import_dataset.py

import os
import json

# Define the directory path
directory_path = "/home/justin/LLaMA-Factory"

# Change directory to the specified path
try:
    os.chdir(directory_path)
except FileNotFoundError:
    print(f"Error: The directory {directory_path} does not exist.")
    exit(1)

MODEL_NAME = "Llama-3"

# Define the path to the JSON file
json_file_path = os.path.join(directory_path, "data/identity.json")

# Read the JSON data from the file
try:
    with open(json_file_path, "r", encoding="utf-8") as f:
        dataset = json.load(f)
except FileNotFoundError:
    print(f"Error: The file {json_file_path} does not exist.")
    exit(1)

# Replace placeholders in the dataset
for sample in dataset:
    sample["output"] = sample["output"].replace("MODEL_NAME", MODEL_NAME).replace("AUTHOR", "LLaMA Factory")

# Write the updated data back to the file
with open(json_file_path, "w", encoding="utf-8") as f:
    json.dump(dataset, f, indent=2, ensure_ascii=False)