"""Download CLIP BPE merges.txt for ANSSAM3 tokenizer.""" import urllib.request import sys import os URL = "https://huggingface.co/openai/clip-vit-base-patch32/resolve/main/merges.txt" def main(): out_dir = sys.argv[1] if len(sys.argv) > 1 else os.path.dirname(os.path.abspath(__file__)) out_path = os.path.join(out_dir, "merges.txt") print(f"Downloading merges.txt to {out_path} ...") urllib.request.urlretrieve(URL, out_path) print(f"Done ({os.path.getsize(out_path)} bytes)") if __name__ == "__main__": main()