UMA

weights

open(manually gated but downloadable uma-s and uma-m checkpoint files)

data

open(OMol25, OMat24, OC20, ODAC23, and OMC25 training datasets published alongside the model)

code

open(configs/uma/training_release ships uma_sm_direct_pretrain.yaml and uma_md_direct_pretrain.yaml with their backbone, dataset, tasks and element_refs configs, driven by the fairchem CLI, alongside the MIT inference and calculator library)

license

FAIR-Chemistry-License-v1(royalty-free commercial use with an acceptable-use policy and gated registration)

Gating and an acceptable-use policy are identity and conduct conditions rather than a commercial ceiling, so the licence does not push UMA below the open-weights centre of gravity. The pretraining configs in configs/uma/training_release and the five published training datasets are what carry it above the open-weights centre of gravity.

• https://api.github.com/repos/facebookresearch/fairchem/contents/configs/uma/training_release recorded 2026-09-10

  Lists uma_sm_direct_pretrain.yaml and uma_md_direct_pretrain.yaml beside uma_sm_conserve_finetune.yaml and uma_md_conserve_finetune.yaml, with backbone, dataset, tasks, element_refs and cluster config directories - the published pretraining recipe, not just inference code.

• https://huggingface.co/api/models/facebook/UMA recorded 2026-09-10

  gated: manual; private: false; license: other under the FAIR Chemistry License v1 with a full-legal-name registration prompt; checkpoints/uma-s-1p2.pt, uma-s-1p2p1.pt, and uma-m-1p1.pt present.

• https://raw.githubusercontent.com/facebookresearch/fairchem/main/docs/core/uma.md recorded 2026-09-10

  Names the five DFT training datasets behind the tasks — OMol25, OMC25, OMat24, OC20, and ODAC23, plus OC25 and OC22 in UMA-1.2 — each with a published reference.

• https://raw.githubusercontent.com/facebookresearch/fairchem/main/LICENSE.md recorded 2026-09-10

  MIT License body for the fairchem library, read directly because the license endpoint reports NOASSERTION; the README adds that model and checkpoint licenses vary by application area.

• https://raw.githubusercontent.com/facebookresearch/fairchem/main/README.md recorded 2026-09-10

  Documents installation, pretrained-model instantiation, ASE calculators, molecular dynamics, and multi-GPU and LAMMPS interfaces, with no pretraining or fine-tuning recipe.

Adoption is measured from PyPI downloads of fairchem-core, the declared package that installs UMA and fetches its checkpoints, because a package that is the documented way to obtain the weights takes precedence over the Hub. The gated facebook/UMA Hub repository reports far fewer downloads, since manual approval suppresses its count.

• https://huggingface.co/api/models/facebook/UMA recorded 2026-09-10

  downloads: 83; likes: 374; gated: manual — recorded so the superseded Hub signal stays visible.

UMA trains on five separate DFT datasets with different functionals and pseudopotentials, which counts as multiple distinct data sources rather than variables of one. It also documents a first-party fine-tuning pathway with a dataset-preparation script and templated configs, so the publisher's note that fine-tuning is usually unnecessary does not change that the pathway exists.

• https://arxiv.org/abs/2506.23971 recorded 2026-09-10

  Describes training on half a billion 3D atomic structures compiled across multiple chemical domains and reports that a single model without any fine-tuning matches or beats specialized models.

• https://raw.githubusercontent.com/facebookresearch/fairchem/main/docs/core/uma.md recorded 2026-09-10

  States UMA is trained on five different DFT datasets with different levels of theory, learns a per-task embedding, and requires the user to select a task at inference; tabulates the functional and pseudopotentials for each.