Modelpublic

DIA-MVP/qwen2.5-7b-lora-a100

sourceHugging Faceapache-2.0updated 3mo agoView on Hugging Face

0likes8downloads

Model Card

Qwen2.5-7B — LoRA (NVIDIA A100)

A demo model from the Data & Impact Accounting (DIA) lab. It performs instruction-tuning (LoRA adapter) via LoRA (PEFT), with the base model Qwen/Qwen2.5-7B, trained on NVIDIA A100.

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 A100-SXM4-80GB
Compute	1.6199 GPU-hours
Energy	0.6828 (measured) kWh
Carbon	0.0442 (measured) kgCO₂eq
Water	1.229–2.731 (estimated-from-default-wue) L
Grid region	ca-on

Energy and carbon are measured with [CodeCarbon](https://github.com/mlco2/codecarbon); water is estimated from a default water-usage-effectiveness range. Carbon uses the local grid's intensity (Ontario, ~0.03 kgCO₂eq/kWh).

Reproduce

bash

REPO=DIA-MVP/qwen2.5-7b-lora-a100 python scripts/train_qwen_lora.py

Qwen2.5-7B — LoRA (NVIDIA A100)

Training footprint

Reproduce

Links