John Christian Lønningdal

> I dare to suggest an option > >  [company_3.zip](https://github.com/feathericons/feather/files/6766234/company_3.zip) This one looks to be in line with the look of the icon set. Is the icon set maintained/expanded...

Was surprised there was no way to add custom headers to the response of http-server. I need it in order to add "Cross-Origin-Opener-Policy: same-origin" and "Cross-Origin-Embedder-Policy: require-corp" in order to...

This package just calls PowerShell for windows in order to enumerate the voices. But for some reason MS had chosen to not make all voices visible through this API call....

So are the autoregressive samples for the provided text in the context? Or are they something that can be pre-run for any voice and then used to generate output faster?...

I am using SocketIOUnity that is built on top of this library. I am having issues where sending two Emits after each other seems to cause some kind of exception...

From what I can see there is no API endpoint even if you run the web server. It will load the model each time by calling the main.exe with the...

Yes this would speed up requests immensely. I don't know exactly how these models work but it looks a bit odd that it seems slow to add each token in...

For alpaca, shouldn't you use this template for this kind of query? At least for me alpaca is giving good output when I use prompts that has these ### markers:...

Personally only getting decent results with "default" that uses the ### markers as well as "instruction-alpaca", so possibly that is how it was trained? Btw I am using alpaca 13B...

I never got the llama model to work, but alpaca 13B works fine. The cpp file tries to call main.exe which the llama build process does not generate (it makes...