correct arch line count

README.md

@@ -75,7 +75,7 @@ headaches.
   single Charbonnier loss for the base stage.
 - **Small and fast.** ~1.8M params — SPAN-class size but conv-only, suited to
   mobile, edge, web and game engines.
-- **Maintainable for years.** One op set, no exotic dependencies, ~90-line arch.
+- **Maintainable for years.** One op set, no exotic dependencies, ~85-line arch.
 
 **When to pick something else.** If the goal is maximum PSNR/LPIPS on academic
 benchmarks, or a large transformer, NERVE is not aiming there — use HEART, HAT,
@@ -243,7 +243,7 @@ everything that actually matters in production:
 - **One variant.** No S/M/L, no fused vs unfused, no attention-window caveats.
 - **Clean to train.** Norm-free, bf16-stable, a single loss for the base stage.
 - **Clean to deploy.** Standard ops only; what you train is what you export.
-- **Maintainable.** One ~90-line arch file a maintainer can read in full.
+- **Maintainable.** One ~85-line arch file a maintainer can read in full.
 
 It does **not** chase benchmark leaderboards. It is the model you can hand to
 someone and they can train, export, and ship it the same afternoon.