llama32-3b-lora-a100

DIA-MVP/llama32-3b-lora-a100

llama32-3b-lora-a100 is a text generation model from DIA-MVP. Use it when you need the model to write or continue text. It is set up for peft. The card lists the license as llama3.2.

A demo model from the Data & Impact Accounting (DIA) lab. It performs instruction-tuning (LoRA adapter) via LoRA (PEFT), with the base model meta-llama/Llama-3.2-3B-Instruct, trained on NVIDIA A100.

Downloads · 30 days

11% of all-time downloads

All-time downloads

Public

Repo size

26.4 MB

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.json17.2 MB · 65%

At a glance

Task: Text Generation
Library: peft
License: llama3.2
Access: Public
Created: Jun 29, 2026
Updated: Jun 29, 2026
SHA: 3b5121b3

Try a prompt

Base models

meta-llama/Llama-3.2-3B-Instruct

Model card

From the Hugging Face model README

Llama 3.2 3B Instruct — 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 meta-llama/Llama-3.2-3B-Instruct, 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	0.3014 GPU-hours
Energy	0.1082 (measured) kWh
Carbon	0.007 (measured) kgCO₂eq
Water	0.195–0.433 (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/llama32-3b-lora-a100 python scripts/train_llama_lora.py