GENCO OPF on datakit

Checkpoints for GENCO §5.4.3 (Optimal Power Flow on datakit), Base and Small, IEEE 14 through GOC 2000, YAML seeds 0 and 1.

Pass last.pt (last-epoch weights extracted from Lightning last.ckpt), except GOC 2000 seed 0 Base and Small, which were scored by a later evaluate of best_model_state_dict.pt. Each folder also has normalizer_stats.pt, metrics.csv, and the training YAML.

The training YAML is in the same folder as the checkpoint. The same files are on GitHub: scripts/datakit_opf/configs. Table CSVs are under scripts/datakit_opf.

Training runs are under mlflow/train/. Their artifacts/test CSVs, including AC/DC, are the table rows.

hf download gridfm/genco-opf-datakit --include "case118_ieee/base/seed0/**" --local-dir genco-opf-datakit

gridfm_graphkit evaluate \
  --config scripts/datakit_opf/configs/case118_ieee_base_seed0.yaml \
  --data_path data \
  --model_path genco-opf-datakit/case118_ieee/base/seed0/last.pt \
  --normalizer_stats genco-opf-datakit/case118_ieee/base/seed0/normalizer_stats.pt

For GOC 2000 seed 0, pass best_model_state_dict.pt instead of last.pt.

Downloads last month

-

Downloads are not tracked for this model. How to track
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Collection including gridfm/genco-opf-datakit