TabICL 0.0.6

JingangQu released this 19 Mar 14:17

· 19 commits to main since this release

266a475

What's Changed

fix (TabICLClassifier): convert output tensor to float before moving to numpy (df1e504)

When AMP is enabled, PyTorch tensors may be in float16. Explicitly casting to float32 ensures stability and prevents errors.

Full Changelog: v0.0.5...v0.0.6

Assets 3