trl/trainer/bco_trainer.py [417:479]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
            )
        elif is_peft_available() and peft_config is not None:
            # if model is a peft model and we have a peft_config, we merge and unload it first
            if isinstance(model, PeftModel):
                model = model.merge_and_unload()

            if getattr(model, "is_loaded_in_8bit", False) or getattr(model, "is_loaded_in_4bit", False):
                _support_gc_kwargs = hasattr(
                    args, "gradient_checkpointing_kwargs"
                ) and "gradient_checkpointing_kwargs" in list(
                    inspect.signature(prepare_model_for_kbit_training).parameters
                )

                prepare_model_kwargs = {"use_gradient_checkpointing": args.gradient_checkpointing}

                if _support_gc_kwargs:
                    prepare_model_kwargs["gradient_checkpointing_kwargs"] = args.gradient_checkpointing_kwargs

                model = prepare_model_for_kbit_training(model, **prepare_model_kwargs)
            elif args.gradient_checkpointing:
                # For backward compatibility with older versions of transformers
                if hasattr(model, "enable_input_require_grads"):
                    model.enable_input_require_grads()
                else:

                    def make_inputs_require_grad(module, input, output):
                        output.requires_grad_(True)

                    model.get_input_embeddings().register_forward_hook(make_inputs_require_grad)

            # get peft model with the given config
            model = get_peft_model(model, peft_config)
            if args.bf16 and getattr(model, "is_loaded_in_4bit", False):
                peft_module_casting_to_bf16(model)
                # If args.bf16 we need to explicitly call `generate` with torch amp autocast context manager
                self._peft_has_been_casted_to_bf16 = True

        # For models that use gradient_checkpointing, we need to attach a hook that enables input
        # to explicitly have `requires_grad=True`, otherwise training will either silently
        # fail or completely fail.
        elif args.gradient_checkpointing:
            # For backward compatibility with older versions of transformers
            if hasattr(model, "enable_input_require_grads"):
                model.enable_input_require_grads()
            else:

                def make_inputs_require_grad(module, input, output):
                    output.requires_grad_(True)

                model.get_input_embeddings().register_forward_hook(make_inputs_require_grad)

        if args.generate_during_eval and not (is_wandb_available() or is_comet_available()):
            raise ValueError(
                "`generate_during_eval=True` requires Weights and Biases or Comet to be installed."
                " Please install `wandb` or `comet-ml` to resolve."
            )

        if model is not None:
            self.is_encoder_decoder = model.config.is_encoder_decoder
        elif args.is_encoder_decoder is None:
            raise ValueError("When no model is provided, you need to pass the parameter is_encoder_decoder.")
        else:
            self.is_encoder_decoder = args.is_encoder_decoder
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -



trl/trainer/cpo_trainer.py [158:220]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
            )
        elif is_peft_available() and peft_config is not None:
            # if model is a peft model and we have a peft_config, we merge and unload it first
            if isinstance(model, PeftModel):
                model = model.merge_and_unload()

            if getattr(model, "is_loaded_in_8bit", False) or getattr(model, "is_loaded_in_4bit", False):
                _support_gc_kwargs = hasattr(
                    args, "gradient_checkpointing_kwargs"
                ) and "gradient_checkpointing_kwargs" in list(
                    inspect.signature(prepare_model_for_kbit_training).parameters
                )

                prepare_model_kwargs = {"use_gradient_checkpointing": args.gradient_checkpointing}

                if _support_gc_kwargs:
                    prepare_model_kwargs["gradient_checkpointing_kwargs"] = args.gradient_checkpointing_kwargs

                model = prepare_model_for_kbit_training(model, **prepare_model_kwargs)
            elif args.gradient_checkpointing:
                # For backward compatibility with older versions of transformers
                if hasattr(model, "enable_input_require_grads"):
                    model.enable_input_require_grads()
                else:

                    def make_inputs_require_grad(module, input, output):
                        output.requires_grad_(True)

                    model.get_input_embeddings().register_forward_hook(make_inputs_require_grad)

            # get peft model with the given config
            model = get_peft_model(model, peft_config)
            if args.bf16 and getattr(model, "is_loaded_in_4bit", False):
                peft_module_casting_to_bf16(model)
                # If args.bf16 we need to explicitly call `generate` with torch amp autocast context manager
                self._peft_has_been_casted_to_bf16 = True

        # For models that use gradient_checkpointing, we need to attach a hook that enables input
        # to explicitly have `requires_grad=True`, otherwise training will either silently
        # fail or completely fail.
        elif args.gradient_checkpointing:
            # For backward compatibility with older versions of transformers
            if hasattr(model, "enable_input_require_grads"):
                model.enable_input_require_grads()
            else:

                def make_inputs_require_grad(module, input, output):
                    output.requires_grad_(True)

                model.get_input_embeddings().register_forward_hook(make_inputs_require_grad)

        if args.generate_during_eval and not (is_wandb_available() or is_comet_available()):
            raise ValueError(
                "`generate_during_eval=True` requires Weights and Biases or Comet to be installed."
                " Please install `wandb` or `comet-ml` to resolve."
            )

        if model is not None:
            self.is_encoder_decoder = model.config.is_encoder_decoder
        elif args.is_encoder_decoder is None:
            raise ValueError("When no model is provided, you need to pass the parameter is_encoder_decoder.")
        else:
            self.is_encoder_decoder = args.is_encoder_decoder
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -