Vladimir Pavlov

In half precision mode 6.7b fits on a 3090. As for the output quality, you need to tweak generation parameters a little, [this blogpost](https://huggingface.co/blog/how-to-generate) explains quite a bit. Here's a...

Authors say in the paper that the model was trained on text in markdown format, so giving markdown-ish prompts to the model should probably work best, I guess. Padding params...

@FurkanGozukara Those are just what I've ended up with after playing around with the model for a bit. There was no real methodology for picking those. They just produced somewhat...