Hk-12-34/green_ai

Model Card Environmental Impact

This model was fine-tuned with the following estimated environmental impact, computed from GPU runtime and datacenter PUE:

Hardware Type: NVIDIA V100 (8x GPUs) GPU Hours: 73.2 hours Power Usage Effectiveness (PUE): 1.1 Total Energy Consumed: 193.248 kWh Region: europe-north1 Grid Carbon Intensity: 120 gCO2eq/kWh Carbon Emitted: 23.190 kg CO2eq

Carbon emissions were estimated using the Machine Learning Impact calculator methodology, following the formulas:

energy_kWh = (TDP_watts * num_gpus * gpu_hours * PUE) / 1000 co2_kg = (energy_kWh * region_carbon_intensity_g_per_kWh) / 1000 Training Details Training regime: fine-tuning Hardware: 8x NVIDIA V100 (TDP 300W each) Datacenter location: europe-north1