Upload model card

README.md

@@ -1,5 +1,7 @@
 ---
 license: mit
+library_name: pytorch
+pipeline_tag: image-classification
 tags:
   - image-to-text
   - ocr
@@ -8,43 +10,33 @@ tags:
   - pytorch
   - cnn
   - image-classification
-  - epochs-150
-  - batch-size-16
-  - learning-rate-3e-4
-  - input-size-128
-  - num-classes-27
-  - early-stopping-15
-  - save-every-5-epochs
-  - optimizer-adam
-  - weight-decay-0.0001
-  - augmentation
-  - model-type-custom
+
+# Shown in model card widget (with model.safetensors)
+model_size: "13.6M params"
+tensor_type: "F32"
+format: Safetensors
+training_epochs: 150
+
 ---
 
 # Moon Cipher Detector (Classifier)
 
 CNN classifier for **moon cipher** glyph recognition: 27 classes (A–Z plus `~`). Input: 128×128 grayscale glyph crop. Use with a detector for full image decoding.
 
-## Training config
-
-| Epochs | Batch size | Learning rate | Input size | Num classes | Early stopping | Augmentation |
-|--------|------------|---------------|------------|-------------|----------------|--------------|
-| 150 | 16 | 3e-04 | 128×128 | 27 | 15 | True |
+**Model card (right sidebar):** This repo includes **Safetensors** (`model.safetensors`), so the Hub shows **Model size**, **Tensor type (F32)**, and format. Best checkpoint from training (up to 150 epochs).
 
 ## Model metadata
 
 | Model | Format | Size | Params | Tensor type |
 |-------|--------|------|--------|--------------|
-| Classifier (`best_classifier.pth`) | PyTorch .pth (state_dict) | 51.98 MB | 13,616,347 params | F32 |
-
-Weights are saved as **PyTorch state dict** (`.pth`), not Safetensors. Load with `torch.load(..., weights_only=True)`.
+| Classifier (`model.safetensors`) | Safetensors | 51.98 MB | 13,616,347 params | F32 |
 
 ## Usage
 
 ### 1. Install
 
 ```bash
-pip install torch torchvision huggingface_hub
+pip install torch torchvision huggingface_hub safetensors
 ```
 
 ### 2. Download from Hugging Face
@@ -52,9 +44,10 @@ pip install torch torchvision huggingface_hub
 ```python
 from huggingface_hub import hf_hub_download
 
+# Safetensors (preferred; used for Hub widget)
 model_path = hf_hub_download(
     repo_id="nhellyercreek/moon-cipher-detector",
-    filename="best_classifier.pth"
+    filename="model.safetensors"
 )
 mappings_path = hf_hub_download(
     repo_id="nhellyercreek/moon-cipher-detector",
@@ -64,12 +57,13 @@ mappings_path = hf_hub_download(
 
 ### 3. Load and run
 
-Use `MoonClassifier` from the Moon-Cipher-Detector repo (`models/moon_classifier.py`). Load with `torch.load(model_path, weights_only=True)` and pass 128×128 grayscale glyph crops.
+Use `MoonClassifier` from the Moon-Cipher-Detector repo (`models/moon_classifier.py`). Load Safetensors with `safetensors.torch.load_file(model_path)` and `model.load_state_dict(state_dict)`, or use `best_classifier.pth` with `torch.load(..., weights_only=True)`. Input: 128×128 grayscale glyph crops.
 
 ## Config
 
 - **Classes**: 27 (A–Z + `~`)
 - **Architecture**: Custom CNN (MoonClassifier), 128×128 input.
-- **Weight format**: PyTorch `.pth` (state_dict), **tensor type**: F32.
+- **Format**: Safetensors + PyTorch `.pth`, **tensor type**: F32.
+- **Training**: Best checkpoint (up to 150 epochs).
 
-See `config.json` for machine-readable settings (params, size, format).
+See `config.json` for machine-readable settings (params, size, format, training_epochs).