Hacker News new | ask | show | jobs
by avereveard 1041 days ago
I like this for turn by turn conversations: https://huggingface.co/NousResearch/Nous-Hermes-Llama2-13b

this for zero shot instructions: https://huggingface.co/Open-Orca/OpenOrcaxOpenChat-Preview2-...

easiest way would be https://github.com/oobabooga/text-generation-webui

a little more complex way I do is I have a stack with llama.cpp server, a openai adapter, and bettergpt as frontend using the openai adapter as the custom endpoint. bettergpt ux beats oogaboga by a long way (and chatgpt on certain aspects)