:py:mod:`neural_compressor.adaptor.torch_utils.layer_wise_quant.utils`
======================================================================

.. py:module:: neural_compressor.adaptor.torch_utils.layer_wise_quant.utils

.. autoapi-nested-parse::

   Utils for layer wise quantization.



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


Functions
~~~~~~~~~

.. autoapisummary::

   neural_compressor.adaptor.torch_utils.layer_wise_quant.utils.get_module
   neural_compressor.adaptor.torch_utils.layer_wise_quant.utils.get_children
   neural_compressor.adaptor.torch_utils.layer_wise_quant.utils.get_named_children
   neural_compressor.adaptor.torch_utils.layer_wise_quant.utils.dowload_hf_model
   neural_compressor.adaptor.torch_utils.layer_wise_quant.utils.load_empty_model
   neural_compressor.adaptor.torch_utils.layer_wise_quant.utils.get_super_module_by_name
   neural_compressor.adaptor.torch_utils.layer_wise_quant.utils.update_module
   neural_compressor.adaptor.torch_utils.layer_wise_quant.utils.load_layer_wise_quantized_model
   neural_compressor.adaptor.torch_utils.layer_wise_quant.utils.load_tensor_from_shard
   neural_compressor.adaptor.torch_utils.layer_wise_quant.utils.load_tensor



.. py:function:: get_module(model, key)

   Get module from model by key name.

   :param model: original model
   :type model: torch.nn.Module
   :param key: module name to be replaced
   :type key: str


.. py:function:: get_children(model)

   Get all the children of given model.


.. py:function:: get_named_children(model, pre=[])

   Get all the name and children of given model.


.. py:function:: dowload_hf_model(repo_id, cache_dir=None, repo_type=None, revision=None)

   Download hugging face model from hf hub.


.. py:function:: load_empty_model(pretrained_model_name_or_path, cls=AutoModelForCausalLM, **kwargs)

   Load a empty model.


.. py:function:: get_super_module_by_name(model, module_name)

   Get the father module with given name of child module.


.. py:function:: update_module(model, module_name, new_module)

   Update module.


.. py:function:: load_layer_wise_quantized_model(path)

   Load layer wise quantized model.


.. py:function:: load_tensor_from_shard(pretrained_model_name_or_path, tensor_name, prefix=None)

   Load tensor from shard.


.. py:function:: load_tensor(path, tensor_name=None, prefix=None)

   Load a tensor from bin file with given tensor name.