SquadForBERTTensorizerForKD.Config

Component: SquadForBERTTensorizerForKD

class SquadForBERTTensorizerForKD.Config

Bases: SquadForBERTTensorizer.Config

All Attributes (including base classes)

is_input: bool = True

columns: list[str] = ['question', 'doc']

tokenizer: Tokenizer.Config = WordPieceTokenizer.Config()

base_tokenizer: Optional[Tokenizer.Config] = None

vocab_file: str = 'manifold://nlp_technologies/tree/huggingface-models/bert-base-uncased/vocab.txt'

max_seq_len: int = 256

answers_column: str = 'answers'

answer_starts_column: str = 'answer_starts'

start_logits_column: str = 'start_logits'

end_logits_column: str = 'end_logits'

has_answer_logits_column: str = 'has_answer_logits'

pad_mask_column: str = 'pad_mask'

segment_labels_column: str = 'segment_labels'

Default JSON

{
    "is_input": true,
    "columns": [
        "question",
        "doc"
    ],
    "tokenizer": {
        "WordPieceTokenizer": {
            "basic_tokenizer": {
                "split_regex": "\\s+",
                "lowercase": true,
                "use_byte_offsets": false
            },
            "wordpiece_vocab_path": "manifold://nlp_technologies/tree/huggingface-models/bert-base-uncased/vocab.txt"
        }
    },
    "base_tokenizer": null,
    "vocab_file": "manifold://nlp_technologies/tree/huggingface-models/bert-base-uncased/vocab.txt",
    "max_seq_len": 256,
    "answers_column": "answers",
    "answer_starts_column": "answer_starts",
    "start_logits_column": "start_logits",
    "end_logits_column": "end_logits",
    "has_answer_logits_column": "has_answer_logits",
    "pad_mask_column": "pad_mask",
    "segment_labels_column": "segment_labels"
}