Feature/hstu #290
Open
Feature/hstu #290
Conversation
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
This reverts commit 8c6ce83. revert torch backbone changes
…nctions & require_context property
Added leave_one_out_mask function in the `utils.py` module of the `transformers` package
blondered
reviewed
Jul 18, 2025
blondered
reviewed
Jul 18, 2025
blondered
reviewed
Jul 18, 2025
blondered
reviewed
Jul 18, 2025
blondered
reviewed
Jul 18, 2025
- `leave_one_out_mask` function (`rectools.models.nn.transformers.utils.leave_one_out_mask`) for LOO validation during transformer models training.
blondered
reviewed
Jul 18, 2025
blondered
reviewed
Jul 18, 2025
blondered
reviewed
Jul 18, 2025
blondered
reviewed
Jul 18, 2025
blondered
reviewed
Jul 20, 2025
blondered
reviewed
Jul 20, 2025
blondered
reviewed
Jul 20, 2025
feldlime
reviewed
Jul 20, 2025
| warnings.warn("Only the earliest row per user is used as context", UserWarning) | ||
| context = context_prep.get_context(context) | ||
| context[Columns.Item] = PADDING_VALUE # External index pad element | ||
| context = context[context[Columns.User].isin(interactions[Columns.User])] |
There was a problem hiding this comment.
Suggested change
| context = context[context[Columns.User].isin(interactions[Columns.User])] | |
| context = context[context[Columns.User].isin(interactions[Columns.User].unique())] |
blondered
reviewed
Jul 22, 2025
blondered
reviewed
Jul 23, 2025
|
|
||
| class HSTUModel(TransformerModelBase[HSTUModelConfig]): | ||
| """ | ||
| HSTUM model: transformer-based sequential model with unidirectional attention mechanism and |
There was a problem hiding this comment.
Suggested change
| HSTUM model: transformer-based sequential model with unidirectional attention mechanism and | |
| HSTU model: transformer-based sequential model with unidirectional pointwise aggregated attention mechanism, combined with "Shifted Sequence" training objective. |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
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.
Description
Type of change
How Has This Been Tested?
Before submitting a PR, please check yourself against the following list. It would save us quite a lot of time.