NEBULA-XB-v1.0_SFT_2_epoch / tokenizer_config.json
TeeZee's picture
Update tokenizer_config.json
5601ddb verified
{
"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": "{{ bos_token }}{% if messages[0]['role'] == 'system' %}{{ messages[0]['content'] + '\n\n' }}{% set loop_messages = messages[1:] %}{% else %}{{ 'Below are some instructions that describes some tasks. Write responses that appropriately completes each request.\n\n' }}{% set loop_messages = messages %}{% endif %}{% for message in loop_messages %}{% if message['role'] == 'user' %}{{ '### Instruction:\n' + message['content'] + '\n\n' }}{% elif message['role'] == 'assistant' %}{{ '### Response:\n' + message['content'] + eos_token + '\n\n' }}{% else %}{{ raise_exception('Only user and assistant roles are supported!') }}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '### Response:\n' }}{% endif %}",
"clean_up_tokenization_spaces": false,
"eos_token": "</s>",
"legacy": true,
"model_max_length": 4096,
"pad_token": "<unk>",
"padding_side": "left",
"sp_model_kwargs": {},
"spaces_between_special_tokens": false,
"tokenizer_class": "LlamaTokenizer",
"unk_token": "<unk>",
"use_default_system_prompt": true
}