twitter-roberta-base-2019-90m / tokenizer_config.json
danlou
add tokenizer
7d66f1f
raw
history blame contribute delete
341 Bytes
{"unk_token": "<unk>", "bos_token": "<s>", "eos_token": "</s>", "add_prefix_space": false, "errors": "replace", "sep_token": "</s>", "cls_token": "<s>", "pad_token": "<pad>", "mask_token": "<mask>", "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "./base-checkpoint-4960000/", "tokenizer_class": "RobertaTokenizer"}