medcat.components.addons.relation_extraction.llama.model

Attributes

logger

Classes

`ConfigRelCAT`	The RelCAT part of the config
`RelExtrLlamaConfig`	Class for LlamaConfig
`RelExtrBaseModel`	Base class for the RelCAT models
`RelExtrLlamaModel`	LlamaModel class for RelCAT
`LlamaPooler`	An attempt to copy the BERT pooling technique for an increase in

Functions

`create_dense_layers`(relcat_config)
`get_annotation_schema_tag`(sequence_output, input_ids, ...)	Gets to token sequences from the sequence_ouput for the specific token

Module Contents

class medcat.components.addons.relation_extraction.llama.model.ConfigRelCAT(/, **data)

Bases: medcat.config.config.ComponentConfig

The RelCAT part of the config

Parameters:: data (Any)

general: General

model: Model

train: Train

class Config

extra = 'allow'

validate_assignment = True

classmethod load(load_path='./')

Load the config from a file.

Parameters:: load_path (str) – Path to RelCAT config. Defaults to “./”.
Returns:: ConfigRelCAT – The loaded config.
Return type:: ConfigRelCAT

comp_name: str = 'default'

The name of the component.

If a custom implementation is required, it needs to be registered using `medcat.components.types.register_core_component(

<core component type>, <component name>, <implementing class>)

By default, only the ‘default’ component is registered.

_is_dirty: bool = False

__setattr__(name, value)

Parameters:

name (str)
value (Any)

property is_dirty: bool

Return type:: bool

mark_clean()

get_strategy()

Return type:: medcat.storage.serialisables.SerialisingStrategy

classmethod get_init_attrs()

Return type:: list[str]

classmethod ignore_attrs()

Return type:: list[str]

classmethod include_properties()

Return type:: list[str]

merge_config(other)

Merge this config with another config’s (partial) model dump.

The exepctation is that the other dict is a partial model dump. Values specified there are overwritten into the current config. Values not specified there are left intact.

The other config can have keys/values that do not exist in the config or sub-config. And they will be added where possible.

Parameters:: other (dict) – The model dump
Raises:: IncorrectConfigValues – If unable to set the attribute, trying to set incorrect value, or trying to set sub-config values in an incorrect format (non-dict).

model_config: ClassVar[pydantic.config.ConfigDict]: Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].

model_fields: ClassVar[Dict[str, pydantic.fields.FieldInfo]]

Metadata about the fields defined on the model, mapping of field names to [FieldInfo][pydantic.fields.FieldInfo] objects.

This replaces Model.__fields__ from Pydantic V1.

model_computed_fields: ClassVar[Dict[str, pydantic.fields.ComputedFieldInfo]]: A dictionary of computed field names and their corresponding ComputedFieldInfo objects.

__class_vars__: ClassVar[set[str]]: The names of the class variables defined on the model.

__private_attributes__: ClassVar[Dict[str, pydantic.fields.ModelPrivateAttr]]: Metadata about the private attributes of the model.

__signature__: ClassVar[inspect.Signature]: The synthesized __init__ [Signature][inspect.Signature] of the model.

__pydantic_complete__: ClassVar[bool] = False: Whether model building is completed, or if there are still undefined fields.

__pydantic_core_schema__: ClassVar[pydantic_core.CoreSchema]: The core schema of the model.

__pydantic_custom_init__: ClassVar[bool]: Whether the model has a custom __init__ method.

__pydantic_decorators__: ClassVar[pydantic._internal._decorators.DecoratorInfos]: Metadata containing the decorators defined on the model. This replaces Model.__validators__ and Model.__root_validators__ from Pydantic V1.

__pydantic_generic_metadata__: ClassVar[pydantic._internal._generics.PydanticGenericMetadata]: Metadata for generic models; contains data used for a similar purpose to __args__, __origin__, __parameters__ in typing-module generics. May eventually be replaced by these.

__pydantic_parent_namespace__: ClassVar[Dict[str, Any] | None] = None: Parent namespace of the model, used for automatic rebuilding of models.

__pydantic_post_init__: ClassVar[None | Literal['model_post_init']]: The name of the post-init method for the model, if defined.

__pydantic_root_model__: ClassVar[bool] = False: Whether the model is a [RootModel][pydantic.root_model.RootModel].

__pydantic_serializer__: ClassVar[pydantic_core.SchemaSerializer]: The pydantic-core SchemaSerializer used to dump instances of the model.

