!pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
    repo_id="darkai-1/darkit-1.5-pro",
    filename="darkit-1.5-pro.gguf",
    n_ctx=4096,
    n_threads=4,
    n_gpu_layers=35,
)

messages = [
    {
        "role": "user",
        "content": "Who are you?"
    }
]

stream = llm.create_chat_completion(
    messages=messages,
    temperature=0.7,
    top_p=0.8,
    top_k=20,
    stream=True
)

full_text = ""

for chunk in stream:
    delta = chunk["choices"][0]["delta"]

    if "content" in delta:
        text = delta["content"]

        print(text, end="", flush=True)

        full_text += text