in scripts/run_prompt_creation.py [0:0]
def __call__(self, features: List[Dict[str, Union[List[int], torch.Tensor]]]) -> Dict[str, torch.Tensor]:
# split inputs and labels since they have to be of different lengths and need
# different padding methods
input_ids = {"input_ids": [feature["input_ids"] for feature in features]}
batch = self.tokenizer.pad(input_ids, return_tensors="pt", padding="longest", return_attention_mask=True)
return batch