def prepare_xlm_input()

in model/mm_dst/gpt2_dst/scripts/run_retrieval.py [0:0]

• 16 lines of code
• 8 McCabe index (conditional complexity)

def prepare_xlm_input(args, model, tokenizer, prompt_text):
    # kwargs = {"language": None, "mask_token_id": None}

    # Set the language
    use_lang_emb = hasattr(model.config, "use_lang_emb") and model.config.use_lang_emb
    if hasattr(model.config, "lang2id") and use_lang_emb:
        available_languages = model.config.lang2id.keys()
        if args.xlm_language in available_languages:
            language = args.xlm_language
        else:
            language = None
            while language not in available_languages:
                language = input(
                    "Using XLM. Select language in "
                    + str(list(available_languages))
                    + " >>> "
                )

        model.config.lang_id = model.config.lang2id[language]
        # kwargs["language"] = tokenizer.lang2id[language]

    # TODO fix mask_token_id setup when configurations will be synchronized between models and tokenizers
    # XLM masked-language modeling (MLM) models need masked token
    # is_xlm_mlm = "mlm" in args.model_name_or_path
    # if is_xlm_mlm:
    #     kwargs["mask_token_id"] = tokenizer.mask_token_id

    return prompt_text