Skip to content

Add optional QK normalization, RMSNorm and SwiGLU to MoT experts - #321

Draft
ElmoPA wants to merge 1 commit into
codex/elmo-large-continuous-20261026-v1from
codex/elmo-qknorm-swiglu-rmsnorm-20261026-v1
Draft

ElmoPA wants to merge 1 commit into
codex/elmo-large-continuous-20261026-v1from
codex/elmo-qknorm-swiglu-rmsnorm-20261026-v1

Add optional QK normalization, RMSNorm and SwiGLU to MoT experts

82f6549
Select commit
Loading
Failed to load commit list.