Upload README.md with huggingface_hub

README.md

@@ -68,7 +68,7 @@ to **6e-08**, so these are apples-to-apples.
 
 | | DaisyChain | Carbon-500M |
 |---|---|---|
-| **Routing accuracy** (held-out) | **99.8%** | — |
+| **Routing accuracy** (held-out) | **100.0%** | — |
 | **Likelihood — base-pair bits/base** (↓) | **1.876** | **1.787** |
 | Seq-recovery, eukaryote (FNS, ↑) | 31.5% | 38.9% |
 | Seq-recovery, bacteria (FNS, ↑) | 40.9% | 54.1% |
@@ -89,7 +89,7 @@ benchmarks" — so it's a fair, achievable target, not the 3B/8B flagships.
 We build in the open, mistakes included. This project's honest history:
 
 **What worked**
-- **Per-domain specialists + a learned router** reached **99.8%** held-out routing — one ~74M model active per query.
+- **Per-domain specialists + a learned router** reached **100%** held-out routing — one ~74M model active per query.
 - **Snapshot-then-pick-best** distillation: snapshot every few thousand steps, deploy the snapshot with the
   best *held-out* score, never the last one. This caught over-distillation (models that memorize the distill
   cache and regress on held-out data) and made every round regression-guarded.