add preprocessor

This commit is contained in:
mjchen6 2023-06-08 14:53:30 +08:00
parent 7d57f188d5
commit f18fcef733
5 changed files with 61237 additions and 0 deletions

23
config.json Normal file
View File

@ -0,0 +1,23 @@
{
"_name_or_path": "distilbert-base-uncased",
"activation": "gelu",
"architectures": [
"DistilBertForMaskedLM"
],
"attention_dropout": 0.1,
"dim": 768,
"dropout": 0.1,
"hidden_dim": 3072,
"initializer_range": 0.02,
"max_position_embeddings": 512,
"model_type": "distilbert",
"n_heads": 12,
"n_layers": 6,
"pad_token_id": 0,
"qa_dropout": 0.1,
"seq_classif_dropout": 0.2,
"sinusoidal_pos_embds": false,
"tie_weights_": true,
"transformers_version": "4.29.2",
"vocab_size": 30522
}

7
special_tokens_map.json Normal file
View File

@ -0,0 +1,7 @@
{
"cls_token": "[CLS]",
"mask_token": "[MASK]",
"pad_token": "[PAD]",
"sep_token": "[SEP]",
"unk_token": "[UNK]"
}

30672
tokenizer.json Normal file

File diff suppressed because it is too large Load Diff

13
tokenizer_config.json Normal file
View File

@ -0,0 +1,13 @@
{
"clean_up_tokenization_spaces": true,
"cls_token": "[CLS]",
"do_lower_case": true,
"mask_token": "[MASK]",
"model_max_length": 512,
"pad_token": "[PAD]",
"sep_token": "[SEP]",
"strip_accents": null,
"tokenize_chinese_chars": true,
"tokenizer_class": "DistilBertTokenizer",
"unk_token": "[UNK]"
}

30522
vocab.txt Normal file

File diff suppressed because it is too large Load Diff