JINIAC_tokenizer_v0.1 / tokenizer_config.json
u-10bei's picture
Upload 3 files
584e4ca verified
raw
history blame
1.81 kB
{
"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": "<pad>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"4": {
"content": "<CLS>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"5": {
"content": "<SEP>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"6": {
"content": "<EOD>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"7": {
"content": "<MASK>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
}
},
"additional_special_tokens": [
"<EOD>"
],
"bos_token": "<s>",
"clean_up_tokenization_spaces": true,
"cls_token": "<CLS>",
"eos_token": "</s>",
"extra_ids": 0,
"legacy": false,
"mask_token": "<MASK>",
"model_max_length": 2048,
"pad_token": "<pad>",
"sep_token": "<SEP>",
"sp_model_kwargs": {},
"split_special_tokens": true,
"tokenizer_class": "T5Tokenizer",
"unk_token": "<unk>"
}