|
{ |
|
"add_bos_token": true, |
|
"add_eos_token": false, |
|
"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 |
|
}, |
|
"7": { |
|
"content": "<0x04>", |
|
"lstrip": false, |
|
"normalized": true, |
|
"rstrip": false, |
|
"single_word": false, |
|
"special": false |
|
}, |
|
"32000": { |
|
"content": "|ENDOFTEXT|", |
|
"lstrip": false, |
|
"normalized": false, |
|
"rstrip": false, |
|
"single_word": false, |
|
"special": true |
|
} |
|
}, |
|
"additional_special_tokens": [ |
|
"<unk>", |
|
"<s>", |
|
"|ENDOFTEXT|" |
|
], |
|
"bos_token": "<s>", |
|
"clean_up_tokenization_spaces": false, |
|
"eos_token": "|ENDOFTEXT|", |
|
"legacy": false, |
|
"model_max_length": 1000000000000000019884624838656, |
|
"pad_token": "|ENDOFTEXT|", |
|
"padding_side": "right", |
|
"sp_model_kwargs": {}, |
|
"tokenizer_class": "LlamaTokenizer", |
|
"unk_token": "<unk>", |
|
"use_default_system_prompt": false |
|
} |
|
|