german-english-code-switching-bert / tokenizer_config.json
igorsterner's picture
Upload tokenizer
f852680
raw
history blame contribute delete
476 Bytes
{
"cls_token": "[CLS]",
"do_lower_case": false,
"mask_token": "[MASK]",
"model_max_length": 512,
"name_or_path": "/home/is473/rds/hpc-work/4X1/ComingSoon/Experiments/mbert_pretraining_on_tongueswitcher_bs_32_warmup_10000_weight_decay/models/checkpoint-191950",
"pad_token": "[PAD]",
"sep_token": "[SEP]",
"special_tokens_map_file": null,
"strip_accents": null,
"tokenize_chinese_chars": true,
"tokenizer_class": "BertTokenizer",
"unk_token": "[UNK]"
}