LongWriter-glm4-9b / tokenizer_config.json
bys0318's picture
Update tokenizer_config.json
fdfab97 verified
raw
history blame
845 Bytes
{
"added_tokens_decoder": {
"151329": {
"content": "<|endoftext|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
}
},
"auto_map": {
"AutoTokenizer": [
"tokenization_chatglm.ChatGLM4Tokenizer",
null
]
},
"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 %}",
"clean_up_tokenization_spaces": false,
"do_lower_case": false,
"eos_token": "<|endoftext|>",
"model_max_length": 1000000000000000019884624838656,
"padding_side": "left",
"remove_space": false,
"tokenizer_class": "ChatGLM4Tokenizer"
}