diff options
| author | Yuren Hao <yurenh2@illinois.edu> | 2026-07-10 03:22:47 -0500 |
|---|---|---|
| committer | Yuren Hao <yurenh2@illinois.edu> | 2026-07-10 03:22:47 -0500 |
| commit | cb1c76762e6f8e028c8ed67682917356f935597f (patch) | |
| tree | 2dddcbf760b3a3ea00217d5d40b167a9b6777a60 /ep_run/muon.py | |
| parent | 129aee2fd1fb344c1980ec687d4bff3f9e295734 (diff) | |
QK-norm: replace nn.MHA with explicit SDPA attn + --qk_norm (OLMo2-style, analog-friendly); cancel epoch, insert 8-run qk validation, stage roadmap TinyStories-epoch->FineWeb-Edu->OLMo2
Diffstat (limited to 'ep_run/muon.py')
0 files changed, 0 insertions, 0 deletions