Why Hacker News recommends it
3 comments from 2 distinct recommending readers, between 2023 and 2023.
- Recommends
Artem Andreenko on Twitter reports getting the 7B model running on a 4GB RaspberryPi! One token every ten seconds, but still, wow. twitter.com/miolini/status/163498236175…
Using LLaMA with M1 Mac and Python 3.11Read the thread - Recommends
Less than 10 days after I post this, and someone's got the small version of LLaMa running (slowly! but running) on a Pi. twitter.com/miolini/status/163498236175…
Replika users fell in love with their AI chatbot companions. Then they lost themRead the thread - Cites it
This is why I think we're seeing a Stable Diffusion moment for LLMs: simonwillison.net/2023/Mar/11/llama/ Look at the timeline: 24th February 2023: LLaMA is announced, starts being shared with academic partners: research.facebook.com/publications/llam…... 2nd March: Someone posts a PR with a BitTorrent link to the models: github.com/facebookresearch/llama/pull… 10th March: First commit to llama.cpp by Georgi Gerganov: github.com/ggerganov/llama.cpp/commit/2…... 11th March: llama.cpp now runs the 7B model on a 4GB RaspberryPi: twitter.com/miolini/status/163498236175… 12th March: npx dalai llama: cocktailpeanut.github.io/dalai/ 13th March (today): llama.cpp on a Pixel 6 phone: twitter.com/thiteanish/status/163518833… And now, Alpaca. It's not even lunchtime yet! Turned this into a blog post: simonwillison.net/2023/Mar/13/alpaca/
Alpaca: A strong open-source instruction-following modelRead the thread