albert-bn-dev / tokenizer_config.json
SaulLu's picture
tokenizer v2 - fix user defined symbols
bf3a9c0
{"do_lower_case": true, "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": true, "__type": "AddedToken"}, "model_max_length": 512, "special_tokens_map_file": null, "tokenizer_file": null, "name_or_path": "/content/drive/MyDrive/collaborative hub training/tokenizer/tokenizer_bn/oscar_wiki_bn_spm_unigram_4000000_2021_04_23_10_05_27/old"}