61 lines
1.3 KiB
JSON
61 lines
1.3 KiB
JSON
|
{
|
||
|
|
"added_tokens_decoder": {
|
||
|
|
"0": {
|
||
|
|
"content": "\u003cunk\u003e",
|
||
|
|
"lstrip": false,
|
||
|
|
"normalized": false,
|
||
|
|
"rstrip": false,
|
||
|
|
"single_word": false,
|
||
|
|
"special": true
|
||
|
|
},
|
||
|
|
"1": {
|
||
|
|
"content": "\u003cs\u003e",
|
||
|
|
"lstrip": false,
|
||
|
|
"normalized": false,
|
||
|
|
"rstrip": false,
|
||
|
|
"single_word": false,
|
||
|
|
"special": true
|
||
|
|
},
|
||
|
|
"2": {
|
||
|
|
"content": "\u003c/s\u003e",
|
||
|
|
"lstrip": false,
|
||
|
|
"normalized": false,
|
||
|
|
"rstrip": false,
|
||
|
|
"single_word": false,
|
||
|
|
"special": true
|
||
|
|
},
|
||
|
|
"3": {
|
||
|
|
"content": "\u003cpad\u003e",
|
||
|
|
"lstrip": false,
|
||
|
|
"normalized": false,
|
||
|
|
"rstrip": false,
|
||
|
|
"single_word": false,
|
||
|
|
"special": true
|
||
|
|
},
|
||
|
|
"4": {
|
||
|
|
"content": "\u003cmask\u003e",
|
||
|
|
"lstrip": false,
|
||
|
|
"normalized": false,
|
||
|
|
"rstrip": false,
|
||
|
|
"single_word": false,
|
||
|
|
"special": true
|
||
|
|
}
|
||
|
|
},
|
||
|
|
"bos_token": "\u003cs\u003e",
|
||
|
|
"bos_token_id": 1,
|
||
|
|
"clean_up_tokenization_spaces": false,
|
||
|
|
"cls_token": null,
|
||
|
|
"eos_token": "\u003c/s\u003e",
|
||
|
|
"eos_token_id": 2,
|
||
|
|
"extra_special_tokens": {},
|
||
|
|
"mask_token": "\u003cmask\u003e",
|
||
|
|
"mask_token_id": 4,
|
||
|
|
"model_max_length": 1024,
|
||
|
|
"pad_token": "\u003cpad\u003e",
|
||
|
|
"pad_token_id": 3,
|
||
|
|
"sep_token": null,
|
||
|
|
"tokenizer_class": "PreTrainedTokenizer",
|
||
|
|
"unk_token": "\u003cunk\u003e",
|
||
|
|
"unk_token_id": 0
|
||
|
|
}
|