{ | |
"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 | |
} | |
}, | |
"additional_special_tokens": [], | |
"bos_token": "<s>", | |
"chat_template": "{% for message in messages %}{% if message['role'] == 'user' %}{{ bos_token + '[INST] ' + message['content'] + ' [/INST]' }}{% elif message['role'] == 'system' %}{{ '<<SYS>>\\n' + message['content'] + '\\n<</SYS>>\\n\\n' }}{% elif message['role'] == 'assistant' %}{{ ' ' + message['content'] + ' ' + eos_token }}{% endif %}{% endfor %}", | |
"clean_up_tokenization_spaces": false, | |
"eos_token": "</s>", | |
"legacy": true, | |
"max_length": 8192, | |
"model_max_length": 1000000000000000019884624838656, | |
"pad_token": "<unk>", | |
"padding": true, | |
"sp_model_kwargs": {}, | |
"spaces_between_special_tokens": false, | |
"tokenizer_class": "LlamaTokenizer", | |
"unk_token": "<unk>", | |
"use_default_system_prompt": false | |
} | |