当前位置: 首页 > news >正文

网站建设广州公司seo研究中心

网站建设广州公司,seo研究中心,可以浏览的外文网站,wordpress 阿里云ossNLP实践——Llama-2 多轮对话prompt构建 1. 问题提出2. prompt的正确形式3. 效果测试4. 结尾 1. 问题提出 最近,META开源了Llama-2模型,受到了广泛的关注和好评,然而,在官方给的使用说明中,并没有对使用方法进行特别细…

NLP实践——Llama-2 多轮对话prompt构建

  • 1. 问题提出
  • 2. prompt的正确形式
  • 3. 效果测试
  • 4. 结尾

1. 问题提出

最近,META开源了Llama-2模型,受到了广泛的关注和好评,然而,在官方给的使用说明中,并没有对使用方法进行特别细节的介绍,尤其是对于对话任务,这就给我们在使用时带来了很多困扰。

以ChatGLM为例,在执行多轮对话时,需要将历史信息拼接到输入中,以供模型在生成时计算历史token与当前query之间的交互(self-attn):

# ChatGLM中对话prompt的产生:prompt = ""for i, (old_query, response) in enumerate(history_input):prompt += "[Round {}]\n问:{}\n答:{}\n".format(i, old_query, response)prompt += "[Round {}]\n问:{}\n答:".format(len(history_input), query_input)

所以可以很自然的想到,如果使用Llama-2模型进行对话,应该也有这样一套模板,与训练过程中的对话形式相匹配。

于是经过简单的搜索后,在reddit论坛找到了Llama-2官方所提供的说明:

https://www.reddit.com/r/LocalLLaMA/comments/155po2p/get_llama_2_prompt_format_right/

2. prompt的正确形式

根据官方账号给出的说明,在对话时,用户所提供的prompt应当满足以下形式:

<s>[INST] <<SYS>>
{{ system_prompt }}
<</SYS>>{{ user_message }} [/INST]

其中,<s><\s><<SYS>><</SYS>>[INST],以及[/INST]是特殊token,标记着prompt中各个部分的构成。

{{ system_prompt }}部分是整个对话中的通用前缀,一般用来给模型提供一个身份,作为对话的大背景。
{{ user_message }}部分是用户所提供的信息,可以理解为多轮对话中其中一轮对话的内容。

并且,其给出了一个样例:

<s>[INST] <<SYS>>
You are a helpful, respectful and honest assistant. Always answer as helpfully as possible, while being safe.  Your answers should not include any harmful, unethical, racist, sexist, toxic, dangerous, or illegal content. Please ensure that your responses are socially unbiased and positive in nature.If a question does not make any sense, or is not factually coherent, explain why instead of answering something not correct. If you don't know the answer to a question, please don't share false information.
<</SYS>>There's a llama in my garden 😱 What should I do? [/INST]

然而,这个简单的样例并不能很好的反映多轮对话的场景,因为它只描述了用户怎样提供第一轮输入,对于几个特殊token如何使用,也没有很好的说明。

幸运的是,在评论区有用户@Evening_Ad6637给出了更加完整的样例以供我们参考:

假设输入是以下形式的对话:

<s>[INST] <<SYS>>You are are a helpful... bla bla.. assistant<</SYS>>Hi there! [/INST] Hello! How can I help you today? </s><s>[INST] What is a neutron star? [/INST] A neutron star is a ... </s><s> [INST] Okay cool, thank you! [/INST]

那么当这个整体作为prompt输入给模型去进行generate时,模型的输出应该是类似于You're welcome! 之类的话。

更详细的解释一下:

    1. 每一组<s></s>之间是一个相对完整的单元,可以理解为一个对话轮次(如果直接给一个文本作为输入,也可以看到模型的输入结果分别是以这两个BOS和EOS token作为结尾的)。
    1. [INST][/INST]用于区分在当前这一轮的对话(历史)中,用户输入的部分与模型返回的部分。位于[INST]之后,/[INST]之前的文本,是用户在这一轮次对话中所输入的query,而/[INST]之后的文本,是模型针对这一query所作出的回答。
    1. 在对话中的第一组单元,可以提供整个对话的背景信息,并以<<SYS>><</SYS>>作为特殊标记,位于它们之间的,是对话的背景信息。
    1. 需要额外注意,有些特殊标记与文本之间是有空格的,容易遗漏。

3. 效果测试

为了验证prompt是否有效,我们做一个简单的实验,场景是询问动物相关的问题。

(1)首先假设Llama-2模型是一个动物学家,以此作为背景:

You are a zoologist, you will answer my questions about animals.

(2)然后提供一轮对话历史:

- What is an elephant?
- Ah, an excellent question! Elephants are fascinating creatures, and I'm happy to share my knowledge with you.\nAn elephant is a large, intelligent, and social mammal that belongs to the family Elephantidae.

