github PriorLabs/TabPFN v10.2.0

42 minutes ago

Added

  • Add TabPFNRegressor(presets=...), named bundles of inference_config values. The "zero_inflated" preset is for nonnegative targets with many exact zeros: it sets the log_fixed_atom target transform and the nonnegative_and_capped readout. On the models up to TabPFN-3.5 it sets log_quantile_gap with the same readout instead. fit suggests the preset, once per process, for nonnegative targets with more than 20% zeros and at least 50 widely spread, non-count positives. (#1413)
  • With GPU preprocessing, a table held in host memory goes through the selective steps (quantile, squashing, safepower, robust) a block at a time, and the fingerprint hashes it where it is. Any other step that cannot run by blocks raises on such a table. (#1426)
  • Add the "grouped" preset for group_col data, on both estimators: presets="grouped" sets APPEND_GROUP_AGGREGATES=True and POOL_GROUP_PREDICTIONS="mean". TabPFNClassifier gets the presets argument for it. Both modes are computed over the rows passed to predict, so predict all rows of a group in one call. (#1434)

Changed

  • A CPU preprocessing pipeline that writes nothing into a float32 input no longer copies it at predict, nor at fit inside overwrite_fit_input(). (#1425)
  • With GPU preprocessing, random sign flips and the feature shuffle write into a table they may consume, and run on a table held in host memory without moving it to the GPU. (#1438)
  • With GPU preprocessing, the quantile, squashing and safepower steps transform a table they may consume in place, a block of columns at a time. Quantile and safepower can then differ from a fit over all columns by float rounding. (#1440)
  • When every CPU preprocessing step only selects, reorders or encodes (as with GPU preprocessing), ensemble members fitted inside overwrite_fit_input() read the caller's table and hold only the categorical columns they encode, rather than a copy each. At predict, a test table without categorical columns is read the same way. (#1442)

Don't miss a new TabPFN release

NewReleases is sending notifications on new releases.