RoSEtta-base-ja / tokenizer_config.json
yano0's picture
Add new SentenceTransformer model.
9221208 verified
{
"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": [
"<EOD|LLM-jp>"
],
"bos_token": "<s|LLM-jp>",
"clean_up_tokenization_spaces": false,
"cls_token": "<CLS|LLM-jp>",
"eod_token": "</s|LLM-jp>",
"eos_token": "</s|LLM-jp>",
"extra_ids": 0,
"mask_token": "<MASK|LLM-jp>",
"max_length": 1024,
"model_max_length": 1024,
"pad_to_multiple_of": null,
"pad_token": "<PAD|LLM-jp>",
"pad_token_type_id": 0,
"padding_side": "right",
"sep_token": "<SEP|LLM-jp>",
"sp_model_kwargs": {},
"stride": 0,
"tokenizer_class": "PreTrainedTokenizerFast",
"truncation_side": "right",
"truncation_strategy": "longest_first",
"unk_token": "<unk|LLM-jp>"
}