fix a type in code comment (#1063)

was pointing to wrong class

fix a type in code comment (#1063)
was pointing to wrong class
ceae1504 · Brian Vaughan · GitHub · 5b28fd3f · ceae1504
Unverified Commit ceae1504 authored Feb 14, 2024 by Brian Vaughan Committed by GitHub Feb 14, 2024
Hide whitespace changes
Inline Side-by-side

Showing with 1 addition and 1 deletion

bitsandbytes/nn/modules.py bitsandbytes/nn/modules.py +1 -1

No files found.
--- a/bitsandbytes/nn/modules.py
+++ b/bitsandbytes/nn/modules.py
@@ -275,7 +275,7 @@ class Linear4bit(nn.Linear):
    compute datatypes such as FP4 and NF4.

    In order to quantize a linear layer one should first load the original fp16 / bf16 weights into
-    the Linear8bitLt module, then call `quantized_module.to("cuda")` to quantize the fp16 / bf16 weights.
+    the Linear4bit module, then call `quantized_module.to("cuda")` to quantize the fp16 / bf16 weights.

    Example: