Skip to content
ModelListedExternal
Download

Tiny Mnist Classifier

Parameters: 970 (<1000) Test accuracy: 92.35% Epochs trained: 45 (early stopping after 5 epochs without improvement)

Sourcehuggingface.co/sapbot/tiny-mnist-classifier/tree/3497b15b204b634bd8224eb166221098d45b20e5
KindOtherVersionRevision 3497b15

Model source

Kind
Other
File size
5.88 KB
Version
vRevision 3497b15
Updated
Sep 28, 2026
Downloads
0
Source
Hugging Face

Source description

Tiny MNIST Classifier

  • Parameters: 970 (<1000)
  • Test accuracy: 92.35%
  • Epochs trained: 45 (early stopping after 5 epochs without improvement)

This model was trained on RX 6600.

Full results

MetricValue
Total parameters970
Best validation loss0.2463
Final test accuracy92.35%
Early stopping patience5
Training epochs45

Model architecture

AvgPool(4x4) → Linear(49→16) → ReLU → Dropout(0.2) → Linear(16→10)

How to use

import torch
from train import TinyMNISTModel

model = TinyMNISTModel()
model.load_state_dict(torch.load("mnist_1k_best.pth"))
model.eval()

Sources

1 source
Hugging FacePrimaryVersion 3497b15b204b634bd8224eb166221098d45b20e5
huggingface.co/sapbot/tiny-mnist-classifier/tree/3497b15b204b634bd8224eb166221098d45b20e5

Verified Sep 28

Model artifacts

1 artifact

mnist_1k_best.pth

pth · 5.88 KB · SHA-256 dc2c283e0d10…37af · Hugging Face

Download

Source excerpts

2 excerpts
ReadmeSep 28huggingface.co/sapbot/tiny-mnist-classifier

--- language: en license: cc0-1.0 tags: - mnist - tiny-model - early-stopping pipeline_tag: image-classification --- # Tiny MNIST Classifier - **Parameters**: 970 (<1000) - **Test accuracy**: 92.35% - **Epochs trained**: 45 (early stopping after 5 epochs without improvement) This model was trained on RX 6600. ## Full results | Metric | Value | |---------------------------|-----------------| | Total parameters | 970 | | Best validation loss | 0.2463 | | Final test accuracy | 92.35% | | Early stopping patience | 5 | | Training epochs | 45 | ## Model architecture AvgPool(4x4) → Linear(49→16) → ReLU → Dropout(0.2) → Linear(16→10) ## How to use ```python import torch from train import TinyMNISTModel model = TinyMNISTModel() model.load_state_dict(torch.load("mnist_1k_best.pth")) model.eval() ```

NoteSep 28huggingface.co/sapbot/tiny-mnist-classifier

Source context: 0 downloads · 0 likes · Pipeline image-classification · Repo sapbot/tiny-mnist-classifier