ExtractGPT
ExtractGPT
Chrome 扩展, 可以直接通过 GPT 自动提取网页内容。从而帮助解决网页限制
实际使用效果一般。猜测是通过对网页抽取后,匹配文字,然后进行总结得到的效果。
有时间可以看看实现原理
DeepSpeed-Chat
本章将演示如何在 DS-Chat 代码中使用除 facebook opt 之外的其他预训练模型,以及如何准备并使用自定义数据进行模型训练,以便训练出针对特定领域或应用的大型模型。
应该是一个教程,教学如何进行自定义训练的。
DeepSpeed-Chat 模型与数据 | 大模型训练入门实战
里面提到一个模型 Phoenix-inst-chat-7b , 和 GPT4 对该模型的评价
Model | Ratio |
---|---|
Phoenix-inst-chat-7b vs. ChatGPT | 85.2% |
Phoenix-inst-chat-7b vs. ChatGLM-6b | 94.6% |
Phoenix-inst-chat-7b vs. Baidu-Wenxin | 96.8% |
Phoenix-inst-chat-7b vs. MOSS-moon-003-sft | 109.7% |
Phoenix-inst-chat-7b vs. BELLE-7b-2m | 122.7% |
Phoenix-inst-chat-7b vs. Chinese-Alpaca-7b | 135.3% |
Phoenix-inst-chat-7b vs. Chinese-Alpaca-13b | 125.2% |
更好的提示语
Useful verbs:
Instruct verbs are the first word in the prompt. They are used to instruct the model to do something. They are the most important part of the prompt. We may argue that they act as magic words that make a successful prompt, it helps to make the machine understand and follow your instructions. Each of these verbs has a specific meaning that can help the model understand what kind of answer is expected. For example, if you ask the model to explain something, it will provide a detailed explanation. On the other hand, if you ask the model to summarize something, it will provide a brief overview.
-
Useful words to give directions to your input texts: (point to a location of your input text)
\Given text
\following passage
\Following
\The following -
Useful words to instruct: (to give instructions to the model)
\Explain
\Create
\Generate
\Provide
\Write
\Summarize
\Paraphrase
\Translate
\Rewrite
\Reword
\Rephrase
\List
\Extract
\Pick out
\Analyze
\Define
\Identify
\Describe
\Predict
\Explain
\Analyze
\compare
\Categorize
\Evaluate
\Critique
\Differentiate
\Examine
\Illustrate
\Outline
\Calculate
\Infer
\Revise
\Summarize
\Classify
\Develop
\Evaluate
\Formulate
\Discuss
\Clarify
\Highlight
\Simplify
\Apply
\Suggest / Propose
\Make
* You may add `Can you` in the case of ChatGPT to make it more conversational, but it still works in both the instruct-model and chatGPT models. - Can you provide … - Can you generate …
Common use cases:
Classification
Instruction verbs that are useful for classification tasks in nlp
Classify
the following as a physical or chemical propertyIdentify
main idea of the given passageCategorize
the following passage as either a myth or a factAssign each
item to its corresponding category based on its characteristicsList
the five main categories of the given data set.Group
the items based on their common characteristicsSort
the data based on the date it was collectedLabel
each data point with its corresponding categoryDivide
the data into smaller subgroups based on their similaritiesGroup
the items based on their similarity in featuresLabel
each group with a descriptive name.
Generation
Instruction verbs that are useful for generation tasks
Generate
a new text based on the given parametersCreate
a short catchy headline based on the following, aim to promote the productWrite
a story using the following keywordsFormulate
a new sentence based on the given structureProduce
a new text that is similar in style to the given sampleConstruct
a new text that combines elements from multiple sourcesCompose
a new poem based on the given themeBuild
a new text by combining different elements in a creative wayDevise
a new narrative based on the given informationInvent
a new story using the following elements.
Transformation:
Instruction verbs that are useful for transformation tasks
- Translate:
Translate
the following function into C#Translate
the following into 1. English, 2. French, 3. Swedish
- Summarize:
Summarize
the main points of the given article
- Paraphrase:
Paraphrase
the following sentence to convey the same meaningReword
the following sentence to make it more concise
- Simplify:
Simplify
the following equation for easier understanding
- Revise:
Revise
the following paragraph to make it more clear and concise
- Outline:
Outline
the steps to solve the given problem
- Calculate:
Calculate
the total cost of the following items
- Infer:
Infer
the meaning of the [jargon, vage phrase] based on the following context:
- Apply:
Apply
the following formula to calculate the resultApply
given tone and voice to the passage below
Comparison:
Instruction verbs that are useful for comparison tasks
- Compare:
Compare
and contrast the two given texts
- Contrast:
Contrast
the given passages to highlight their differences
- Differentiate:
Differentiate
between the two given terms
- Examine:
Examine
the similarities and differences between the two given texts
- Analyze:
Analyze
the two given pieces and identify their similarities and differences
- Critique:
Critique
the two given passages and compare their strengths and weaknesses
- Evaluate:
Evaluate
the two given passages and determine which one is more effective
Moment.JS
一个同时支持 js 和 node 的日期和时间库。上百万次使用。
Auto-Dev
AutoDev 是一款高度自动化的 AI 辅助编程工具。AutoDev 能够与您的需求管理系统(例如 Jira、Trello、Github Issue 等)直接对接。在 IDE 中,您只需简单点击,AutoDev 会根据您的需求自动为您生成代码。您所需做的,仅仅是对生成的代码进行质量检查。