chatglm3-6b-32k / tokenizer_config.json
chielo's picture
add ChatGLMTokenizerFast and ChatGLMTokenizerConverter
7ba7038
raw
history blame
559 Bytes
{
"name_or_path": "THUDM/chatglm3-6b-32k",
"remove_space": false,
"do_lower_case": false,
"tokenizer_class": "ChatGLMTokenizer",
"chat_template": "{% for message in messages %}{% if loop.first %}[gMASK]sop<|{{ message['role'] }}|> \n {{ message['content'] }}{% else %}<|{{ message['role'] }}|> \n {{ message['content'] }}{% endif %}{% endfor %}{% if add_generation_prompt %}<|assistant|>{% endif %}",
"auto_map": {
"AutoTokenizer": [
"tokenization_chatglm.ChatGLMTokenizer",
"tokenization_chatglm.ChatGLMTokenizerFast"
]
}
}