YAML Metadata Warning:empty or missing yaml metadata in repo card
Check out the documentation for more information.
MLX-Cric pretrained weights
Cricket winner predictor (Apple MLX MLP x5 + HGB sidecar, stacked). Trained on ~27k matches, walk-forward split (train ≤2021, val 2022–23, test 2024–26).
Use (no training needed)
pip install git+https://github.com/ranveersoni98/mlx-cricket.git
mlx-cric download-model
mlx-cric predict --team1 India --team2 Australia --venue-country India --format ODI
Files: model_*.safetensors (5 MLP seeds), hgb.pkl + stacker.pkl (gradient-boosting sidecar), draw_lr.pkl (Test draw model), features.json (vocabularies), ratings.json/pool.json (team strength), plus calibration (temperature.json, ensemble.json).
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support