deftdawg/bitsandbytes-rocm
1
0
Fork 0
forked from mrq/bitsandbytes-rocm
Code Pull Requests Activity

Merge pull request #14 from SirRob1997/main

Browse Source 
[FIX] passing of sparse in StableEmbedding
This commit is contained in:
Tim Dettmers 2021-11-29 08:22:16 -08:00 committed by GitHub
commit 262350c10f
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 2 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
bitsandbytes/nn/modules.py
View File

@ -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)