Scripts/Inference_llama.cpp.py

from llama_cpp import Llama

# Insert your research topic here
RESEARCH_TOPIC = """

"""

model_path = "./" # Path to the directory containing your model weight files

llm = Llama(
    model_path=model_path,
    n_gpu_layers=33, 
    n_ctx=2048,
    n_threads=4
)

topic = RESEARCH_TOPIC.strip()
prompt = f"USER: Research Topic: \"{topic}\"\nLet's think step by step:\nASSISTANT:"


output = llm(
    prompt,
    max_tokens=2500,
    temperature=0.7,
    top_p=0.9,
    repeat_penalty=1.1
)

result = output.get("choices", [{}])[0].get("text", "").strip()

print(result)