Open dream-desktop opened 1 year ago
Hi @dream-desktop,
Thanks for your attention. Currently, 6G is not sufficient for running Phoenix
. We will work on the Quantization version.
Or you can try Phoenix
using cpu:
python -m llmzoo.deploy.cli --model-name FreedomIntelligence/phoenix-inst-chat-7b --device cpu
which requires ~30GB of CPU memory.
Best, Zhihong
Please check if this helps: https://gist.github.com/rain-1/8cc12b4b334052a21af8029aa9c4fafc @dream-desktop
It is for LLaMA based models
My computer has the rtx 2060 6G, the results say my gpu is lack, is there any way to run the phoenix model. thank you.