Rahul Somani

Hi, apologies for the delay. I've taken the links down since I believe people weren't respecting the license. The model is open for non-commercial use. If you'd like to use...

I'm leaving the issue open if anyone wants to discuss :)

@thoppe this is really interesting! The video is quite fun to watch, and a nice direction to explore. Perhaps as you add different filtering criteria -- CUs with dialogues, WS...

Hi @omarsar. As we'd spoken briefly on Slack, I'd like to contribute to this project. Would you prefer I add diagrams straight to the docs or make a PR here?

@FraPochetti @ai-fast-track converting this to a draft for now. Hope to get back to it soon!

Quick observation: @fstroth and rafaelpadilla's project both use NumPy whereas the lightning implementation uses PyTorch. Curious how much of a speedup that would offer

> Numpy would be better for us because eventually pytorch should become an optional dependency (we want to start offering tensorflow support) Makes sense. Ambitious! Not to crowd this space,...

@Breakthrough > unless there's something for numpy I'm unware of? [PyTorch](https://pytorch.org/) can work as a GPU replacement for numpy. Their syntax is similar, and the ability to convert PyTorch `tensors`...

@Breakthrough, that sounds like a great way to go forward, both w.r.t dependencies and efficiency.

@saurabhhjjain Did you try loading any of the other resnext models? There's six of them.