DIA-MVP/tinyllama-lora-cpu

TinyLlama 1.1B Chat — LoRA (CPU (80-core))

A demo model from the Data & Impact Accounting (DIA) lab. It performs instruction-tuning (LoRA adapter) via LoRA (PEFT), with the base model TinyLlama/TinyLlama-1.1B-Chat-v1.0, 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	1.0613 GPU-hours
Energy	0.0515 (measured) kWh
Carbon	0.0033 (measured) kgCO₂eq
Water	0.093–0.206 (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/tinyllama-lora-cpu python scripts/train_llama_lora.py

Links

• Footprint table (dataset): DIA-MVP/dia-state-lab-2026
• Project / paper: ai-impact-accounting
• Lab workflow: see LAB.md in the repo