feat: stable/experimental model split, save/load, and bug fixes#346
Open
mkumar73 wants to merge 21 commits into
Open
feat: stable/experimental model split, save/load, and bug fixes#346mkumar73 wants to merge 21 commits into
mkumar73 wants to merge 21 commits into
Conversation
… of reusing encoder norm
…abR platform skip
This was referenced May 14, 2026
Closed
TabR used num_classes > 1 to select nn.Embedding for label encoding, mistaking LSS distribution param count (e.g. 2 for Normal) for a class count. This caused IndexError when continuous candidate_y targets were cast to .long() indices. Fix: add lss: bool = False to TabR.__init__, use nn.Linear label encoder when lss=True regardless of num_classes, and guard the three forward-pass classification branches with 'and not self.hparams.lss'. TaskModel already receives lss=True from SklearnBaseLSS; now forwards it to the model class so TabR can observe it.
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
No description provided.