Downloads · 30 days
0
green-ai-carbon-audit
24ds2000033/green-ai-carbon-audit
green-ai-carbon-audit is a machine learning model from 24ds2000033. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
This model card documents the environmental impact of the assigned GPU training run.
Access
Public
Updated Aug 25, 2026
Repo size
—
Likes
0
Public
Repo makeup
Click a slice to open those files.
Other1.5 KB · 55%
At a glance
- Access
- Public
- Created
- Aug 25, 2026
- Updated
- Aug 25, 2026
- SHA
- 4ee72a42
Model card
From the Hugging Face model README
Green AI Training Run
Carbon Accounting
This model card documents the environmental impact of the assigned GPU training run.
Training Information
| Parameter | Value |
|---|---|
| GPU | NVIDIA H100 |
| Number of GPUs | 1 |
| GPU runtime | 164.8 hours |
| GPU TDP | 700 W |
| Power Usage Effectiveness | 1.42 |
| Region | europe-west4 |
| Training type | fine-tuning |
| Grid carbon intensity | 200 gCO2eq/kWh |
Energy Calculation
The required formula is:
energy_kWh = (gpu_type_TDP_watts * num_gpus * gpu_hours * power_usage_effectiveness) / 1000
Substituting the training run values:
energy_kWh = (700 * 1 * 164.8 * 1.42) / 1000
Therefore:
163.8112 kWh
Carbon Emissions Calculation
The required formula is:
co2_kg = (energy_kWh * region_carbon_intensity_gCO2_per_kWh) / 1000
Using the assigned grid intensity:
co2_kg = (163.8112 * 200) / 1000
Therefore:
32.762 kg CO2eq
Carbon Footprint Metadata
The co2_eq_emissions metadata above records the calculated carbon
emissions for this training run, rounded to three decimal places.
- Created
- Aug 25, 2026
- Updated
- Aug 25, 2026