from Hacker News

Petals runs Llama 2 (70B) from Colab at 5 tokens/sec

by borzunov on 7/19/23, 8:52 PM with 3 comments

• by borzunov on 7/19/23, 8:52 PM

  Chat web app: http://chat.petals.ml

  Colab: https://colab.research.google.com/drive/1uCphNY7gfAUkdDrTx21...

  Project description: https://github.com/bigscience-workshop/petals

• by amrb on 7/19/23, 10:20 PM

  Great project and I'm happy to see it expand to more models!