Add v3 OOD checkpoints + README
#1
by Leogrin - opened
Adds tabpfn-v3-{classifier,regressor}-v3_ood.ckpt.
Built from the v3 release defaults (identical state_dict) with only PREPROCESS_TRANSFORMS swapped to OOD-robust recipes:
- classifier: squashing_scaler_max10 + none (200 features)
- regressor: quantile_uni_extrapolate + squashing_scaler_max10 (500 features)
All other inference_config fields inherited from the defaults unchanged. The regressor depends on the quantile_uni_extrapolate preset added in PriorLabs/TabPFN#971 (merged); a TabPFN release that contains that merge is required to load it.
Closing in favor of the replacement PR above, which is a single clean commit based on current main (so it doesn't drop the arxiv link / full citation updates the way this PR's first commit did).
Leogrin changed pull request status to closed