from ctransformers import AutoModelForCausalLM

llm_model = AutoModelForCausalLM.from_pretrained(
    "TheBloke/zephyr-7B-alpha-GGUF",
    model_file="zephyr-7b-alpha.Q4_K_M.gguf",
    model_type="llama",
    max_new_tokens=256,
    temperature=0.7
)