Diffusion-Research-Lab/alpha-stable-mixture-1p7-100d-diffusion

synthetic_alpha_stable_mixture

Unconditional reference models trained with gendynamics. The weights correspond to the best validation epoch.

Dataset

Synthetic unbalanced high-dimensional alpha-stable mixture. Generated by gendynamics.datasets.fetch_synthetic_data('unbalanced_highdim_alpha_stable_mixture'). Sample the configured mixture, then make a seeded random train/validation/test split. The train/validation/test splits contain 20,000/2,000/10,000 samples of shape [100]. Normalization: None The exact generator arguments or processed-file identity, split settings, and seed are in dataset.json. The source data themselves are not redistributed here; source-data terms remain with their provider. The preparation code is in gendynamics. API-backed sources can change; the processed-file checksum identifies this snapshot.

Architecture and training

All independently trained models use this network architecture:

{
  "name": "mlp",
  "params": {
    "width": 240,
    "depth": 4,
    "time_dim": 128,
    "dropout": 0.0,
    "use_norm": true,
    "dim": 100
  }
}

Directory	Model	Prediction target	Trainable parameters	Sampling steps	Learning rate	Epochs run / best	Val loss	Test loss
ddpm-v	DDPM-V	velocity	669,844	128	0.0005	640 / 636	2.193	3.797
dlpm-eps	DLPM-Eps	noise	669,844	128	0.0005	227 / 127	0.8141	0.8667
tedm-origin	t-EDM	denoised data	669,844	64	0.0005	183 / 83	0.7668	2.032

The complete selected final model and training settings are below and in each directory's config.json. The training settings include the maximum epoch budget; epochs run / best reports what actually happened. provenance.json records software versions and the source revision. Each model was reloaded and checked before upload; export_check.json records that check. Losses use each model's own objective, so they are not comparable sample-quality scores. The number of held-out rows used for each test loss is in metrics.json. Sample previews do not establish tail accuracy.

DDPM-V (ddpm-v/)

{
  "model_parameters": {
    "n_steps": 128,
    "sigma_max": 2.0,
    "sampler": "ddpm"
  },
  "training": {
    "device": "cuda",
    "data_device": "cpu",
    "batch_size": 1024,
    "n_epochs": 640,
    "early_stopping_patience": 100,
    "lr": 0.0005,
    "num_workers": 0,
    "use_adamw": true,
    "weight_decay": 1e-06,
    "grad_clip_norm": 10.0,
    "lr_schedule": "cosine",
    "warmup_steps": 400,
    "cosine_eta_min_ratio": 0.05,
    "freq_logging": 50,
    "stats_freq_epochs": 1,
    "log_grad_norm": true,
    "ckpt_freq_epochs": 64,
    "ckpt_keep_last": 8
  }
}

DLPM-Eps (dlpm-eps/)

{
  "model_parameters": {
    "n_steps": 128,
    "alpha": 1.9,
    "sampler": "native"
  },
  "training": {
    "device": "cuda",
    "data_device": "cpu",
    "batch_size": 1024,
    "n_epochs": 640,
    "early_stopping_patience": 100,
    "lr": 0.0005,
    "num_workers": 0,
    "use_adamw": true,
    "weight_decay": 1e-06,
    "grad_clip_norm": 10.0,
    "lr_schedule": "cosine",
    "warmup_steps": 400,
    "cosine_eta_min_ratio": 0.05,
    "freq_logging": 50,
    "stats_freq_epochs": 1,
    "log_grad_norm": true,
    "ckpt_freq_epochs": 64,
    "ckpt_keep_last": 8
  }
}

t-EDM (tedm-origin/)

{
  "model_parameters": {
    "n_steps": 64,
    "nu": 2.1,
    "sigma_min": 0.005,
    "sigma_max": 5.0,
    "sigma_data": 1.0,
    "solver": "edm_stochastic_heun"
  },
  "training": {
    "device": "cuda",
    "data_device": "cpu",
    "batch_size": 1024,
    "n_epochs": 640,
    "early_stopping_patience": 100,
    "lr": 0.0005,
    "num_workers": 0,
    "use_adamw": true,
    "weight_decay": 1e-06,
    "grad_clip_norm": 10.0,
    "lr_schedule": "cosine",
    "warmup_steps": 400,
    "cosine_eta_min_ratio": 0.05,
    "freq_logging": 50,
    "stats_freq_epochs": 1,
    "log_grad_norm": true,
    "ckpt_freq_epochs": 64,
    "ckpt_keep_last": 8
  }
}

DDIM-V (ddim-v/) shares the trained DDPM-V weights. Only the reverse sampler changes to deterministic DDIM (eta=0); it has no separate training run. Its exact sampling settings are in ddim-v/config.json.

Loading

Install the training package and its dependencies:

python -m pip install git+https://github.com/Diffusion-Research-Lab/2_training_2026_tail_reference_models.git

Then load one of the listed model directories by its underscored name:

from toolkit.huggingface import load_huggingface_model

model, normalization, data_scale = load_huggingface_model("Diffusion-Research-Lab/alpha-stable-mixture-1p7-100d-diffusion", "ddpm_v", device="cpu")
samples = model.sample(16).float().cpu()
if normalization is not None:
    samples = samples * normalization["std"] + normalization["mean"]

The model-specific files are model.safetensors, config.json, dataset.json, metrics.json, provenance.json, export_check.json, and, when applicable, normalization.safetensors. This repository is released under the MIT license. Cite the model repository revision when using these weights.