I'm playing around with this wonderful code but I'm running into a curious issue when I try to train the model with my own data.

I replicated the personachat_self_original.json file structure and added my own data. I deleted dataset_cache_OpenAIGPTTokenizer file but when I try to train, I get this error:

INFO:train.py:Pad inputs and convert to Tensor
Traceback (most recent call last)

Hi, I wrote an extensible chatbot for which developers can add dialogs including the corresponding python modules. So far, I can create a Chat instance using one main template and a default template. It would be nice if I could optionally specify a main folder so that your fantastic library loads all template files from this folder.

For example, now it is not possible to import TextProps of Text component from @urban-bot/core

Only as import { TextProps } from '@urban-bot/core/dist/components/Text';