InputConfig

class pytext.models.bert_regression_model.InputConfig

Bases: ConfigBase

All Attributes (including base classes)

tokens: BERTTensorizer.Config = BERTTensorizer.Config(columns=['text1', 'text2'], max_seq_len=128)

labels: NumericLabelTensorizer.Config = NumericLabelTensorizer.Config()

Default JSON

{
    "tokens": {
        "BERTTensorizer": {
            "is_input": true,
            "columns": [
                "text1",
                "text2"
            ],
            "tokenizer": {
                "WordPieceTokenizer": {
                    "basic_tokenizer": {
                        "split_regex": "\\s+",
                        "lowercase": true
                    },
                    "wordpiece_vocab_path": "/mnt/vol/nlp_technologies/bert/uncased_L-12_H-768_A-12/vocab.txt"
                }
            },
            "base_tokenizer": null,
            "vocab_file": "/mnt/vol/nlp_technologies/bert/uncased_L-12_H-768_A-12/vocab.txt",
            "max_seq_len": 128
        }
    },
    "labels": {
        "is_input": false,
        "column": "label",
        "rescale_range": null
    }
}