86 lines
1.9 KiB
JSON
86 lines
1.9 KiB
JSON
{
|
|
"added_tokens_decoder": {
|
|
"0": {
|
|
"content": "<unk|LLM-jp>",
|
|
"lstrip": false,
|
|
"normalized": false,
|
|
"rstrip": false,
|
|
"single_word": false,
|
|
"special": true
|
|
},
|
|
"1": {
|
|
"content": "<s|LLM-jp>",
|
|
"lstrip": false,
|
|
"normalized": false,
|
|
"rstrip": false,
|
|
"single_word": false,
|
|
"special": true
|
|
},
|
|
"2": {
|
|
"content": "</s|LLM-jp>",
|
|
"lstrip": false,
|
|
"normalized": false,
|
|
"rstrip": false,
|
|
"single_word": false,
|
|
"special": true
|
|
},
|
|
"3": {
|
|
"content": "<mask|LLM-jp>",
|
|
"lstrip": false,
|
|
"normalized": false,
|
|
"rstrip": false,
|
|
"single_word": false,
|
|
"special": true
|
|
},
|
|
"4": {
|
|
"content": "<pad|LLM-jp>",
|
|
"lstrip": false,
|
|
"normalized": false,
|
|
"rstrip": false,
|
|
"single_word": false,
|
|
"special": true
|
|
},
|
|
"5": {
|
|
"content": "<CLS|LLM-jp>",
|
|
"lstrip": false,
|
|
"normalized": false,
|
|
"rstrip": false,
|
|
"single_word": false,
|
|
"special": true
|
|
},
|
|
"6": {
|
|
"content": "<SEP|LLM-jp>",
|
|
"lstrip": false,
|
|
"normalized": false,
|
|
"rstrip": false,
|
|
"single_word": false,
|
|
"special": true
|
|
},
|
|
"7": {
|
|
"content": "<EOD|LLM-jp>",
|
|
"lstrip": false,
|
|
"normalized": false,
|
|
"rstrip": false,
|
|
"single_word": false,
|
|
"special": true
|
|
}
|
|
},
|
|
"additional_special_tokens": [
|
|
"</s|LLM-jp>"
|
|
],
|
|
"bos_token": "<s|LLM-jp>",
|
|
"clean_up_tokenization_spaces": false,
|
|
"cls_token": "<CLS|LLM-jp>",
|
|
"eod_token": "<EOD|LLM-jp>",
|
|
"eos_token": "<EOD|LLM-jp>",
|
|
"extra_ids": 0,
|
|
"legacy": false,
|
|
"mask_token": "<mask|LLM-jp>",
|
|
"model_max_length": 1000000000000000019884624838656,
|
|
"pad_token": "<pad|LLM-jp>",
|
|
"sep_token": "<SEP|LLM-jp>",
|
|
"sp_model_kwargs": {},
|
|
"tokenizer_class": "PreTrainedTokenizerFast",
|
|
"unk_token": "<unk|LLM-jp>"
|
|
}
|