Yea it’s called Text Generation web UI. If you check out the Ooba Booga git, it goes into good details. From what I can tell it’s based on the automatic1111 UI for stable diffusion.
GPTQ-for-llama with ooba booga works pretty well. I’m not sure to what extent it uses CPU, but my GPU is at 100% during inference so it seems to be mainly that.
Someone said you can format links so that login is not required to subscribe. I still don’t totally understand how all this works. The example they gave was /c/news@lemmy.pineapplemachine.com
Ha, where do you find such talents⸮
I’m sure there’s an instance for that
The modern version just made the news. Death in 20ms by the abyss
It makes every comment like yours all the more valuable :)
Wow oil and now this. Good for Norway
Some subs are pointing to Lemmy. The Star Trek instance is awesome , less about complaining about the shows, more about fun trek stuff. Fell in love
Yea it’s called Text Generation web UI. If you check out the Ooba Booga git, it goes into good details. From what I can tell it’s based on the automatic1111 UI for stable diffusion.
GPTQ-for-llama with ooba booga works pretty well. I’m not sure to what extent it uses CPU, but my GPU is at 100% during inference so it seems to be mainly that.
Someone said you can format links so that login is not required to subscribe. I still don’t totally understand how all this works. The example they gave was /c/news@lemmy.pineapplemachine.com