LawGLM3 / tokenizer_config.json
jupiterjjj's picture
Upload 17 files
64c4bd5 verified
{
"added_tokens_decoder": {
"64790": {
"content": "[gMASK]",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"64792": {
"content": "sop",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"64795": {
"content": "<|user|>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"64796": {
"content": "<|assistant|>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
}
},
"auto_map": {
"AutoTokenizer": [
"tokenization_chatglm.ChatGLMTokenizer",
null
]
},
"chat_template": "{% if messages[0]['role'] == 'system' %}{% set system_message = messages[0]['content'] %}{% endif %}{% if system_message is defined %}{{ system_message + '\\n' }}{% endif %}{% for message in messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ 'Human: ' + content + '\\nAssistant: ' }}{% elif message['role'] == 'assistant' %}{{ content + '</s>' + '\\n' }}{% endif %}{% endfor %}",
"clean_up_tokenization_spaces": false,
"do_lower_case": false,
"eos_token": "</s>",
"model_max_length": 1000000000000000019884624838656,
"pad_token": "<unk>",
"padding_side": "left",
"remove_space": false,
"split_special_tokens": false,
"tokenizer_class": "ChatGLMTokenizer",
"unk_token": "<unk>"
}