Pari
Pari
这个问题已经解决，我出现此bug应该是torch版本或者cuda版本过低引起的，谢谢
> > 运行chatGPT项目时，一直停留在 No pre-built kernel is found, build and load the cpu_adam kernel during runtime now 显存显示已经载入模型，但没有任何进展。请问是否与内网无法连接网络有关？ > > 能看一下`colossalai check -i`吗？ #### Installation Report #### ------------ Environment ------------...
> cuda 10.1 torch 1.10.0 torchvision 0.11.1 It works 你是解决了吗？我能添加一个你的联系方式吗，我第一次接触这类项目，有些问题问您
I have solved it. PLS check your mmdeploy version acorrding to the [table](https://github.com/open-mmlab/mmdeploy/tree/main#highlights). Furthermore, preparing the dataset according to the [instructions](https://mmpretrain.readthedocs.io/en/latest/user_guides/dataset_prepare.html)
I met the same issue
I tried a project [lanchain-ChatGLM](https://github.com/imClumsyPanda/langchain-ChatGLM),its emmbedding is text2vec. Using both text2vec & LLM(chatglm), the chatbot can answer user's question according to the text materials uploaded by users. So I think...
Thank you for your reply@yzh119，I have figured out the reason for my error, and it was not caused by incomplete download of the submodule. I was not running on a...
same problem， Using pip 22.3.1 from /home/panz/anaconda3/envs/gpt/lib/python3.8/site-packages/pip (python 3.8) WARNING: Implying --no-binary=:all: due to the presence of --build-option / --global-option / --install-option. Consider using --config-settings for more flexibility. DEPRECATION: --no-binary...