{ | |
"added_tokens_decoder": { | |
"0": { | |
"content": "<|pad|>", | |
"lstrip": false, | |
"normalized": false, | |
"rstrip": false, | |
"single_word": false, | |
"special": true | |
}, | |
"1": { | |
"content": "<|startoftext|>", | |
"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": "<|unknown|>", | |
"lstrip": false, | |
"normalized": false, | |
"rstrip": false, | |
"single_word": false, | |
"special": true | |
} | |
}, | |
"bos_token": "<|startoftext|>", | |
"clean_up_tokenization_spaces": false, | |
"eos_token": "<|endoftext|>", | |
"model_max_length": 1024, | |
"pad_token": "<|pad|>", | |
"tokenizer_class": "PreTrainedTokenizerFast", | |
"unk_token": "<|unknown|>" | |
} | |