[P] Running Llama 2 locally in <10 min

I wanted to play with Llama 2 right after its release yesterday, but it took me \~4 hours to download all 331GB of the 6 models. If you don’t have 4 hours or 331GB to spare, I brought all the models into XetHub, where it’s now available for you to use: [https://xethub.com/XetHub/Llama2](https://xethub.com/XetHub/Llama2).

I used xet mount to get started in seconds, and within a few minutes, I had the model generating text without needing to download everything or make an …

api call chat code download everything inference install instance llama machinelearning requirements test text ubuntu venv