CamBabyTokenizer-16384 / tokenizer_config.json
codebyzeb's picture
Upload tokenizer
53206a1
raw
history blame contribute delete
573 Bytes
{
"add_prefix_space": true,
"bos_token": "<s>",
"cls_token": "<s>",
"eos_token": "</s>",
"errors": "replace",
"mask_token": {
"__type": "AddedToken",
"content": "<mask>",
"lstrip": true,
"normalized": false,
"rstrip": false,
"single_word": false
},
"model_max_length": 1000000000000000019884624838656,
"name_or_path": "CamBabyTrainers/CamBabyTokenizer-8192",
"pad_token": "<pad>",
"sep_token": "</s>",
"special_tokens_map_file": null,
"tokenizer_class": "RobertaTokenizer",
"trim_offsets": true,
"unk_token": "<unk>"
}