RoBERTaContextTensorizerForDenseRetrieval.Config

Component: RoBERTaContextTensorizerForDenseRetrieval

class RoBERTaContextTensorizerForDenseRetrieval.Config

Bases: RoBERTaTensorizer.Config

All Attributes (including base classes)

is_input: bool = True

columns: list[str] = ['text']

tokenizer: Tokenizer.Config = GPT2BPETokenizer.Config()

base_tokenizer: Optional[Tokenizer.Config] = None

vocab_file: str = 'gpt2_bpe_dict'

max_seq_len: int = 256

add_selfie_token: bool = False

Default JSON

{
    "is_input": true,
    "columns": [
        "text"
    ],
    "tokenizer": {
        "GPT2BPETokenizer": {
            "bpe_encoder_path": "manifold://pytext_training/tree/static/vocabs/bpe/gpt2/encoder.json",
            "bpe_vocab_path": "manifold://pytext_training/tree/static/vocabs/bpe/gpt2/vocab.bpe",
            "lowercase": false
        }
    },
    "base_tokenizer": null,
    "vocab_file": "gpt2_bpe_dict",
    "max_seq_len": 256,
    "add_selfie_token": false
}