Errors with Using Python LLM Api with local llama2 13b model

import llm
model = llm.get_model("llama2-chat-13b")
model.prompt("hello").text()

I don't want to run OpenAI in any remote, I am running this locally. I am seeing exceptions on this api

Traceback (most recent call last):
  File "<stdin>", line 1, in <module>
  File "/Users/ramahadevan/Library/Python/3.9/lib/python/site-packages/llm/models.py", line 112, in text
    self._force()
  File "/Users/ramahadevan/Library/Python/3.9/lib/python/site-packages/llm/models.py", line 106, in _force
    list(self)
  File "/Users/ramahadevan/Library/Python/3.9/lib/python/site-packages/llm/models.py", line 91, in __iter__
    for chunk in self.model.execute(
  File "/Users/ramahadevan/Library/Python/3.9/lib/python/site-packages/llm_llama_cpp.py", line 255, in execute
    llm_model = Llama(
  File "/Users/ramahadevan/Library/Python/3.9/lib/python/site-packages/llama_cpp/llama.py", line 365, in __init__
    assert self.model is not None
AssertionError

Start by reproducing the provided Python snippet and tracing the failure through llm/models.py, llm_llama_cpp.py, and llama_cpp/llama.py. Check how the local llama2-chat-13b model is located and initialized; done means the example runs locally without the AssertionError.