Downloads · 30 days
0
multiverse49/SAAFEC-STAIR-inference-checkpoints
SAAFEC-STAIR-inference-checkpoints is a machine learning model from multiverse49. Use it for the machine learning task on the model card, and read the license before you ship it in a product. It is set up for pytorch. The card lists the license as other.
This model repository stores the SAAFEC-STAIR inference model weights as PyTorch checkpoint files. The checkpoint files are used by the SAAFEC-STAIR inference package for structure-based single- and double-mutation pr…
Downloads · 30 days
0
Access
Public
Updated Jul 18, 2026
Repo size
115 MB
Likes
0
Public
Click a slice to open those files.
.pt115 MB · 100%
From the Hugging Face model README
This model repository stores the SAAFEC-STAIR inference model weights as PyTorch checkpoint files. The checkpoint files are used by the SAAFEC-STAIR inference package for structure-based single- and double-mutation protein folding free-energy change prediction.
The checkpoint files are intentionally distributed separately from the GitHub
source repository. They should be restored into the ignored local
assets/checkpoints/ paths before running inference.
checkpoints/
single_mutation/
seeds/
seed_1337/phase1/checkpoints/best_head.pt
seed_2027/phase1/checkpoints/best_head.pt
seed_3407/phase1/checkpoints/best_head.pt
double_mutation/
best_double_mutation_package.pt
Use these checkpoints with the SAAFEC-STAIR GitHub repository:
https://github.com/cosmicprawin-ux/saafec-stair
hf download multiverse49/SAAFEC-STAIR-inference-checkpoints \
--local-dir SAAFEC-STAIR-inference-checkpoints
Then copy only the four required checkpoint files into the corresponding
assets/checkpoints/ paths in the SAAFEC-STAIR source tree.
External third-party assets such as SaProt, ProteinMPNN, ThermoMPNN's pinned ProteinMPNN utility module, and Foldseek are not included here. Restore those from their official sources as described in the GitHub repository documentation.