提示词格式化
利用jinja2,对提示词进行格式输出。以下是qwen2中tokenizer_config.json文件中的chat_template模块定义的提示词转换方式。
(1)查看qwen2的chat_template
{
"add_prefix_space": false,
"added_tokens_decoder": {
"151643": {
"content": "<|endoftext|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151644": {
"content": "<|im_start|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151645": {
"content": "<|im_end|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
}
},
"additional_special_tokens": ["<|im_start|>", "<|im_end|>"],
"bos_token": null,
"chat_template": "{% for message in messages %}{% if loop.first and messages[0]['role'] != 'system' %}{{ '<|im_start|>system\nYou are a helpful assistant.<|im_end|
>\n' }}{% endif %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>ass
istant\n' }}{% endif %}",
"clean_up_tokenization_spaces": false,
"eos_token": "<|im_end|>",
"errors": "replace",
"model_max_length": 32768,
"pad_token": "<|endoftext|>",
"split_special_tokens": false,
"tokenizer_class": "Qwen2Tokenizer",
"unk_token": null
}
(2)提示词格式话
from jinja2 import Template
# 定义模板字符串
template_str = """
{% for message in messages %}
{% if loop.first and messages[0]['role'] != 'system' %}
{{ '<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n' }}
{% endif %}
{{ '<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n' }}
{% endfor %}
{% if add_generation_prompt %}
{{ '<|im_start|>assistant\n' }}
{% endif %}
"""
# 创建模板对象
template = Template(template_str)
# 定义数据
messages = [
{'role': 'user', 'content': '你好,我需要帮助。'},
{'role': 'assistant', 'content': '你好!我能帮你什么吗?'},
{'role': 'user', 'content': '我想了解一下天气。'},
{'role': 'assistant', 'content': '今天的天气是晴朗的。'},
]
add_generation_prompt = True #一个控制标志,用于在需要时向用户或系统提供额外的提示信息,特别是在生成文本或对话的上下文中。它帮助区分不同的发言者或指示接下来的操作步骤
# 渲染模板
output = template.render(messages=messages, add_generation_prompt=add_generation_prompt)
# 打印输出结果
print(output)