RJ Adriaansen

This is how I generated it: ``` import pickle import numpy as np f = open('glove.6B.300d.txt', 'r') g = open('glove.6B.300d_pickle', 'wb') word_dict = {} wordvec = [] for idx, line...

Got it to work, but I had to run `!pip install --upgrade ipykernel` first, otherwise I couldn't reconnect to runtime (would stay on 'Busy').

I ran into the same issue. Saving the sprite image to this directory `/usr/local/share/jupyter/nbextensions/google.colab/` solved it for me. You can then load the image: `document.querySelector("#elem").atlasUrl = "/nbextensions/google.colab/complete_atlas_image.jpg";`

You have to set `scope` and `lang_code` as well in [main.py](https://github.com/aahnik/telewater/blob/main/telewater/main.py#L24), see: https://tl.telethon.dev/methods/bots/set_bot_commands.html

I got it running on Google Colab, check [this notebook](https://gist.github.com/rjadr/8967effee72795dd0d9792073a9b4cd5)!

@nafis-saad I fixed the issue in the notebook

@nafis-saad that was just to force the runtime to restart, but I'll remove it.

Looks like the download link is broken, try replacing it with https://s3.amazonaws.com/ahalterman-geo/geonames_index.tar.gz

@nafis-saad I updated the original notebook, and made one for [mordecai3](https://gist.github.com/rjadr/cbbc65bc3ce97bed4e57ca1811c04194) as well.

@Zetaphor Correct, llama.cpp has set the default token context window at 512 for performance, which is also the default `n_ctx` value in [langchain](https://github.com/hwchase17/langchain/blob/master/langchain/llms/llamacpp.py#L30). You can set it at 2048 max,...