Sara Rabhi

rerun tests

@viswa-nvidia I have just updated the ticket with the tasks that are moving to later release.

This issue is fixed in [#771](https://github.com/NVIDIA-Merlin/models/pull/771) and [#780](https://github.com/NVIDIA-Merlin/models/pull/780)

I moved the task of creating the example to a separate ticket NVIDIA-Merlin/models#791 (expected in 22.11)

Thank you for the ticket @gabrielspmoreira. I just have a two additions to the list: * If we remove the ItemRetrievalScorer, we can also remove the PopularityBasedSampler: https://github.com/NVIDIA-Merlin/models/blob/5765c8ce2262f7f14fcb095f67b845235b8c16ac/merlin/models/tf/blocks/sampling/cross_batch.py#L26 * We...

Hi @nate-wandb, any updates on supporting Sweeps on Slurm?

closing this ticket as the scope is more detailed in this RMP [ticket](https://github.com/NVIDIA-Merlin/Merlin/issues/279)

Thank you @zuoxingdong for your question!  I can think of two different methods to support context features:  * Case 1: Repeat the context feature for each position in the input...

We have a class, called [InBatchNegatives](https://github.com/NVIDIA-Merlin/models/blob/eb1e54196a64a70950b2a7e7744d2150e052d53e/merlin/models/tf/transforms/negative_sampling.py#L29C7-L29C23), where the positive samples within a batch are used as negative samples. You can check this [page](https://github.com/NVIDIA-Merlin/models/blob/eb1e54196a64a70950b2a7e7744d2150e052d53e/tests/unit/tf/transforms/test_negative_sampling.py#L175) for the unit tests.

The top-k model uses a brute force evaluation where each user query scores against the whole catalog of items and by default shuffling is set to False for eval and...