Transformers
tom-20k / tokenizer_config.json
Tran Thai
Upload tokenizer
b62778b verified
Raw
History Blame Contribute Delete
2.3 kB
{
"add_prefix_space": true,
"added_tokens_decoder": {
"0": {
"content": "<pad>",
"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": "<unk>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"20000": {
"content": "<translate-en-vi>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"20001": {
"content": "<translate-vi-en>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"20002": {
"content": "<pad_0>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"20003": {
"content": "<pad_1>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"20004": {
"content": "<pad_2>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"20005": {
"content": "<pad_3>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"20006": {
"content": "<pad_4>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"20007": {
"content": "<pad_5>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
}
},
"additional_special_tokens": [],
"clean_up_tokenization_spaces": false,
"eos_token": "</s>",
"extra_ids": 0,
"extra_special_tokens": {},
"legacy": true,
"model_max_length": 1000000000000000019884624838656,
"pad_token": "<pad>",
"sp_model_kwargs": {},
"tokenizer_class": "T5Tokenizer",
"unk_token": "<unk>"
}