README.md

metadata

library_name: peft
tags:
  - dia
  - carbon-footprint
  - energy-efficiency
  - sustainability
dia_report:
  scope: incremental
  lineage:
    - model: TinyLlama/TinyLlama-1.1B-Chat-v1.0
      relation: lora
  compute:
    hardware:
      gpu: NVIDIA A40
      count: 1
    duration_gpu_hours: 0.0415
  footprint:
    energy_kwh:
      value: 0.0122
      quality: measured
    carbon_kgco2eq:
      value: 0.0008
      quality: measured
    water_liters:
      value:
        - 0.022
        - 0.049
      quality: estimated-from-default-wue
  context:
    region: ca-on
    carbon_intensity: 0.03
    wue_l_per_kwh:
      - 1.8
      - 4
  tool: codecarbon
dia_version: '0.1'
license: apache-2.0
pipeline_tag: text-generation
base_model: TinyLlama/TinyLlama-1.1B-Chat-v1.0

TinyLlama 1.1B Chat — LoRA (NVIDIA A40)

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 NVIDIA A40.

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× NVIDIA A40
Compute	0.0415 GPU-hours
Energy	0.0122 (measured) kWh
Carbon	0.0008 (measured) kgCO₂eq
Water	0.022–0.049 (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-a40 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