Comments (3)
from med-chatglm.
您好,感谢您的关注,当前模型的效果确实存在局限,尤其针对chatGLM这种训练过程比较完备的模型,我们的全量微调策略会在一定程度上带来性能下降,未来我们会尝试和华驼类似的lora微调。此外,模型当前的多轮对话能力有限,我们也会不断完善
from med-chatglm.
您好,感谢您的关注,当前模型的效果确实存在局限,尤其针对chatGLM这种训练过程比较完备的模型,我们的全量微调策略会在一定程度上带来性能下降,未来我们会尝试和华驼类似的lora微调。此外,模型当前的多轮对话能力有限,我们也会不断完善
我也遇到了这个问题“我们的全量微调策略会在一定程度上带来性能下降”, 会导致模型忘记原有的日常知识
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.