YadiHe
YadiHe
谢谢指点，请问第二个是部署langchian接入形式的llama3，这里的langchian就是可以接入很多大模型给自己选择用哪一个吗？
大佬，在终端中运行以下命令，启动streamlit服务，并按照 autodl 的指示将端口映射到本地，然后在浏览器中打开链接 http://localhost:6006/ ，即可看到聊天界面。 这里怎么打开啊，我到这一步了 
When I train the model with 'att' for 200 epochs, I usually start to see small grid-like noise artifacts appearing around the 20th epoch, and they get worse and worse...
> @YadiHe, as you said, it could be a problem with the net. Just in case, your dataset is public. I would like to explore the reasons behind this. Sorry,...