In [1]: from llama_cpp import Llama

In [2]: class A:
   ...:     def __init__(self):
   ...:         self.model = Llama('/Users/pas/.cache/py-llm-core/models/mistral', verbose=False, n_ctx=4000, n_gpu_layers=100, n_threads=4)
   ...:     def generate(self, prompt):
   ...:         return self.model.create_completion(prompt)
   ...:     def free_model(self):
   ...:         del self.model
   ...:

In [3]: instance = A()

In [4]: instance.generate('Write a recipe to make a pizza')
Out[4]:
{'id': 'cmpl-76b2943e-1169-4062-bb6b-8e916279b329',
 'object': 'text_completion',
 'created': 1696768489,
 'model': '/Users/pas/.cache/py-llm-core/models/mistral',
 'choices': [{'text': ' crust that is perfect for a thin and crispy pizza.\n\nIngredients:\n- 3 cups all-purpose flour\n- 1 package active dry yeast\n- 2 tablespoons olive oil\n- 1 teaspoon salt\n- 1 cup warm water\n\nInstructions:\n\n1) In a large mixing bowl, combine the flour and yeast.\n\n2) Add the olive oil and salt to the mixture and stir until well combined.\n\n3) Pour in the warm water and use your hands to knead the dough until it forms a smooth ball.',
   'index': 0,
   'logprobs': None,
   'finish_reason': 'length'}],
 'usage': {'prompt_tokens': 8, 'completion_tokens': 128, 'total_tokens': 136}}

In [5]: instance.free_model()
ggml_metal_free: deallocating