xinj7
xinj7
> 你好，暂时还不支持英文，后续会支持 你好 现在似乎还没有支持？
Hi did you solve the problem? I tried with solution 3 and the router doesn't seem to stop even if it gets the right answer from the first vectorstore. It...
> Hi @eavanvalkenburg ,the deployment_name parameter is filled, but it doesn't works, I think that a proper documentation with a working sample should be in the langchain documentation. https://github.com/hwchase17/langchain/issues/1942 You...
> > > > > 大佬们都微调了多久，我微调后全是重复的语句 > > > > > > > > > > > > 我微调后都是空。。。 > > > > > > > > > 怎么解决的？我也出现空 >...
I face the same issue even when using chatgpt. Did you manage to fix it somehow? Is it just a matter of the model performance?
similar problem here
I think it's a matter of the gpt model performance. When the model doens't understand and complete exactly the same as what we want, e.g. upper case vs lower case,...
> 我是报错找不到“\lib\site-packages\senta\model_files\ernie_1.0_skep_large_ch.Chnsenticorp.cls\save_inference_model\inference_step_601/infer_data_params.json” 后来解决了吗？
> I have the same issue. I can train T5-large on a single 3090 Ti with batch_size=4 without OOM. However, when I tried to use DeepSpeed to speed up training...