lmflow.pipeline.rm_inferencer
=============================

.. py:module:: lmflow.pipeline.rm_inferencer


Attributes
----------

.. autoapisummary::

   lmflow.pipeline.rm_inferencer.logger


Classes
-------

.. autoapisummary::

   lmflow.pipeline.rm_inferencer.RewardModelInferencer


Module Contents
---------------

.. py:data:: logger

.. py:class:: RewardModelInferencer(model_args: lmflow.args.ModelArguments, data_args: lmflow.args.DatasetArguments, inferencer_args: lmflow.args.InferencerArguments, **kwargs)

   Bases: :py:obj:`lmflow.pipeline.base_pipeline.BasePipeline`


   
   Initializes the `Inferencer` class with given arguments.


   :Parameters:

       **model_args** : ModelArguments object.
           Contains the arguments required to load the model.

       **data_args** : DatasetArguments object.
           Contains the arguments required to load the dataset.

       **inferencer_args** : InferencerArguments object.
           Contains the arguments required to perform inference.














   ..
       !! processed by numpydoc !!

   .. py:attribute:: data_args


   .. py:attribute:: inferencer_args


   .. py:attribute:: model_args


   .. py:attribute:: local_rank


   .. py:attribute:: world_size


   .. py:method:: inference(model: lmflow.models.hf_text_regression_model.HFTextRegressionModel, dataset: lmflow.datasets.dataset.Dataset, transform_dataset_in_place: bool = True, use_vllm: bool = False, enable_distributed_inference: bool = False, **kwargs) -> lmflow.datasets.dataset.Dataset


   .. py:method:: _inference(model: lmflow.models.hf_text_regression_model.HFTextRegressionModel, model_input: Union[lmflow.datasets.dataset.Dataset, ray.data.Dataset], enable_distributed_inference: bool = False, **kwargs)


   .. py:method:: __inference(model: lmflow.models.hf_text_regression_model.HFTextRegressionModel, model_input: lmflow.datasets.dataset.Dataset) -> Union[List[float], List[List[float]]]


   .. py:method:: __distributed_inference(model: lmflow.models.hf_text_regression_model.HFTextRegressionModel, model_input: ray.data.Dataset, num_instances: int, batch_size: int) -> List[lmflow.utils.data_utils.RewardModelInferenceResultWithInput]


   .. py:method:: __vllm_inference(model: lmflow.models.hf_text_regression_model.HFTextRegressionModel, model_input: List[str], enable_distributed_inference: bool = False) -> List[float]
      :abstractmethod:



   .. py:method:: __post_process_model_output(model_output: transformers.modeling_outputs.SequenceClassifierOutputWithPast) -> List[float]


   .. py:method:: flatten_list(list_of_list: List[List]) -> Tuple[List, List[int]]


   .. py:method:: compress_list(list_to_compress: List, sublist_lengths: List[int]) -> List[List]