micro-kiki Router v4 β 34-Domain Multi-Label Classifier
MiniLM-L6 embedding + MLP head. Classifies a user prompt into up to 34 domains (sigmoid, not softmax β domains are not mutually exclusive). Used at inference time by the micro-kiki serving layer to pick the top-K LoRA adapters to load alongside the Qwen3.6-35B-A3B base.
Numbers (2026-04-22)
| Metric | Value |
|---|---|
| Train / val | 21 510 / 5 377 |
| top-1 accuracy | 0.464 |
| top-3 accuracy | 0.696 |
Files
router.safetensorsβ MLP head weightslabel_map.jsonβ domain β index mapmeta.jsonβ training config snapshot
Source
Training & serving pipeline at
hypneum-lab/micro-kiki.
Trained by scripts/train_router_v4.py.
Inference Providers NEW
This model isn't deployed by any Inference Provider. π Ask for provider support
Model tree for clemsail/micro-kiki-router-v4
Base model
sentence-transformers/all-MiniLM-L6-v2