Could you share what you did to convert the models? The mirrors aren't very reli... | Hacker News

Hacker Newsnew | past | comments | ask | show | jobs | submit

		ddren on March 16, 2023 \| parent \| context \| favorite \| on: Show HN: Alpaca.cpp – Run an Instruction-Tuned Cha... Could you share what you did to convert the models? The mirrors aren't very reliable and it would be good to have it documented somewhere. There is some discussion about this at https://github.com/ggerganov/llama.cpp/issues/172

antimatter15 on March 16, 2023 [–]

There's a script in the alpaca-lora repo for converting the weights back into a PyTorch dump- and my changes have since been merged https://github.com/tloen/alpaca-lora/pull/19

Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact