biondizzle 483046b9d6 fix: shared_experts gate_up_proj stacking was skipped by .experts. check ...

The stacking logic skipped any key containing '.experts.' to avoid
MoE routed expert weights. But 'shared_experts' also matches that
substring, so gate_proj and up_proj were never stacked into
gate_up_proj. Changed to '.ffn.experts.' which only matches the
routed experts path.

Also includes POST-LOAD all-zero param scan.

2026-05-15 00:08:04 +00:00

..

patches

fix: shared_experts gate_up_proj stacking was skipped by .experts. check

2026-05-15 00:08:04 +00:00