AlvinAi
AlvinAi
> Besides, in the evaluation, I wonder if Match R-CNN use the in-class setting or not: For in-class evaluation, we only compare the query instances and the gallery instances with...
> > > Besides, in the evaluation, I wonder if Match R-CNN use the in-class setting or not: For in-class evaluation, we only compare the query instances and the gallery...
I got the same problem. It seems that LSTM is hard to compatible with the self-define train config.
You could turn ``normalize_L2 = True`` manually on the path of ``/your_envs/langchain-chatchat-qwen/lib/python3.10/site-packages/langchain/vectorstores/faiss.py`` as below: 
@denglixi @ysjakking @shaoxuan92 @SijieSong Any solution did you get? I also come across this problem.
pip install ctranslate2==3.24.0, this works for cuda 11.x Please ref: https://github.com/OpenNMT/CTranslate2/blob/master/CHANGELOG.md
Sorry, I didn’t save the dataset.
> 大佬你好,请问还有这个比赛的数据集吗? 有的，如有数据集需要，可加我微信ahf1996
> I'm also having the same issue with Azure OpenAI. > > I've followed the manual (https://docs.ragas.io/en/latest/howtos/customisations/azure-openai.html#test-set-generation). > > Keep getting: > > ``` > Generating: 0%| ` > ```...
> I tried it with packing the script in a fastapi app and run it with uvicorn. For the standard server it also get stuck, then I tried to increase...