llama-7b / tokenizer_config.json
chujiezheng's picture
Add chat_template so that it can be used for chat out-of-box
dd4402b
{
"add_bos_token": true,
"add_eos_token": false,
"bos_token": {
"__type": "AddedToken",
"content": "<s>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
},
"chat_template": "{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% set system_message = '' %}{% endif %}{% for message in loop_messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if loop.index0 == 0 %}{{ bos_token + system_message }}{% endif %}{% if message['role'] == 'user' %}{{ '\\n\\nUser: ' + message['content'].strip() }}{% elif message['role'] == 'assistant' %}{{ '\\n\\nAssistant: ' + message['content'].strip() }}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '\\n\\nAssistant:' }}{% endif %}",
"clean_up_tokenization_spaces": false,
"eos_token": {
"__type": "AddedToken",
"content": "</s>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
},
"model_max_length": 2048,
"pad_token": null,
"sp_model_kwargs": {},
"tokenizer_class": "LlamaTokenizer",
"unk_token": {
"__type": "AddedToken",
"content": "<unk>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
}
}