Token Classification
Transformers
PyTorch
Bulgarian
bert
torch
bert-base-pos-theseus-bg / tokenizer_config.json
rmihaylov's picture
add tokenizer
9895ad5
raw
history blame
583 Bytes
{"do_lower_case": false, "remove_space": true, "keep_accents": true, "bos_token": "[CLS]", "eos_token": "[SEP]", "unk_token": "<unk>", "sep_token": "[SEP]", "pad_token": "<pad>", "cls_token": "[CLS]", "mask_token": {"content": "[MASK]", "single_word": false, "lstrip": true, "rstrip": false, "normalized": false, "__type": "AddedToken"}, "sp_model_kwargs": {}, "model_max_length": 512, "special_tokens_map_file": "/content/drive/MyDrive/ColabModels/MBERT_POS_THESEUS/pytorch_model/special_tokens_map.json", "name_or_path": "/content/tokenizer/", "tokenizer_class": "AlbertTokenizer"}