InputConfig

class pytext.models.masked_lm.InputConfig

Bases: ConfigBase

All Attributes (including base classes)

tokens: BERTTensorizerBase.Config = BERTTensorizerBase.Config(max_seq_len=128)

Default JSON

{
    "tokens": {
        "BERTTensorizerBase": {
            "is_input": true,
            "columns": [
                "text"
            ],
            "tokenizer": {
                "Tokenizer": {
                    "split_regex": "\\s+",
                    "lowercase": true,
                    "use_byte_offsets": false
                }
            },
            "base_tokenizer": null,
            "vocab_file": "",
            "max_seq_len": 128
        }
    }
}