[ggerganov]

Cool demo

Just want to point out that we are actively working on improving the quantization accuracy / performance of ggml [0]. We already have promising results that are yet to be ported to the WASM code path, so hopefully such type of demos will become a bit better in the future.

[0] https://github.com/users/ggerganov/projects/2

[lxe]

Thank you for your amazing work! This is inspired by your whisper wasm demo!

I can barely keep up with the changes to your repos. You landed gpt-neox / stablelm support right around the time I was finishing up this demo, which I can’t wait to try after I get some sleep.