vumichien's picture
add tokenizer
640c0ce
raw
history blame
1.28 kB
{"bos_token": {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "eos_token": {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "unk_token": {"content": "<unk>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "pad_token": {"content": "<pad>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "sep_token": {"content": "[SEP]", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "mask_token": {"content": "[MASK]", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "cls_token": {"content": "[CLS]", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "sp_model_kwargs": {}, "model_max_length": 4096, "name_or_path": "google/bigbird-roberta-base", "special_tokens_map_file": "/root/.cache/huggingface/transformers/400be7e354ea6eb77319bcc7fa34899ec9fa2e3aff0fa677f6eb7e45a01b1548.75b358ecb30fa6b001d9d87bfde336c02d9123e7a8f5b90cc890d0f6efc3d4a3", "tokenizer_class": "BigBirdTokenizer"}