Skip to content

GitLab

Unverified Commit e0c3cee1 authored by mobicham's avatar mobicham Committed by GitHub
Browse files

hqq - fix weight check in check_quantized_param (#30748) 

* hqq - fix weight check in check_quantized_param

* ruff format
parent 8ce4fefc
Hide whitespace changes
Inline Side-by-side
Showing with 1 addition and 1 deletion
src/transformers/quantizers/quantizer_hqq.py
View file @ e0c3cee1
...@@ -101,7 +101,7 @@ class HqqHfQuantizer(HfQuantizer): ...@@ -101,7 +101,7 @@ class HqqHfQuantizer(HfQuantizer):
) -> bool: ) -> bool:
module, tensor_name = get_module_from_name(model, param_name) module, tensor_name = get_module_from_name(model, param_name)
return isinstance(module, torch.nn.Linear) return isinstance(module, torch.nn.Linear) and (tensor_name == "weight")
def create_quantized_param( def create_quantized_param(
self, self,
......
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