3c
Ryan W
3c7a30d512ec597604d0a983c47c8a4e910999f236d6e628df74bde66140a6cd
AI enthusiast
Model is https://huggingface.co/TheBloke/airoboros-65B-gpt4-1.2-GGML
Software is https://github.com/ggerganov/llama.cpp
Not pretend that response was fast. A 30B or even 13B model might be faster than Pygmalion.
Llama can offload layers to GPU.
Koboldcpp can use llama.
That model is huge! How do you even run it?
Yeah I didn’t put any Bitcoin in it though
Thanks for the rec I’ll definitely have to check it out
Probably this, I think
https://nostrcheck.me/media/public/nostrcheck.me_7989170161208255881687899393.webp
That’s really good! Maybe we can talk more in dm

