So i was starting off sort of with the end goal of fine tuning llama 3 model with some medical datasets. On cloning GitHub - meta-llama/llama-recipes: Scripts for fine-tuning Meta Llama3 with composable FSDP & PEFT methods to cover single/multi-node GPUs. Supports default & custom datasets for applications such as summarization and Q&A. Supporting a number of candid inference solutions such as HF TGI, VLLM for local or cloud deployment. Demo apps to showcase Meta Llama3 for WhatsApp & Messenger. repo and starting with the basics where they show how to use said restricted models-
I went through everything and it worked uptil the point of downloading the model
after that when trying to generate some response with some prompt in the pipeline, its been running over 40 mins and no response
I have run the pipeline on similar large ones earlier(Nous research llama 2 7b) and it didn’t take nearly as much time. Am I missing something