(3)接下来,提供新一轮对话的query

How much does it weigh?

注意,在这里我回避了使用elephant这个词,而是直接用it进行指代。

(4)完整的prompt
根据前文所述的prompt格式,可以将当前轮次输入给模型进行generate的完整prompt构造如下:

text = """<s>[INST] <<SYS>>
You are a zoologist, you will answer my questions about animals. 
<</SYS>>What is an elephant? [/INST] Ah, an excellent question! Elephants are fascinating creatures, and I'm happy to share my knowledge with you.\nAn elephant is a large, intelligent, and social mammal that belongs to the family Elephantidae.</s><s>[INST] How much does it weigh? [/INST]"""

(5)返回结果
经过generate(生成参数为:{“max_length”: 4096, “num_beams”: 3, “temperature”: 0.9})并解码之后,模型生成结果为:

"<s><s> [INST] <<SYS>>\nYou are a zoologist, you will answer my questions about animals. \n<</SYS>>\n\nWhat is an elephant? [/INST] Ah, an excellent question! Elephants are fascinating creatures, and I'm happy to share my knowledge with you.\nAn elephant is a large, intelligent, and social mammal that belongs to the family Elephantidae.</s><s> [INST] How much does it weigh? [/INST]  Great question! The weight of an elephant can vary depending on the species and the individual animal. Here are the average weights for the two main species of elephants:\n* African elephants: Males typically weigh between 5,000 to 14,000 pounds (2,268 to 6,350 kilograms), while females weigh between 4,000 to 9,000 pounds (1,814 to 4,082 kilograms).\n* Asian elephants: Males typically weigh between 3,000 to 6,000 pounds (1,361 to 2,722 kilograms), while females weigh between 2,000 to 3,000 pounds (907 to 1,361 kilograms).\nIt's worth noting that these are just averages, and individual elephants can vary significantly in weight depending on various factors such as age, sex, and nutrition.</s>"

可以看到对话的效果还是不错的,可以比较好的回答出当前轮次关于大象体重的问题。

4. 结尾

本文介绍了如何构建Llama多轮对话的prompt,以适应模型的训练过程中的结构。如果需要搭建一个对话工具,还需要进行一些其他额外的工作,例如对模型生成结果进行截断、对中间kv进行缓存等。

chat与stream_chat的实现可以参考chatGLM的写法:
https://huggingface.co/THUDM/chatglm2-6b/blob/main/modeling_chatglm.py

如何在对话过程中进行显存控制,可以参考我之前的这一篇博客:
https://blog.csdn.net/weixin_44826203/article/details/130401177

此外,还有关于特殊token的一点小疑问,我实验过程中所使用的Llama-2-7b-chat-hf模型,只将<s><\s>列为了特殊token,而<<SYS>><</SYS>>[INST],以及[/INST]都只是普通字符,在tokenize的时候会被切分开,不知道是我用错了模型还是什么其他的原因,希望官方在后续能够提供更加详细的说明介绍。

如果本文对你的学习和工作有所帮助的话,记得点一个免费的赞。转载请注明出处。

http://www.yidumall.com/news/740.html

相关文章:

  • 学做网站的学校企业推广平台
  • 什么是网站托管百度收录是什么意思
  • 上海东道设计成都网站seo厂家
  • 全国网站建设公司排名免费seo技术教程
  • 在线图片修改新手做seo怎么做
  • 做网站的流程分析-图灵吧网络营销专业是学什么的
  • 做自媒体资源的网站保温杯软文营销300字
  • 川沙网站建设南宁百度推广代理公司
  • 做标书的专业网站百度搜索什么关键词排名
  • 做任务网站源码推广营销
  • 客户网站分析百度推广竞价开户
  • 彭州网站建设程序员培训
  • 网站建设教程浩森宇特免费网页模板网站
  • wordpress 注册发邮件班级优化大师怎么下载
  • 莱芜网站建设排行免费外链代发平台
  • 建设个人网站教程微信推广软件哪个好
  • 与人妖做视频网站品牌seo如何优化
  • 网站备案相关手续费临汾网络推广
  • 青岛安装建设股份公司网站seo搜索引擎优化师
  • 买过域名之前就可以做网站了吗?小说网站排名免费
  • 文山seo搜索引擎优化代理
  • 网站建设费用首选网络百度一下马上知道
  • 淘宝联盟链接的网站怎么做链交换
  • 定制旅游网站建设成都2345网址导航官网官方电脑版
  • id怎么打开wordpressseo搜索如何优化
  • 电商网站的二级菜单怎么做郑州品牌网站建设
  • 河北省建设工程协会网站优化方案官网电子版
  • 怎样给公司做一个网站seo销售
  • 在网站做时时彩代理违法短期培训学什么好
  • wordpress 个人资料页电脑网络优化软件