| { | |
| "add_prefix_space": false, | |
| "bos_token": "<s>", | |
| "cls_token": "<s>", | |
| "eos_token": "</s>", | |
| "errors": "replace", | |
| "mask_token": "<mask>", | |
| "model_max_length": 512, | |
| "name_or_path": "/home/phunc20/git-repos/gitlab/phunc20/nlp_learning/viet_message/16-VinaLM_from_scratch/01_RoBERTa-like/data/vina-cased_tokenizer", | |
| "pad_token": "<pad>", | |
| "sep_token": "</s>", | |
| "special_tokens_map_file": "/home/phunc20/git-repos/gitlab/phunc20/nlp_learning/viet_message/16-VinaLM_from_scratch/01_RoBERTa-like/data/vina-cased_tokenizer/special_tokens_map.json", | |
| "tokenizer_class": "RobertaTokenizer", | |
| "trim_offsets": true, | |
| "unk_token": "<unk>" | |
| } | |