### apply\_kn\_to\_model-> *PreTrainedModel*
> Main function: Given the request, it applies mend to your model. Return the changed weights of the model.
```python
def apply_kn_to_model(
model,
tok: AutoTokenizer,
request: List[Dict],
hparams: KNHyperParams,
copy=False,
return_orig_weights=False,
keep_original_weight=True,
**kwargs
)
```
* **Paramters**
* model(PreTrainedModel): model to be edited
* tok(PreTrainedTokenizer): tokenizer for inputs
* requests(List\[Dict]): The edit descriptors and targets.
* hparams(Hyperparams): hyperparameters for editing method
* copy(bool): whether to copy original model
* return\_orig\_weights(bool): whether to return the weights of original model
* keep\_original\_weight(bool): whether to edit sequentially
* `False`: edit sequentially(because the original weight is not maintained after each edit)
* `True`: not edit sequentially
* **Return Type**
* edited\_model(PreTrainedModel): model weights after editing
### Example
```python
editor = BaseEditor.from_hparams(hparams)
prompts = ['What university did Watts Humphrey attend?',
'Which family does Ramalinaceae belong to',
'What role does Denny Herzig play in football?'
]
target_new = ['University of Michigan',
'Lamiinae',
'winger'
]
metrics, edited_model, _ = editor.edit(
prompts=prompts,
target_new=target_new,
keep_original_weight=True
)
```
###
