Skip to content

Commit

Permalink
[docs] Docstring link (#1356)
Browse files Browse the repository at this point in the history
* fix format

* hmm
  • Loading branch information
stevhliu authored Jan 12, 2024
1 parent a43ec59 commit bf54136
Showing 1 changed file with 1 addition and 1 deletion.
2 changes: 1 addition & 1 deletion docs/source/developer_guides/lora.md
Original file line number Diff line number Diff line change
Expand Up @@ -83,7 +83,7 @@ model = PeftModel.from_pretrained(base_model, peft_model_id)
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 [`~tuners.tuner_utils.BaseTuner.merge_adapter`] function instead. Now you have the option to use [`~LoraModel.unmerge_adapter`] to return the base model.
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

0 comments on commit bf54136

Please sign in to comment.