Qwen-7B-Chat-Cantonese / tokenizer_config.json
stvlynn's picture
Upload 19 files
7037382 verified
raw
history blame contribute delete
928 Bytes
{
"added_tokens_decoder": {},
"auto_map": {
"AutoTokenizer": [
"tokenization_qwen.QWenTokenizer",
null
]
},
"chat_template": "{% set system_message = 'You are a helpful assistant.' %}{% if messages[0]['role'] == 'system' %}{% set system_message = messages[0]['content'] %}{% endif %}{% if system_message is defined %}{{ '<|im_start|>system\\n' + system_message + '<|im_end|>\\n' }}{% endif %}{% for message in messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ '<|im_start|>user\\n' + content + '<|im_end|>\\n<|im_start|>assistant\\n' }}{% elif message['role'] == 'assistant' %}{{ content + '<|im_end|>' + '\\n' }}{% endif %}{% endfor %}",
"clean_up_tokenization_spaces": true,
"eos_token": "<|im_end|>",
"model_max_length": 32768,
"pad_token": "<|im_end|>",
"padding_side": "left",
"split_special_tokens": false,
"tokenizer_class": "QWenTokenizer"
}