Skip to content

FIX Transformers weight conversion regression #3197

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
BenjaminBossan merged 2 commits into from
Apr 29, 2026
+8 −5
Merged

FIX Transformers weight conversion regression #3197

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
45b5dd0
FIX Transformers weight conversion regression
BenjaminBossan Apr 24, 2026
141fdd5
Revert argument names
BenjaminBossan Apr 28, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
13 changes: 8 additions & 5 deletions src/peft/utils/transformers_weight_conversion.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -206,7 +206,10 @@ def build_peft_weight_mapping(
return []

# strip "base_model.model" and add adapter name
new_weight_conversions = [WeightRenaming("base_model.model.model.", "model.")]
new_weight_conversions = [
WeightRenaming("base_model.model.model.", "model."),
WeightRenaming("base_model.model.", ""),
]

prefixes = set()
from peft.mapping import PEFT_TYPE_TO_PREFIX_MAPPING
Expand Down Expand Up @@ -268,10 +271,10 @@ def build_peft_weight_mapping(
new_conversion = orig_conversion.__class__(
source_patterns=new_source_patterns,
target_patterns=new_target_patterns,
distributed_operation=orig_conversion.distributed_operation,
quantization_operation=orig_conversion.quantization_operation,
operations=peft_weight_operations,
)
new_conversion.distributed_operation = orig_conversion.distributed_operation
new_conversion.quantization_operation = orig_conversion.quantization_operation
new_weight_conversions.append(new_conversion)

elif len(orig_conversion.target_patterns) == 1 and orig_conversion.target_patterns[0].endswith("down_proj"):
Expand Down Expand Up @@ -310,10 +313,10 @@ def build_peft_weight_mapping(
new_conversion = orig_conversion.__class__(
source_patterns=new_source_patterns,
target_patterns=new_target_patterns,
distributed_operation=orig_conversion.distributed_operation,
quantization_operation=orig_conversion.quantization_operation,
operations=peft_weight_operations,
)
new_conversion.distributed_operation = orig_conversion.distributed_operation
new_conversion.quantization_operation = orig_conversion.quantization_operation
new_weight_conversions.append(new_conversion)

return new_weight_conversions
Expand Down
Loading