Ajinkya Bankar

The error got resolved when I removed square brackets as: ```trainer.fit( tft, train_dataloaders = train_dataloader, val_dataloaders = val_dataloader ) ``` Also, you need to include ```min_prediction_idx = training_cutoff + 1```...

Hi @sophia-kwon there is another library `Pytorch Forecasting`, which works on `non-periodic` data, as you mentioned above. Here is the link for TFT tutorial- https://pytorch-forecasting.readthedocs.io/en/latest/tutorials/stallion.html

Hi @HarikrishnareddGali, May I know details of getting vicuna13b 4bit quantized model and koala 7b 5_1 bit quantized model? And how to use them within this PrivateGPT?

Getting the same error. Were you able to solve this?

@notBradPitt have you faced such issue?

@notBradPitt I am using the same data and same parameters as given in the notebook. My expectation is that I should get the same results as given in their notebook....

@XiaoYangLiu-FinRL Can you provide more details about sources of randomness for this notebook? And any strategies to fix them?

@notBradPitt @mmmarchetti It can be a good way to replicate the results by choosing a seed value. But won't this lead to limited design space for model training?

Hi @p-c-c and @fredmgg, I have same question. Did you figure out the reason? Looking forward to hearing.

@NeoWang9999 were you able to resolve the issue? Did you use any custom method? Looking forward to hearing