Skip to content
Other

PyramidDiff

a model for analyzing and generating population pyramids

2 min readupdated

PyramidDiff is a compact conditional diffusion model (a 1D UNet—a one-dimensional network for sequential data—with around 7.3 million parameters) trained on the UN World Population Prospects 2024 dataset. It is built to generate and refine national population structures by age and sex, helping smooth out age distortions in statistics, fill in missing data, and sanity-check demographic pyramids. The tool is aimed at demographers, data researchers, and statistical system developers.

Key features

  • Trained on UN data (World Population Prospects 2024) covering countries worldwide from 1950 to 2023.
  • Uses a 1D UNet architecture with around 7.3M parameters to model age distributions.
  • Supports correcting age distortions and rounding artifacts in statistical data.
  • Generates plausible pyramids conditioned on summary metrics like median age and sex ratio.

What you can do

  • Generate synthetic population age pyramids for a specific year and target demographic parameters.
  • Clean up age rounding errors (age heaping) in statistical datasets.
  • Spot anomalies and implausible distributions in demographic reports using denoising error scoring.

Example

from huggingface_hub import snapshot_download
import importlib.util, os
p = snapshot_download("SallySims/pyramiddiff-wpp2024")
spec = importlib.util.spec_from_file_location("pyramiddiff", os.path.join(p, "pyramiddiff.py"))
P = importlib.util.module_from_spec(spec); spec.loader.exec_module(P)
model, diff, norm = P.load_pretrained(p)
samples = P.generate(model, diff, norm, median_age=20, u15=0.42, p65=0.03, sex_ratio=99, year=2005)
Read moreDetails
• Architecture: 1D UNet, ~7.3M parameters
• MAE score: best result using PCHIP initialization is 0.103
• Limitations: research prototype trained on smoothed UN estimates, not intended for official statistics
• Dataset: UN World Population Prospects 2024 (1950–2023)
Discuss Telegram 0 25

Will it run?

Runs in F32

Fits without quantisation.

  • F32weights 0.0 GB · ready files0.5 GB
  • BF16weights 0.0 GB0.5 GB
  • FP8 / INT8recommendedweights 0.0 GB0.5 GB
  • 4-bitweights 0.0 GB0.5 GB

Tip: go 8-bit.FP8 / INT8 is within about a percent of full precision in quality, takes half the memory and runs faster on RTX 40/50 and H100. Full precision only pays off for fine-tuning.

What to get for this model

Massed ComputeOpen Massed Compute

Your own GPU: FP8 / INT8 — from RTX 2060 · F32 — from RTX 2060

Massed Compute hourly prices, November 2026. The discounted price applies with the coupon at checkout.

Estimate: weights plus working memory. Long videos, high resolutions and long contexts need more.

Run it on Massed Compute

The script downloads the model to the rented machine. How to run it is in the model card.

  1. 1. Rent a machine with a fitting GPU

    Open Massed Compute
  2. 2. Paste the script into the machine's terminal

    Connect over SSH (the Massed Compute panel shows the command) or open a terminal on the machine's desktop.

    HF_TOKEN / CIVITAI_TOKENThe script starts with token lines: paste yours between the quotes. The Hugging Face token is for gated models, the Civitai one for Civitai models.

    # SallySims/pyramiddiff-wpp2024
    mkdir -p ~/models
    curl -LsSf https://astral.sh/uv/install.sh | sh
    source "$HOME/.local/bin/env"
    uv tool install "huggingface_hub[cli]"
    hf download SallySims/pyramiddiff-wpp2024 --local-dir ~/models/pyramiddiff-wpp2024
    # The model is in ~/models. How to run it is in the model card (link above).
    Add more LoRAs to pyramiddiff-wpp2024
  3. 3. Use it

    The model is in ~/models. How to run it is in the model card (link above).

Stop the machine in the panel when you are done: it bills by the minute while it runs.

How to speed it up

Picked for this model type. Choose your hardware above to see what fits you exactly.

  • FlashAttention 44.0.0b40from November 18, 2026new release

    fastest exact attention on B200

    Kernels for Blackwell (beta). Exact attention without quantisation — fine for everything, LLMs included.

    How to enable: pip install flash-attn-4; vLLM and SGLang pick it up themselves.

    Earlier generations (2)
    • FlashAttention 3 — The Hopper (H100/H200) version with FP8.
    • FlashAttention 2 — The standard for RTX 30/40/50 and A100: exact attention without the memory cost of long contexts.
  • torch.compile2.15.0from October 28, 2026new release

    10–30% for free

    Compiles the model for your GPU. Slower first run, faster afterwards.

    How to enable: model = torch.compile(model); in ComfyUI the TorchCompileModel node.

Model family

New posts about versions of pyramiddiff-wpp2024 (quants, finetunes, LoRAs) will show up under the bell.

No known relatives of this model yet. All derivatives on Hugging Face

About the model

SallySims/pyramiddiff-wpp2024
Author
SallySims
Category
Other
Released
Posted

On NeyroLearn

Hugging Face

250

Ask AI about this model

Answered by Gemini 4 · the chat is kept only in this tab

Comments