Skip to content

Update LoRA developer guides: non-in-place operations #2871

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
merged 2 commits into from
Oct 27, 2025
+4 −4
Merged

Update LoRA developer guides: non-in-place operations #2871

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
3e02b4b
update LoRA developer guides
DargorAbraxas Oct 26, 2025
11131d6
add correction
DargorAbraxas Oct 27, 2025
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
8 changes: 4 additions & 4 deletions docs/source/developer_guides/lora.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -511,10 +511,10 @@ from peft import PeftModel
base_model = AutoModelForCausalLM.from_pretrained("mistralai/Mistral-7B-v0.1")
peft_model_id = "alignment-handbook/zephyr-7b-sft-lora"
model = PeftModel.from_pretrained(base_model, peft_model_id)
model.merge_and_unload()
model = model.merge_and_unload()
```

If you need to keep a copy of the weights so you can unmerge the adapter later or delete and load different ones, you should use the [`~LoraModel.merge_adapter`] function instead. Now you have the option to use [`~LoraModel.unmerge_adapter`] to return the base model.
It is important to assign the returned model to a variable and use it, [`~LoraModel.merge_and_unload`] is not an in-place operation. If you need to keep a copy of the weights so you can unmerge the adapter later or delete and load different ones, you should use the [`~LoraModel.merge_adapter`] function instead. Now you have the option to use [`~LoraModel.unmerge_adapter`] to return the base model.

```py
from transformers import AutoModelForCausalLM
Expand Down Expand Up @@ -603,11 +603,11 @@ model.load_adapter("alignment-handbook/zephyr-7b-dpo-lora", adapter_name="dpo")
model.set_adapter("dpo")
```

To return the base model, you could use [`~LoraModel.unload`] to unload all of the LoRA modules or [`~LoraModel.delete_adapter`] to delete the adapter entirely.
To return the base model, you could use [`~LoraModel.unload`] to unload all of the LoRA modules or [`~LoraModel.delete_adapter`] to delete the adapter entirely. [`~LoraModel.unload`] is not an in-place operation, remember to assign the returned model to a variable and use it.

```py
# unload adapter
model.unload()
model = model.unload()

# delete adapter
model.delete_adapter("dpo")
Expand Down