Update best model - Epoch 0 - Acc: 0.1099

README.md

@@ -0,0 +1,78 @@
+---
+tags:
+- vision
+- image-classification
+- fractal-positional-encoding
+- geometric-deep-learning
+- devil-staircase
+- simplex-geometry
+license: mit
+---
+
+# ViT-Beatrix: Fractal PE + Geometric Simplex Vision Transformer
+
+This model integrates Devil's Staircase positional encoding with geometric simplex features
+for vision tasks. Trained on CIFAR-10.
+
+## Model Details
+
+- **Architecture**: Vision Transformer with fractal positional encoding
+- **Dataset**: CIFAR-100 (100 classes)
+- **Embedding Dimension**: 512
+- **Depth**: 4 layers
+- **Patch Size**: 4x4
+- **PE Levels**: 12
+- **Simplex Dimension**: 5-simplex
+
+## Training
+
+- **Dataset**: CIFAR-100
+- **Epochs**: 0
+- **Best Accuracy**: 0.1099
+- **Batch Size**: 512
+- **Learning Rate**: 0.001
+
+## Loss Components
+
+- Task Loss Weight: 1.0
+- Flow Alignment Weight: 0.5
+- Coherence Weight: 0.3
+- Multi-Scale Weight: 0.2
+
+## Usage
+
+```python
+from geovocab2.train.model.vit_beatrix import SimplifiedGeometricClassifier
+from safetensors.torch import load_file
+
+# Load model
+model = SimplifiedGeometricClassifier(
+    num_classes=100,  # CIFAR-100
+    img_size=32,
+    embed_dim=512,
+    depth=4
+)
+
+# Load weights (renamed from model_best.safetensors to model.safetensors in Hub)
+state_dict = load_file("model.safetensors")
+model.load_state_dict(state_dict)
+model.eval()
+
+# Inference
+output = model(images)
+```
+
+## Citation
+
+```bibtex
+@misc{vit-beatrix,
+  author = {AbstractPhil},
+  title = {ViT-Beatrix: Fractal Positional Encoding with Geometric Simplices},
+  year = {2025},
+  url = {https://github.com/AbstractEyes/lattice_vocabulary}
+}
+```
+
+## License
+
+MIT License

config.json

@@ -0,0 +1,43 @@
+{
+  "num_classes": 100,
+  "img_size": 32,
+  "patch_size": 4,
+  "embed_dim": 512,
+  "k_simplex": 5,
+  "depth": 4,
+  "num_heads": 8,
+  "mlp_ratio": 4.0,
+  "dropout": 0.0,
+  "pe_levels": 12,
+  "pe_features_per_level": 2,
+  "pe_smooth_tau": 0.25,
+  "simplex_feature_weight": 0.2,
+  "batch_size": 512,
+  "num_epochs": 50,
+  "learning_rate": 0.001,
+  "weight_decay": 0.005,
+  "warmup_epochs": 10,
+  "task_loss_weight": 1.0,
+  "flow_loss_weight": 0.5,
+  "coherence_loss_weight": 0.3,
+  "multiscale_loss_weight": 0.2,
+  "volume_reg_weight": 0.1,
+  "use_augmentation": true,
+  "mixup_alpha": 0.2,
+  "cutmix_alpha": 1.0,
+  "device": "cuda",
+  "num_workers": 2,
+  "pin_memory": true,
+  "save_dir": "./checkpoints",
+  "save_every": 10,
+  "use_safetensors": true,
+  "timestamp_dirs": true,
+  "push_to_hub": true,
+  "hub_model_id": "AbstractPhil/vit-beatrix",
+  "hub_upload_best_only": true,
+  "use_tensorboard": true,
+  "log_dir": "./logs",
+  "log_every": 50,
+  "train_baseline": false,
+  "hub_token": null
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fe1e10a0a0c80c671a546fb82bc663d8754fe57e9fc1457f0c4f2da12c41f607
+size 50831604