Upload trained MNIST distilled student model

README.md

@@ -0,0 +1,76 @@
+---
+tags:
+- pytorch
+- mnist
+- image-classification
+- computer-vision
+- knowledge-distillation
+library_name: pytorch
+---
+
+# MNIST Distilled Student Model
+
+A neural network trained on the MNIST dataset using knowledge distillation from a teacher model.
+
+## Model Description
+
+This is a StudentNet model trained on MNIST using knowledge distillation with the following architecture:
+- Fully connected: 28 × 28 → 128 → 10 (output)
+- ReLU activation
+
+The model was trained using knowledge distillation, combining:
+- KL divergence between student and teacher logits (with temperature scaling)
+- Cross-entropy loss on true labels
+
+## Training Details
+
+### Training Hyperparameters
+- **Batch size**: 128
+- **Epochs**: 10
+- **Learning rate**: 0.001
+- **Weight decay**: 0.0
+- **Optimizer**: AdamW
+- **Training set size**: 50,000
+- **Validation set size**: 10,000
+- **Test set size**: 10,000
+- **Device**: cuda
+- **Seed**: 42
+
+### Distillation Parameters
+- **Temperature**: 3.0
+- **Alpha (KL weight)**: 0.5
+
+The loss function is: `loss = alpha × KL_loss + (1 - alpha) × CE_loss`
+
+### Results
+- **Test Accuracy**: 0.9785
+- **Test Loss**: 0.0808
+
+## Usage
+
+```python
+import torch
+from pathlib import Path
+
+# Download the model
+model_path = "model.pt"
+state_dict = torch.load(model_path)
+
+# Load into your StudentNet architecture
+# (you'll need to define the StudentNet class from the training script)
+model = StudentNet()
+model.load_state_dict(state_dict)
+model.eval()
+
+# Make predictions
+with torch.no_grad():
+    predictions = model(images)
+```
+
+## Dataset
+
+The model was trained on the [MNIST dataset](http://yann.lecun.com/exdb/mnist/), which contains 70,000 grayscale images of handwritten digits (0-9), each 28x28 pixels.
+
+## Model Card Authors
+
+Generated automatically during training.

config.json

@@ -0,0 +1,16 @@
+{
+  "architecture": "StudentNet",
+  "task": "MNIST classification",
+  "training_method": "knowledge_distillation",
+  "batch_size": 128,
+  "epochs": 10,
+  "learning_rate": 0.001,
+  "weight_decay": 0.0,
+  "trainset_size": 50000,
+  "temperature": 3.0,
+  "alpha": 0.5,
+  "seed": 42,
+  "device": "cuda",
+  "test_accuracy": 0.9785,
+  "test_loss": 0.08084478095881059
+}

model.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:90ec13a90e328db6e574865522183f13896bb315895695782e48319f728a9cf0
+size 409353