Deploying A LLAMA Model On PVT Server

basic things that i found that will help me with on the road
- hugging face - github for large language models
- runpods - GPU server renting place for run machine learning models
- thebloke - hugging face dude that creating more efficient language models. every one is using his models i dont know why https://huggingface.co/TheBloke
most easiest way that i found to host language model and create an API is by using the runpods. but they asking for minimum top up of 25$ so thats can not be done in my current financial status so i have to find a cost effective way. following video is the best video that i found to do this via runpods

https://www.youtube.com/watch?v=kKkWuxaXfqM