soodoku

@soodoku.bsky.social

gojiberries.io github.com/soodoku

Post-training quantization for fitted tree ensembles. Bring your trained XGBoost or scikit-learn model, get back the same model with 2-4 bit leaf values, a compact .tgq artifact, and a report stating exactly how much space you saved and how much accuracy it cost. github.com/finite-sampl...

GitHub - finite-sample/treegptq: Post-training quantization for fitted tree ensembles.

Post-training quantization for fitted tree ensembles. - finite-sample/treegptq

github.com

Post-training quantization for fitted tree ensembles. Bring your trained XGBoost or scikit-learn model, get back the same model with 2-4 bit leaf values, a compact .tgq artifact, and a report stating exactly how much space you saved and how much accuracy it cost. github.com/finite-sampl...

GitHub - finite-sample/treegptq: Post-training quantization for fitted tree ensembles.

Post-training quantization for fitted tree ensembles. - finite-sample/treegptq

github.com

ethnicolr 1.0 is out 🎉 Predict race/ethnicity from names — now pure PyTorch. All 9 models retrained; the Wikipedia models now train on 3.7M names (25× more data), with top-3 accuracy >90% across 13 ethnic groups. Python 3.11–3.13. pip install ethnicolr ▎ github.com/appeler/ethnicolr

GitHub - appeler/ethnicolr: Predict Race and Ethnicity Based on the Sequence of Characters in a Name

Predict Race and Ethnicity Based on the Sequence of Characters in a Name - appeler/ethnicolr

github.com

ethnicolr 1.0 is out 🎉 Predict race/ethnicity from names — now pure PyTorch. All 9 models retrained; the Wikipedia models now train on 3.7M names (25× more data), with top-3 accuracy >90% across 13 ethnic groups. Python 3.11–3.13. pip install ethnicolr ▎ github.com/appeler/ethnicolr

GitHub - appeler/ethnicolr: Predict Race and Ethnicity Based on the Sequence of Characters in a Name

Predict Race and Ethnicity Based on the Sequence of Characters in a Name - appeler/ethnicolr

github.com