import json
import argparse

from llama_cpp import Llama

parser = argparse.ArgumentParser()
parser.add_argument("-m", "--model", type=str, default="/data/llama/7B/ggml-model-f16.bin")
args = parser.parse_args()

llm = Llama(model_path=args.model, n_ctx=8192, n_threads=16, n_gpu_layers=40)

def read_file_to_string(filename):
    try:
        with open(filename, 'r') as file:
            data = file.read()
        return data
    except FileNotFoundError:
        print("File not found.")
        return None

filename = 'genesis70.txt'
file_content = read_file_to_string(filename)
if file_content is not None:
    output = llm(
        file_content,
        max_tokens=2048,
        #stop=["Q:", "\n"],
        echo=True,
    )

print(json.dumps(output, indent=2))