DDPM — MNIST (CPU (80-core))

A demo model from the Data & Impact Accounting (DIA) lab. It performs denoising diffusion generative model (MNIST) via from-scratch DDPM, with the base model trained from scratch, trained on CPU (80-core).

The point of this repo is not the model itself but its dia_report — a standardized record of the energy, carbon, and water used to train it, embedded in this card's metadata.

This footprint feeds the DIA dashboard, which rolls up a base model and all its derivatives to show the cumulative carbon, water, and energy cost of a model family.

Training footprint

Metric Value
Hardware 1× cpu-80core
Compute 0.502 GPU-hours
Energy 0.0244 (measured) kWh
Carbon 0.0016 (measured) kgCO₂eq
Water 0.044–0.098 (estimated-from-default-wue) L
Grid region ca-on

Energy and carbon are measured with CodeCarbon; water is estimated from a default water-usage-effectiveness range. Carbon uses the local grid's intensity (Ontario, ~0.03 kgCO₂eq/kWh).

Reproduce

REPO=DIA-MVP/mnist-ddpm-cpu python scripts/train_ddpm_mnist.py

Links

Downloads last month

-

Downloads are not tracked for this model. How to track
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support