add-model
01Command Claude Code
Add a new model to this repository following all repo conventions.
Command Claude Code
Add a new model to this repository following all repo conventions.
Command Claude Code
Create or improve a recipe (inference, fine-tune, eval, etc.) for a model already in AI4Science Studio.
Command Claude Code
Audit which models are fully set up and which have gaps.
Command Claude Code
Audit an existing model entry in AI4Science Studio and report any issues.
Command Claude Code
Detect the current cluster environment and create a .cluster-config.yaml file with site-specific settings. This file is gitignored and never committed.
Command Claude Code
Discover what models are available in this repository.
Command Claude Code
Guide the user through running ArchesWeather end-to-end on an AMD cluster.
Command Claude Code
Guide the user through running Aurora (0.1° resolution) end-to-end on an AMD cluster.
Command Claude Code
Guide the user through running GenCast end-to-end on an AMD cluster.
Command Claude Code
Guide the user through running GP-MoLFormer on an AMD cluster via SLURM.
Command Claude Code
Guide the user through running HydraGNN predictive GFM inference on AMD GPUs.
Command Claude Code
Guide the user through training or inference with MATEY on AMD GPUs.
Command Claude Code
Guide the user through running MatterGen end-to-end on an AMD cluster via SLURM or Docker.
Command Claude Code
Guide the user through running NeuralGCM end-to-end on an AMD cluster via Docker or SLURM.
Command Claude Code
Guide the user through running ORBIT-2 end-to-end on an AMD cluster via SLURM.
Command Claude Code
Guide the user through running PanguWeather end-to-end on an AMD cluster.
Command Claude Code
Guide the user through performance engineering for HydraGNN Predictive GFM: one-shot perf-analysis (2-node training + TraceLens + Omnistat diagnosis) or iterative perf-optimizer-loop (accept/revert on epochtimes). This is not ensemble inference — use /run-hydragnn for that.
Command Claude Code
Guide the user through performance engineering workflows for ORBIT-2 (Bayes-CAST EDM / same-dir timing configs): one-shot perf-analysis (TraceLens + Omnistat diagnosis) or iterative perf-optimizer-loop (accept/revert on throughput). This is not inference/visualization — use /run-orbit2 for that.
Command Claude Code
Guide the user through running REINVENT4 transfer learning for molecular design on AMD GPUs.
Command Claude Code
Guide the user through generating 3D molecular structures with SemlaFlow on AMD GPUs.
Command Claude Code
Guide the user through running StormCast end-to-end on an AMD cluster via SLURM.
Command Claude Code
Guide the user through training or inference with SwinUNETR on AMD GPUs.
Command Claude Code
Guide the user through running Walrus autoregressive rollout on AMD GPUs.
Cursor rule Cursor
Preferred approach for building Apptainer overlay images that avoid re-downloading torch.