Estimates training emissions of top HF open-source models at 6.0e4 metric tons CO2e via tiered metadata handling and introduces ATCI as emissions-per-compute metric.
These files provide parameter counts, layer depths, hidden sizes, patch sizes, and other FLOPs-relevant attributes
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CY 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Hugging Carbon: Quantifying the Training Carbon Emissions of AI Models at Scale
Estimates training emissions of top HF open-source models at 6.0e4 metric tons CO2e via tiered metadata handling and introduces ATCI as emissions-per-compute metric.