NeuroMF bug

[monkey0head]

After indexing change negative generation for NeuroMF got a bug.
Before: negatives were sampled from [0, num_items) uniform distribution; for now it is from [0, max_item + 1) distribution.
Ids were consecutive before and now they are not, so we can sample absent ids, which can break a training or make it less efficient.
Here:

    def _get_neg_batch(self, batch: Tensor) -> Tensor:
        negative_items = torch.randint(
            0,
            self._item_dim,
            (batch.shape[0] * self.count_negative_sample,),
        )
        return negative_items

[monkey0head]

• probably affects slim, admm slim, lightFM, multVAE