Downloads · 30 days
0
apebench-paper-ablations
thuerey-group/apebench-paper-ablations
apebench-paper-ablations is a machine learning model from thuerey-group. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as mit.
Access
Public
Updated May 12, 2026
Repo size
114 GB
Likes
1
Public
Repo makeup
Click a slice to open those files.
.eqx40.8 GB · 83%
At a glance
- License
- mit
- Access
- Public
- Created
- Jul 17, 2024
- Updated
- May 12, 2026
- SHA
- 686f7b4f
Model card
From the Hugging Face model README
Ablation Results & Postprocessing for the APEBench paper
Check if git lfs is available
git lfs --version
Clone without large files (subsets or all data can be downloaded later)
GIT_LFS_SKIP_SMUDGE=1 git clone [email protected]:thuerey-group/apebench-paper-ablations
Alternatively if you have ~155GB of free space, you can download all the data at once
git clone [email protected]:thuerey-group/apebench-paper-ablations
Usage and partial download guides over at apebench-paper
Rebuttal additions
Following reviewer feedback on the OpenReview submission (iWc0qE116u), three further ablation studies have been added:
fno_vary_modes: sweeping the number of Fourier modes in FNO (advection, Burgers, KS).fno_vary_unrolling: supervised rollout-length sweep for FNO (advection, Burgers, diffusion, KdV, KS).unrolling_and_spectral_metrics: rollout sweep evaluated with band-pass spectral metrics (ResNet + FNO across multiple equations, including a high-difficulty advection variant).
Each follows the same studies/ → results/{raw,network_weights}/ → melted/<name>/ → postprocessing/<name>/ layout as the original studies.
- License
- mit
- Created
- Jul 17, 2024
- Updated
- May 12, 2026