Update typo in README.md

dvmazur / mixtral-offloading

Run Mixtral-8x7B models in Colab or consumer desktops

MIT License

2.28k stars 223 forks source link

Open kaushalpowar opened 6 months ago

kaushalpowar commented 6 months ago

There was a typo (pack -> back).

Old: Each expert per layer is offloaded separately and only brought pack to GPU when needed.

Changed: Each expert per layer is offloaded separately and only brought back to GPU when needed.