Hacker News Reader

I see the quantized model is supplied.

> Note: the full model on GPU (16GB of RAM required) performs much better in our qualitative evaluations.

Is there a download for a trained full model?

They have the LoRA delta weights on huggingface, which is linked on the github. Since it's the just the deltas, they're substantially smaller (~8mb), and you'll need to supply the original 7b LLaMA yourself.

just dequantize it

Arguably the funniest comment I've seen in a while

Reply on news.ycombinator.com