polyglot-ko-1.3b-total / tokenizer_config.json
hyunjae's picture
Upload tokenizer
5b99adf verified
{
"added_tokens_decoder": {
"0": {
"content": "<|unused0|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"1": {
"content": "<|unused1|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"2": {
"content": "<|endoftext|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"3": {
"content": "<|sep|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"30000": {
"content": "<|acc|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"30001": {
"content": "<|tel|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"30002": {
"content": "<|rrn|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
}
},
"additional_special_tokens": [
"<|endoftext|>",
"<|sep|>",
"<|acc|>",
"<|tel|>",
"<|rrn|>"
],
"clean_up_tokenization_spaces": true,
"eos_token": "<|endoftext|>",
"max_length": 2048,
"model_max_length": 2048,
"pad_to_multiple_of": null,
"pad_token": "<|endoftext|>",
"pad_token_type_id": 0,
"padding_side": "right",
"stride": 0,
"tokenizer_class": "PreTrainedTokenizerFast",
"truncation_side": "right",
"truncation_strategy": "longest_first"
}