alibi_detect.utils.prediction
Functions
tokenize_transformer
tokenize_transformertokenize_transformer(x: Union[list, numpy.ndarray], tokenizer: Callable, max_len: int, backend: str) -> dictBatch tokenizer for transformer models.
Name
Type
Default
Description
x
Union[list, numpy.ndarray]
Batch of instances.
tokenizer
Callable
Tokenizer for model.
max_len
int
Max token length.
backend
str
PyTorch ('pt') or TensorFlow ('tf') backend.
Returns
Type:
dict
Last updated
Was this helpful?

