hierarchical-transformer-base-4096 / tokenizer_config.json
kiddothe2b's picture
Initial commit
ab7b7bf
raw
history blame
463 Bytes
{"errors": "replace", "bos_token": "<s>", "eos_token": "</s>", "sep_token": "</s>", "cls_token": "<s>", "unk_token": "<unk>", "pad_token": "<pad>", "mask_token": "<mask>", "add_prefix_space": false, "trim_offsets": true, "model_max_length": 4096, "special_tokens_map_file": null, "name_or_path": "kiddothe2b/hat-base-4096", "tokenizer_class": "RobertaTokenizer", "auto_map": {"AutoTokenizer": ["tokenization_hat.HATTokenizer", "tokenization_hat.HATTokenizer"]}}