Comments (2)
你的见解是合理的,手动构建模板无法保证指令多样性,我们通过self-struct的方法构建指令数据集,由于gpt3.5功能比gpt3更强大,所以我们使用gpt3.5一次性生成多个提问和回答。保证了多样性之后,我们对一些重要的疾病手动设计了生成模板进行增强生成,并吸收了现有的问答数据。具体的知识库和生成代码还在整理中,感谢关注!
from med-chatglm.
感谢回复。所以我总结一下,你们的做法是
方法1. 利用gpt3.5阅读某条疾病医疗知识,然后针对这一条疾病医疗知识生成多个提问和回答。
方法2. 部分重要疾病则是利用方法1 + 手动设计模版
最后的数据集合是方法1+方法2+现有的问答数据。
关于方法1,我自己通过修改belle项目中的prompt,尝试过让chatgpt(gpt3.5-turbo)先阅读材料,然后针对该材料提问和回答,发现效果并不理想(格式和内容质量都很不稳定)。对于医疗问答任务来说对事实性要求相对来说会更高(所以希望他根据给定医疗知识文本提问和回答而不是凭空生成),像请问你们是如何处理这样的问题呢?单纯的调整prompt似乎并不能满足对于指令数据质量的要求
from med-chatglm.
Related Issues (20)
- modeling_chatglm.py里的quantize能用么?在run_clm.py里添加model.quantize(4)为什么报ImportError: attempted relative import with no known parent package错误
- 项目如何改成cpu微调的,可不可以把用内存,不用显存 HOT 1
- 6G显存问题和模型参数本地目录指向问题 HOT 1
- 把chatglm-6b-med模型放到官方chatglm-6b中训练报错 HOT 1
- ”医学知识库和数据集构建代码还在整理中,整理完成将会发布。“ HOT 3
- 报错150004 is not in list,请问如何进一步修改?谢谢 HOT 3
- 显示不出答案
- 请问如何将知识图谱批量地转为问答对
- Out of memory. 48G is not enough, either. What happend? HOT 1
- 问题
- 是否支持使用多机多卡进行微调?
- chatGLM2微调问题 HOT 1
- 希望取得联系
- 运行报错 HOT 4
- RuntimeError: "LayerNormKernelImpl" not implemented for 'Half' HOT 1
- 批量喂数据给模型
- 是否有定义评价指标
- 运行infer,py出现问题 HOT 1
- 使用RTX 4090D(24GB)运行微调,出现错误,提示超出内存,这该如何解决 HOT 1
- 运行Python infer.py 报错 value 130001 not in list ,切换版本后,运行微调报错 value 150001 not in list 这该如何解决 HOT 1
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from med-chatglm.