diff --git a/bitsandbytes/nn/modules.py b/bitsandbytes/nn/modules.py index bf0945c..ce2f3a4 100644 --- a/bitsandbytes/nn/modules.py +++ b/bitsandbytes/nn/modules.py @@ -15,8 +15,8 @@ from bitsandbytes.optim import GlobalOptimManager class StableEmbedding(torch.nn.Embedding): def __init__(self, num_embeddings: int, embedding_dim: int, padding_idx: Optional[int] = None, max_norm: Optional[float] = None, norm_type: float = 2., scale_grad_by_freq: bool = False, - sparse: bool = True, _weight: Optional[Tensor] = None) -> None: - super(StableEmbedding, self).__init__(num_embeddings, embedding_dim, padding_idx, max_norm, norm_type, scale_grad_by_freq, False, _weight) + sparse: bool = False, _weight: Optional[Tensor] = None) -> None: + super(StableEmbedding, self).__init__(num_embeddings, embedding_dim, padding_idx, max_norm, norm_type, scale_grad_by_freq, sparse, _weight) self.norm = torch.nn.LayerNorm(embedding_dim) GlobalOptimManager.get_instance().register_parameters(self.weight) GlobalOptimManager.get_instance().override_config(self.weight, 'optim_bits', 32)