Simply use this model as you would any other now. Below is an example:
tokenizer = transformers.LLaMATokenizer.from_pretrained("Bitsy/Not-LLaMA-7B-Pytorch-Transformer-Compatible")
model = transformers.LLaMAForCausalLM.from_pretrained("Bitsy/Not-LLaMA-7B-Pytorch-Transformer-Compatible")