Use Hugging Face inline math syntax in the model card

README.md

@@ -33,7 +33,7 @@ CPU.
 
 ## Model
 
-Each row is one location and day, with up to two targets $y_1, y_2$ (log values, standardised).
+Each row is one location and day, with up to two targets \\( y_1, y_2 \\) (log values, standardised).
 
 $$
 \begin{aligned}
@@ -45,16 +45,16 @@ $$
 
 - **Location**: an 8-dim area embedding plus a station offset that starts near zero and is penalised, so a
   station with little data falls back to its area.
-- **Time**: fixed Gaussian bumps $b_k(t) = \exp\{-\tfrac12((t - c_k)/w)^2\}$ with centres every $w$ days, so the
+- **Time**: fixed Gaussian bumps \\( b_k(t) = \exp\big(-\tfrac12((t - c_k)/w)^2\big) \\) with centres every \\( w \\) days, so the
   level is a smooth function of time.
 - **Shared trunk, two heads**: two layers of 64 with SiLU, then one linear head per target. A day where only one
   target was observed still trains everything the other depends on.
 
-**Loss.** An observed value is a mean of $n$ readings, so its variance around the level is $\sigma_j^2 / n + \tau_j^2$,
-with $\sigma_j$, $\tau_j$ learned per target. The Gaussian negative log-likelihood is averaged over observed cells
+**Loss.** An observed value is a mean of \\( n \\) readings, so its variance around the level is \\( \sigma_j^2 / n + \tau_j^2 \\),
+with \\( \sigma_j \\), \\( \tau_j \\) learned per target. The Gaussian negative log-likelihood is averaged over observed cells
 only: a missing target is **masked**, not dropped. Added to it:
 
-- a **curvature penalty** $\lambda \cdot \overline{(\mu_{t+1} - 2\mu_t + \mu_{t-1})^2}$ over every location's
+- a **curvature penalty** \\( \lambda \cdot \overline{(\mu_{t+1} - 2\mu_t + \mu_{t-1})^2} \\) over every location's
   predicted series on the **whole** day grid, observed or not, which keeps the level smooth through gaps;
 - a small L2 penalty on the station offsets.
 
@@ -65,8 +65,8 @@ cross-validation in the post:
 
 | Setting | Value |
 |---|---|
-| curvature penalty $\lambda$ (`rough`) | 1e5 |
-| bump spacing $w$ (`spacing`) | 30 days |
+| curvature penalty \\( \lambda \\) (`rough`) | 1e5 |
+| bump spacing \\( w \\) (`spacing`) | 30 days |
 | hidden width | 64 |
 | learning rate | 5e-3 |
 | weight decay | 1e-4 |