Petals runs Llama 2 (70B) from Colab at 5 tokens/sec
1–4 of 4 posts
Re: Petals runs Llama 2 (70B) from Colab at 5 tokens/sec
#2Chat web app: http://chat.petals.ml
Colab: https://colab.research.google.com/drive/1uCphNY7gfAUkdDrTx21...
Project description: https://github.com/bigscience-workshop/petals
Re: Petals runs Llama 2 (70B) from Colab at 5 tokens/sec
#3Great project and I'm happy to see it expand to more models!
Re: Petals runs Llama 2 (70B) from Colab at 5 tokens/sec
#4Chat web app: http://chat.petals.ml Colab: https://colab.research.google.com/drive/1uCphNY7gfAUkdDrTx21... Project description: https://github.com/bigscience-workshop/petals
We've moved to a new domain, the chat is now at https://chat.petals.dev