YuhaoWU

 I think for T5 summarization we will have to append the prefix "summarize: " to every input data.

Hi, When I run '' in Tune_T5_WikiHow-Github.ipynb, an exception is thrown but I cannot find a related solution online, > --------------------------------------------------------------------------- > MisconfigurationException Traceback (most recent call last) > in...

For custom RE dataset with entity marked in advanced

1

Hi, as a green hand, I would like to ask some naive questions: for fine-tuning on a custom RE dataset with entity marked in advanced, 1) do we need to...

我看参考的[安装文档](https://github.com/imClumsyPanda/langchain-ChatGLM/blob/master/docs/INSTALL.md)里面，安装conda环境用的是， `$ conda create -p /your_path/env_name python=3.8` 显式地使用 -p 选项来指定环境路径，但这样反而每次activate该环境的时候，因为该环境没有名字只有-path名，都要**非常麻烦的写出 /your_path/env_name** `$ source activate /your_path/env_name` 替代方案 / Alternative Solutions：我**新增了一条可选项**，安装更丝滑 `conda create -n env_name python=3.8`

##**功能描述 / Feature Description** 我看参考的[安装文档](https://github.com/imClumsyPanda/langchain-ChatGLM/blob/master/docs/INSTALL.md)里面，安装conda环境用的是， `$ conda create -p /your_path/env_name python=3.8` 显式地使用 -p 选项来指定环境路径，但这样反而每次activate该环境的时候，因为该环境没有名字只有-path名，都要**非常麻烦的写出 /your_path/env_name** `$ source activate /your_path/env_name` **实现建议 / Implementation Suggestions** 看似多此一举？ **替代方案 / Alternative Solutions** 为何不直接改成 `conda...

老师能传个Recommender System那一章节的视频吗，就一节

1

想听听言简意赅的Recommender System协同过滤内容~

Dynamic FewShot GPTClassifier: does it cache Embd locally?

6

I wonder: 1. if `DynamicFewShotGPTClassifier ` will cache embeddings by OpenAI locally for the 1st time calling it. 2. And can we access them as embeds can be used in...

centOS镜像能通过其他途径分享一下不？谢谢啦