Skip to content

GitLab

Unverified Commit cd8bd2d6 authored by mklabunde's avatar mklabunde Committed by GitHub
Browse files

pass current bnb_quantized when moving quantized Params4bit to different device (#1665)

parent 55ebaac7
Hide whitespace changes
Inline Side-by-side
Showing with 1 addition and 0 deletions
bitsandbytes/nn/modules.py
View file @ cd8bd2d6
...@@ -354,6 +354,7 @@ class Params4bit(torch.nn.Parameter): ...@@ -354,6 +354,7 @@ class Params4bit(torch.nn.Parameter):
compress_statistics=self.compress_statistics, compress_statistics=self.compress_statistics,
quant_type=self.quant_type, quant_type=self.quant_type,
quant_storage=self.quant_storage, quant_storage=self.quant_storage,
bnb_quantized=self.bnb_quantized,
) )
return new_param return new_param
......
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment