llama_cpp_python using metal gpu and without simple QA python

l.py

from llama_cpp import Llama
llm = Llama(
      model_path="/Users/vincent/development/llama.cpp/models/mistral-7b-instruct-v0.2.Q4_K_M.gguf",
      n_gpu_layers=-1, # Uncomment to use GPU acceleration
      seed=1337,
      n_ctx=2048)
output = llm(
      "[INST] Question: Write a paper on the industrial revolution. Answer: [/INST]", # Prompt
      max_tokens=None, # Generate up to 32 tokens, set to None to generate up to the end of the context window
      #stop=["Q:", "\n"], # Stop generating just before the model would generate a new question
      echo=True # Echo the prompt back in the output
) # Generate a completion, can also call create_completion
print(output['choices'][0]["text"])