slbert_scotus_classsification / tokenizer_config.json
danielsaggau's picture
Training in progress, epoch 1
131f264
raw
history blame contribute delete
560 Bytes
{
"cls_token": "[CLS]",
"do_basic_tokenize": true,
"do_lower_case": true,
"mask_token": "[MASK]",
"model_max_length": 4096,
"name_or_path": "/content/drive/MyDrive/sbert_longformer_ecthr_b_simcse/train_simcse-_root_.local_share_jupyter_runtime_kernel-702ca39d-5545-4b00-b884-05176c135763.json-2022-10-21_08-44-17/1500",
"never_split": null,
"pad_token": "[PAD]",
"sep_token": "[SEP]",
"special_tokens_map_file": null,
"strip_accents": null,
"tokenize_chinese_chars": true,
"tokenizer_class": "BertTokenizer",
"unk_token": "[UNK]"
}