model/mm_dst/gpt2_dst/scripts/run_generation.py [240:291]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
    )
    parser.add_argument(
        "--path_output",
        type=str,
        default=None,
        help="Path to output predictions in a line separated text file.",
    )
    args = parser.parse_args()

    args.device = torch.device(
        "cuda" if torch.cuda.is_available() and not args.no_cuda else "cpu"
    )
    args.n_gpu = 0 if args.no_cuda else torch.cuda.device_count()

    set_seed(args)

    if args.prompts_from_file and not os.path.exists(args.prompts_from_file):
        raise Exception(f"prompt file '{args.prompts_from_file}' not found")

    # Initialize the model and tokenizer
    try:
        args.model_type = args.model_type.lower()
        model_class, tokenizer_class = MODEL_CLASSES[args.model_type]
    except KeyError:
        raise KeyError(
            "the model {} you specified is not supported. You are welcome to add it and open a PR :)"
        )

    tokenizer = tokenizer_class.from_pretrained(args.model_name_or_path)
    model = model_class.from_pretrained(args.model_name_or_path)
    model.to(args.device)

    args.length = adjust_length_to_model(
        args.length, max_sequence_length=model.config.max_position_embeddings
    )
    logger.info(args)

    results = []
    prompts = []
    if args.prompts_from_file:
        with open(args.prompts_from_file) as handle:
            prompts = handle.readlines()

    while True:
        if not prompts:
            prompts = [args.prompt if args.prompt else input("Model prompt >>> ")]
            if not args.prompt and (
                len(prompts) == 0
                or prompts[0].strip() == ""
                or prompts[0].lower() == "quit"
            ):
                break  # break while True loop
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -



model/mm_dst/gpt2_dst/scripts/run_retrieval.py [213:264]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
    )
    parser.add_argument(
        "--path_output",
        type=str,
        default=None,
        help="Path to output predictions in a line separated text file.",
    )
    args = parser.parse_args()

    args.device = torch.device(
        "cuda" if torch.cuda.is_available() and not args.no_cuda else "cpu"
    )
    args.n_gpu = 0 if args.no_cuda else torch.cuda.device_count()

    set_seed(args)

    if args.prompts_from_file and not os.path.exists(args.prompts_from_file):
        raise Exception(f"prompt file '{args.prompts_from_file}' not found")

    # Initialize the model and tokenizer
    try:
        args.model_type = args.model_type.lower()
        model_class, tokenizer_class = MODEL_CLASSES[args.model_type]
    except KeyError:
        raise KeyError(
            "the model {} you specified is not supported. You are welcome to add it and open a PR :)"
        )

    tokenizer = tokenizer_class.from_pretrained(args.model_name_or_path)
    model = model_class.from_pretrained(args.model_name_or_path)
    model.to(args.device)

    args.length = adjust_length_to_model(
        args.length, max_sequence_length=model.config.max_position_embeddings
    )
    logger.info(args)

    results = []
    prompts = []
    if args.prompts_from_file:
        with open(args.prompts_from_file) as handle:
            prompts = handle.readlines()

    while True:
        if not prompts:
            prompts = [args.prompt if args.prompt else input("Model prompt >>> ")]
            if not args.prompt and (
                len(prompts) == 0
                or prompts[0].strip() == ""
                or prompts[0].lower() == "quit"
            ):
                break  # break while True loop
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -