v0.6.0

What's Changed

• baseten: rename invoke env var to SYNTHEFY_NORI_API_KEY by @raimishah in #27
• Docs/readme reorder toc by @realPohanLi in #40
• Remove dangling lazy imports for nonexistent modules by @raimishah in #42
• Expose predictive distribution via output_type="quantiles"/"full" by @realPohanLi in #41
• AGENTS.md: run /review before finalizing a PR; align import convention by @realPohanLi in #43
• Bump version to 0.6.0 by @yogabbagabb in #44

New Contributors

• @raimishah made their first contribution in #27

Full Changelog: v0.5.0...v0.6.0

v0.5.0

What's Changed

• Remove the require-approval workflow by @yogabbagabb in #32
• docs: make Interpretability README user-facing (SHAP keyword + use cases) by @sagarwal-atg in #33
• docs: add Nori banner to README by @sagarwal-atg in #34
• Port inference speedups: GPU SVD, capped quantile, adaptive fit-subsample by @sagarwal-atg in #30
• docs: add documentation link to README by @sagarwal-atg in #36
• Port KV-cache inference fast path to public + enable by default by @sagarwal-atg in #35
• docs: reorder README for new users + add table of contents by @sagarwal-atg in #37
• Add CITATION.cff for GitHub citation support by @sagarwal-atg in #38
• Release v0.5.0 by @yogabbagabb in #39

Full Changelog: v0.4.0...v0.5.0

v0.4.0

What's Changed

• docs: add HF/DOI badges and citation to README by @realPohanLi in #28
• Add branch protection and approval workflow by @yogabbagabb in #17
• Add interpretability extension (shapiq Shapley/interactions, PDP, feature selection) by @sagarwal-atg in #29
• Release 0.4.0 by @yogabbagabb in #31

Full Changelog: v0.3.0...v0.4.0

v0.3.0

What's Changed

• Large-GPU eval protocol everywhere; best numbers reproduced via one command (builds on #21) by @sagarwal-atg in #23
• Rename "Synthefy Tabular" → "Nori" by @adityanarayanan03 in #25

Full Changelog: v0.2.3...v0.3.0

v0.2.3

What's Changed

• Add token accounting for inference requests by @yogabbagabb in #14
• Make context-size budget configurable via SYNTHEFY_MAX_ELEMENTS_BUDGET by @sagarwal-atg in #15
• Add OpenAI-compatible usage block to inference output by @yogabbagabb in #16
• Enable HF download tracking; scrub stale classification + gated-repo docs by @sagarwal-atg in #18
• Fix Truss deploy: bundle token_accounting so production /predict stops 500ing by @yogabbagabb in #19
• Add benchmark reproduction harness and pin cu128 torch build by @realPohanLi in #21
• Release 0.2.3 by @yogabbagabb in #24

New Contributors

• @realPohanLi made their first contribution in #21

Full Changelog: v0.2.2...v0.2.3

v0.2.1

Private build of synthefy-tabular v0.2.1. Install: see docs/private-distribution.md

v0.2.0

Private build of synthefy-tabular v0.2.0. Install: see docs/private-distribution.md

v0.1.0

First public release of synthefy-tabular.

Install

pip install synthefy-tabular

Authentication

The default model checkpoint at Synthefy/synthefy-tabular on Hugging Face currently requires access. See the README for details on requesting access and providing an HF token.

If you have a local checkpoint, pass model_path= to skip the Hugging Face download.

Usage

from synthefy_tabular import SynthefyTabularRegressor
model = SynthefyTabularRegressor()
model.fit(X_train, y_train)
pred = model.predict(X_test)