outputs / tokenizer_config.json
Shadman-Rohan's picture
Training in progress, epoch 1
671bb5a
raw
history blame contribute delete
468 Bytes
{
"cls_token": "[CLS]",
"do_basic_tokenize": true,
"do_lower_case": false,
"full_tokenizer_file": null,
"mask_token": "[MASK]",
"model_max_length": 1000000000000000019884624838656,
"name_or_path": "csebuetnlp/banglabert",
"never_split": null,
"pad_token": "[PAD]",
"sep_token": "[SEP]",
"special_tokens_map_file": null,
"strip_accents": null,
"tokenize_chinese_chars": false,
"tokenizer_class": "ElectraTokenizer",
"unk_token": "[UNK]"
}