DISC-LawLLM-Int8 / tokenizer_config.json
JigmeNgodup's picture
Upload tokenizer_config.json
4031665 verified
{
"add_bos_token": false,
"add_eos_token": false,
"auto_map": {
"AutoTokenizer": [
"tokenization_baichuan.BaichuanTokenizer",
null
]
},
"bos_token": {
"__type": "AddedToken",
"content": "<s>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": true
},
"clean_up_tokenization_spaces": false,
"eos_token": {
"__type": "AddedToken",
"content": "</s>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": true
},
"model_max_length": 4096,
"pad_token": {
"__type": "AddedToken",
"content": "<unk>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": true
},
"padding_side": "right",
"sp_model_kwargs": {},
"tokenizer_class": "BaichuanTokenizer",
"unk_token": {
"__type": "AddedToken",
"content": "<unk>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": true
},
"use_default_system_prompt": false,
"chat_template": "{% if messages[0]['role'] == 'system' %}{% set system_message = messages[0]['content'] %}{% endif %}{% if system_message is defined %}{{ system_message }}{% endif %}{% for message in messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ '<s>user\\n' + content + '</s>\\n<s>assistant\\n' }}{% elif message['role'] == 'assistant' %}{{ content + '</s>' + '\\n' }}{% endif %}{% endfor %}"
}