tokenizer_config.json

{
 "add_prefix_space": true,
 "added_tokens_decoder": {
 "0": {
 "content": "<unk>",
 "lstrip": false,
 "normalized": false,
 "rstrip": false,
 "single_word": false,
 "special": true
 },
 "1": {
 "content": "<s>",
 "lstrip": false,
 "normalized": false,
 "rstrip": false,
 "single_word": false,
 "special": true
 },
 "2": {
 "content": "</s>",
 "lstrip": false,
 "normalized": false,
 "rstrip": false,
 "single_word": false,
 "special": true
 },
 "3": {
 "content": "<cls>",
 "lstrip": false,
 "normalized": false,
 "rstrip": false,
 "single_word": false,
 "special": true
 },
 "4": {
 "content": "<sep>",
 "lstrip": false,
 "normalized": false,
 "rstrip": false,
 "single_word": false,
 "special": true
 },
 "5": {
 "content": "<pad>",
 "lstrip": false,
 "normalized": false,
 "rstrip": false,
 "single_word": false,
 "special": true
 },
 "6": {
 "content": "<mask>",
 "lstrip": true,
 "normalized": false,
 "rstrip": false,
 "single_word": false,
 "special": true
 },
 "7": {
 "content": "<eod>",
 "lstrip": false,
 "normalized": false,
 "rstrip": false,
 "single_word": false,
 "special": true
 },
 "8": {
 "content": "<eop>",
 "lstrip": false,
 "normalized": false,
 "rstrip": false,
 "single_word": false,
 "special": true
 }
 },
 "additional_special_tokens": [
 "<eop>",
 "<eod>"
 ],
 "bos_token": "<s>",
 "clean_up_tokenization_spaces": true,
 "cls_token": "<cls>",
 "do_lower_case": false,
 "eos_token": "</s>",
 "keep_accents": false,
 "mask_token": "<mask>",
 "max_length": 512,
 "model_max_length": 512,
 "pad_token": "<pad>",
 "remove_space": true,
 "sep_token": "<sep>",
 "stride": 0,
 "tokenizer_class": "XLNetTokenizer",
 "truncation_side": "right",
 "truncation_strategy": "longest_first",
 "unk_token": "<unk>"
}