Skip to content
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

Fix dtype mismatch when merging LoRA checkpoints #1246

Merged
merged 1 commit into from
Apr 4, 2024
Merged

Fix dtype mismatch when merging LoRA checkpoints #1246

Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
4 changes: 2 additions & 2 deletions litgpt/scripts/merge_lora.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -43,7 +43,7 @@ def merge_lora(
fabric = L.Fabric(devices=1, precision=precision, accelerator="cpu")
config = Config.from_file(checkpoint_dir / "model_config.yaml", **lora_params)

with fabric.init_module(), torch.device("meta"):
with fabric.init_module():
model = GPT(config)

lora_path = checkpoint_dir / "lit_model.pth.lora"
Expand All @@ -52,7 +52,7 @@ def merge_lora(

# Merge LoRA weights into the base model
pretrained_checkpoint.update(lora_checkpoint.get("model", lora_checkpoint))
model.load_state_dict(pretrained_checkpoint, assign=True)
model.load_state_dict(pretrained_checkpoint)
merge_lora_weights(model)

# Remove LoRA parameters and the LoRA linear substring
Expand Down