|
{ |
|
"add_bos_token": false, |
|
"add_prefix_space": false, |
|
"added_tokens_decoder": { |
|
"1": { |
|
"content": "\"", |
|
"lstrip": false, |
|
"normalized": true, |
|
"rstrip": false, |
|
"single_word": false, |
|
"special": true |
|
}, |
|
"2": { |
|
"content": "#", |
|
"lstrip": false, |
|
"normalized": true, |
|
"rstrip": false, |
|
"single_word": false, |
|
"special": true |
|
}, |
|
"50256": { |
|
"content": "<|endoftext|>", |
|
"lstrip": false, |
|
"normalized": true, |
|
"rstrip": false, |
|
"single_word": false, |
|
"special": true |
|
}, |
|
"50257": { |
|
"content": "</s>", |
|
"lstrip": false, |
|
"normalized": false, |
|
"rstrip": false, |
|
"single_word": false, |
|
"special": true |
|
}, |
|
"50258": { |
|
"content": "<s>", |
|
"lstrip": false, |
|
"normalized": false, |
|
"rstrip": false, |
|
"single_word": false, |
|
"special": true |
|
} |
|
}, |
|
"bos_token": "<s>", |
|
"clean_up_tokenization_spaces": true, |
|
"eos_token": "</s>", |
|
"errors": "replace", |
|
"model_max_length": 32768, |
|
"pad_token": "\"", |
|
"tokenizer_class": "GPT2Tokenizer", |
|
"unk_token": "<|endoftext|>" |
|
} |
|
|