facebookresearch / bitsandbytes

Library for 8-bit optimizers and quantization routines.

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

sparse is not passed in __init__ function of StableEmbedding

SirRob1997 opened this issue · comments

commented

In this line instead of passing the sparse parameter, False is passed. Is this intended? It's a little confusing since the default for sparse is True here but False in torch.nn.Embedding

Good catch! Thank you for reporting this! I will fix this with the next release. Feel free to create a pull request!