ssd / tokenizer_config.json
tktung's picture
Upload tokenizer
ec754a9 verified
{
"add_bos_token": true,
"add_eos_token": false,
"add_prefix_space": null,
"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
}
},
"bos_token": "<s>",
"chat_template": "{% if messages[0]['role'] == 'system' %}\n {% set loop_messages = messages[1:] %}\n {% set system_message = messages[0]['content'] %}\n{% else %}\n {% set loop_messages = messages %}\n {% set system_message = 'You are a helpful, respectful and honest assistant. Always answer as helpfully as possible, while being safe.' %}\n{% endif %}\n{{- '### Instruction:\n' + system_message + '\n\n' }}\n{% for message in loop_messages %}\n {% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}\n {{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}\n {% endif %}\n {% set content = message['content'] %}\n {% if message['role'] == 'user' %}\n {{- '### Input:\n' + content.strip() + '\n\n'}}\n {% elif message['role'] == 'assistant' %}\n {{- '### Response:\n' + content.strip() + '\n\n'}}\n {% endif %}\n{% endfor %}\n{%- if add_generation_prompt %}\n {{- '### Response:\n' }}\n{%- endif %}",
"clean_up_tokenization_spaces": false,
"eos_token": "</s>",
"legacy": true,
"model_max_length": 1000000000000000019884624838656,
"pad_token": "</s>",
"sp_model_kwargs": {},
"spaces_between_special_tokens": false,
"tokenizer_class": "LlamaTokenizer",
"unk_token": "<unk>",
"use_default_system_prompt": false
}