zoo_3exp_v2_2epoch_v2_200 / tokenizer_config.json
if001's picture
Upload tokenizer
e5b80ca verified
{
"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
},
"32000": {
"content": "<SEP>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32001": {
"content": "<pad>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32002": {
"content": "<CLS>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32003": {
"content": "<MASK>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32004": {
"content": "<EOD>",
"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>",
"device_map": "auto",
"eos_token": "</s>",
"extra_ids": 0,
"legacy": false,
"mask_token": "</s>",
"model_max_length": 4096,
"pad_token": "</s>",
"sep_token": "<SEP>",
"sp_model_kwargs": {},
"split_special_tokens": true,
"tokenizer_class": "T5Tokenizer",
"unk_token": "<unk>"
}