model/mm_dst/gpt2_dst/scripts/run_generation.py [296:315]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
            prompt_text = prompt_text.strip("\n")

            # Different models need different input formatting and/or extra arguments
            requires_preprocessing = args.model_type in PREPROCESSING_FUNCTIONS.keys()
            if requires_preprocessing:
                prepare_input = PREPROCESSING_FUNCTIONS.get(args.model_type)
                preprocessed_prompt_text = prepare_input(
                    args, model, tokenizer, prompt_text
                )
                encoded_prompt = tokenizer.encode(
                    preprocessed_prompt_text,
                    add_special_tokens=True,
                    return_tensors="pt",
                    add_space_before_punct_symbol=True,
                )
            else:
                encoded_prompt = tokenizer.encode(
                    prompt_text, add_special_tokens=True, return_tensors="pt"
                )
            encoded_prompt = encoded_prompt.to(args.device)
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -



model/mm_dst/gpt2_dst/scripts/run_retrieval.py [270:289]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
                prompt_text = prompt_text.strip("\n")

                # Different models need different input formatting and/or extra arguments
                requires_preprocessing = args.model_type in PREPROCESSING_FUNCTIONS.keys()
                if requires_preprocessing:
                    prepare_input = PREPROCESSING_FUNCTIONS.get(args.model_type)
                    preprocessed_prompt_text = prepare_input(
                        args, model, tokenizer, prompt_text
                    )
                    encoded_prompt = tokenizer.encode(
                        preprocessed_prompt_text,
                        add_special_tokens=True,
                        return_tensors="pt",
                        add_space_before_punct_symbol=True,
                    )
                else:
                    encoded_prompt = tokenizer.encode(
                        prompt_text, add_special_tokens=True, return_tensors="pt"
                    )
                encoded_prompt = encoded_prompt.to(args.device)
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -