mannix/ ornith-1.5-27b-a3b-coder:Q8_0

317 1 month ago

Code-targeted 184-expert prune of Ornith-1.5-35B-A3B (256e→184e, ~27B, A3B active, top-8). Beats the 256-expert teacher on LiveCodeBench v6 (+6.5pp) and HumanEval+ (+2.4pp) at ~28% fewer experts. Native MTP head + vision tower

vision tools thinking
... /
template
b507b9c2f6ca · 13B
{{ .Prompt }}