ClimaX

license

MIT(OSI)

weights

open(MIT ungated checkpoints at two grid resolutions)

data

open(Snakemake download and regrid workflow plus preprocessing scripts reconstruct the CMIP6 pretraining corpus end to end)

code

open(pretraining entry point and config alongside per-task fine-tuning configs and data preparation scripts)

ClimaX is the rare complete release in this category - the corpus is rebuildable from shipped scripts rather than merely described, the pretraining run is a documented command with its config, and MIT covers both the repository and the published checkpoints.

• https://huggingface.co/api/models/tungnd/climax recorded 2026-10-13

  license: mit; gated: false; private: false; checkpoint files 5.625deg.ckpt, 1.40625deg.ckpt, vits.ckpt, vitb.ckpt and vitl.ckpt.

• https://microsoft.github.io/ClimaX/usage/ recorded 2026-10-13

  A Snakemake workflow downloads and regrids CMIP6 variables and nc2np_equally_cmip6.py preprocesses them for pretraining; pretraining runs as src/climax/pretrain/train.py --config configs/pretrain_climax.yaml; two pretrained checkpoints at 5.625deg and 1.40625deg are provided, both pretrained on all five CMIP6 datasets, and each downstream task has a fine-tuning config.

• https://raw.githubusercontent.com/microsoft/ClimaX/main/LICENSE recorded 2026-10-13

  Full MIT License text, copyright Microsoft Corporation, with no added use restriction.

The checkpoints are hosted under lead author Tung Nguyen's personal Hugging Face namespace, but the ClimaX repository's own fine-tuning commands point directly at those files, confirming it as the official release. The Hub reports zero downloads despite 2.6 GB of stored checkpoints, so GitHub stars are used as the adoption signal instead.

• https://api.github.com/repos/microsoft/ClimaX recorded 2026-09-10

  stargazers_count: 709; archived: false; fork: false.

ClimaX earns two capabilities: per-task fine-tuning configs, and checkpoints at two grid resolutions. It is not credited for combining multiple data sources, because its five CMIP6 datasets are simulation archives from one data system, and ERA5 only enters at fine-tuning, not pretraining.

• https://microsoft.github.io/ClimaX/usage/ recorded 2026-09-10

  Gives fine-tuning commands and configs for global forecasting, regional forecasting, and climate projection, each loading a pretrained checkpoint, and publishes checkpoints at 5.625deg and 1.40625deg resolution.