylich
|
8648e0e697
|
updated baseline results
|
2026-03-06 15:07:14 -08:00 |
|
Noah Cylich
|
7d8f27d424
|
Merge branch 'main' into fixed-mrl
|
2026-03-06 13:49:33 -08:00 |
|
Noah Cylich
|
4965912099
|
matryoshka in mixer, fixed and removed all references to MRL
|
2026-03-06 11:32:24 -08:00 |
|
Noah Cylich
|
c5096577ad
|
1 additional ablation
|
2026-03-06 02:25:39 -08:00 |
|
Karen Mosoyan
|
8db045baf5
|
more planning
|
2026-03-06 01:17:30 -08:00 |
|
Noah Cylich
|
cbc38056e6
|
proper matryoshka and results
|
2026-03-05 19:53:31 -08:00 |
|
Karen Mosoyan
|
4ca75ed56f
|
added post and pretraining docs
|
2026-03-05 16:34:03 -08:00 |
|