Upload folder using huggingface_hub

README.md

@@ -48,7 +48,7 @@ A diagram becomes its Gauss sequence: walk the knot and, at each crossing, recor
 | Parameters | 4,924,943 (6 layers, width 256) |
 | Steps | 20000, 512 knots (two diagrams each) per step |
 | Learning rate | 0.0003, cosine; temperature 0.05 |
-| Final loss | 0.2043 (contrastive 0.1145) |
+| Final loss | 0.6226 (contrastive 0.1426) |
 | Hardware | NVIDIA A10G, 102 min |
 
 ## 📊 Results
@@ -57,8 +57,8 @@ Each test diagram is a fresh scramble. The model names it by the nearest canonic
 
 | Knots | n | Top-1 | Top-5 | Signature | Determinant ±10% | Volume MAE |
 |---|---|---|---|---|---|---|
-| seen | 46676 | 0.849 | 0.973 | 0.794 | 0.199 | 1.507 |
-| unseen | 5184 | 0.856 | 0.969 | 0.781 | 0.207 | 1.583 |
+| seen | 46676 | 0.881 | 0.976 | 0.917 | 0.267 | 1.237 |
+| unseen | 5184 | 0.88 | 0.976 | 0.891 | 0.248 | 1.39 |
 
 Chance top-1 is 7.7e-05. For an exact answer, use SnapPy's `identify()`.