InputConfigΒΆ
-
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,
"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": 128
}
},
"labels": {
"is_input": false,
"column": "label",
"rescale_range": null
}
}