|
{ |
|
"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 |
|
}, |
|
"46331": { |
|
"content": "<|sep|>", |
|
"lstrip": false, |
|
"normalized": false, |
|
"rstrip": false, |
|
"single_word": false, |
|
"special": true |
|
}, |
|
"46332": { |
|
"content": "<|endoftext|>", |
|
"lstrip": false, |
|
"normalized": false, |
|
"rstrip": false, |
|
"single_word": false, |
|
"special": true |
|
}, |
|
"46333": { |
|
"content": "<|acc|>", |
|
"lstrip": false, |
|
"normalized": false, |
|
"rstrip": false, |
|
"single_word": false, |
|
"special": true |
|
}, |
|
"46334": { |
|
"content": "<|rrn|>", |
|
"lstrip": false, |
|
"normalized": false, |
|
"rstrip": false, |
|
"single_word": false, |
|
"special": true |
|
}, |
|
"46335": { |
|
"content": "<|tel|>", |
|
"lstrip": false, |
|
"normalized": false, |
|
"rstrip": false, |
|
"single_word": false, |
|
"special": true |
|
} |
|
}, |
|
"bos_token": "<s>", |
|
"chat_template": "{% for message in messages %}\n{% if message['role'] == 'system' %}\n{{ '### System:\n' + message['content'] + eos_token }}\n\n{% elif message['role'] == 'user' %}\n{{ '### User:\n' + message['content'] + eos_token }}\n\n{% elif message['role'] == 'assistant' %}\n{{ '### Assistant:\n' + message['content'] + eos_token }}\n\n{% endif %}\n{% if loop.last and add_generation_prompt %}\n{{ '### Assistant:\n' }}\n{% endif %}\n{% endfor %}", |
|
"clean_up_tokenization_spaces": false, |
|
"eos_token": "</s>", |
|
"legacy": false, |
|
"max_length": 4096, |
|
"model_max_length": 1000000000000000019884624838656, |
|
"pad_token": "</s>", |
|
"sp_model_kwargs": {}, |
|
"stride": 0, |
|
"tokenizer_class": "LlamaTokenizer", |
|
"truncation_side": "right", |
|
"truncation_strategy": "longest_first", |
|
"unk_token": "<unk>", |
|
"use_default_system_prompt": true |
|
} |
|
|