Qwen-14B-lora-pretrain / tokenizer_config.json
ytcheng's picture
Training in progress, step 500
8ad801f verified
raw
history blame contribute delete
744 Bytes
{
"added_tokens_decoder": {},
"auto_map": {
"AutoTokenizer": [
"tokenization_qwen.QWenTokenizer",
null
]
},
"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' %}{{ content }}{% elif message['role'] == 'assistant' %}{{ content }}{% endif %}{% endfor %}",
"clean_up_tokenization_spaces": true,
"eos_token": "<|endoftext|>",
"model_max_length": 8192,
"pad_token": "<|endoftext|>",
"padding_side": "right",
"split_special_tokens": false,
"tokenizer_class": "QWenTokenizer"
}