__pydantic_validator__: ClassVar[pydantic_core.SchemaValidator | pydantic.plugin._schema_validator.PluggableSchemaValidator]: The pydantic-core SchemaValidator used to validate instances of the model.

__pydantic_extra__: dict[str, Any] | None: A dictionary containing extra values, if [extra][pydantic.config.ConfigDict.extra] is set to ‘allow’.

__pydantic_fields_set__: set[str]: The names of fields explicitly set during instantiation.

__pydantic_private__: dict[str, Any] | None: Values of private attributes set on the model instance.

__slots__ = ('__dict__', '__pydantic_fields_set__', '__pydantic_extra__', '__pydantic_private__')

__init__(/, **data)

Create a new model by parsing and validating input data from keyword arguments.

Raises [ValidationError][pydantic_core.ValidationError] if the input data cannot be validated to form a valid model.

self is explicitly positional-only to allow self as a field name.

Parameters:: data (Any)
Return type:: None

property model_extra: dict[str, Any] | None

Get extra fields set during validation.

Returns:: A dictionary of extra fields, or `None` if `config.extra` is not set to `”allow”`.
Return type:: dict[str, Any] | None

property model_fields_set: set[str]

Returns the set of fields that have been explicitly set on this model instance.

Returns:: A set of strings representing the fields that have been set, – i.e. that were not filled from defaults.
Return type:: set[str]

classmethod model_construct(_fields_set=None, **values)

Creates a new instance of the Model class with validated data.

Creates a new model setting __dict__ and __pydantic_fields_set__ from trusted or pre-validated data. Default values are respected, but no other validation is performed.

!!! note: model_construct() generally respects the model_config.extra setting on the provided model. That is, if model_config.extra == ‘allow’, then all extra passed values are added to the model instance’s __dict__ and __pydantic_extra__ fields. If model_config.extra == ‘ignore’ (the default), then all extra passed values are ignored. Because no validation is performed with a call to model_construct(), having model_config.extra == ‘forbid’ does not result in an error if extra values are passed, but they will be ignored.

Parameters:

_fields_set (set[str] | None) – A set of field names that were originally explicitly set during instantiation. If provided, this is directly used for the [model_fields_set][pydantic.BaseModel.model_fields_set] attribute. Otherwise, the field names from the values argument will be used.
values (Any) – Trusted or pre-validated data dictionary.

Returns:

A new instance of the `Model` class with validated data.

Return type:

typing_extensions.Self

model_copy(*, update=None, deep=False)

Usage docs: https://docs.pydantic.dev/2.9/concepts/serialization/#model_copy

Returns a copy of the model.

Parameters:

update (dict[str, Any] | None) – Values to change/add in the new model. Note: the data is not validated before creating the new model. You should trust this data.
deep (bool) – Set to True to make a deep copy of the model.

Returns:

New model instance.

Return type:

typing_extensions.Self

model_dump(*, mode='python', include=None, exclude=None, context=None, by_alias=False, exclude_unset=False, exclude_defaults=False, exclude_none=False, round_trip=False, warnings=True, serialize_as_any=False)

Usage docs: https://docs.pydantic.dev/2.9/concepts/serialization/#modelmodel_dump

Generate a dictionary representation of the model, optionally specifying which fields to include or exclude.

Parameters:

mode (Literal['json', 'python'] | str) – The mode in which to_python should run. If mode is ‘json’, the output will only contain JSON serializable types. If mode is ‘python’, the output may contain non-JSON-serializable Python objects.
include (IncEx | None) – A set of fields to include in the output.
exclude (IncEx | None) – A set of fields to exclude from the output.
context (Any | None) – Additional context to pass to the serializer.
by_alias (bool) – Whether to use the field’s alias in the dictionary key if defined.
exclude_unset (bool) – Whether to exclude fields that have not been explicitly set.
exclude_defaults (bool) – Whether to exclude fields that are set to their default value.
exclude_none (bool) – Whether to exclude fields that have a value of None.
round_trip (bool) – If True, dumped values should be valid as input for non-idempotent types such as Json[T].
warnings (bool | Literal['none', 'warn', 'error']) – How to handle serialization errors. False/”none” ignores them, True/”warn” logs errors, “error” raises a [PydanticSerializationError][pydantic_core.PydanticSerializationError].
serialize_as_any (bool) – Whether to serialize fields with duck-typing serialization behavior.

Returns:

A dictionary representation of the model.

Return type:

dict[str, Any]

model_dump_json(*, indent=None, include=None, exclude=None, context=None, by_alias=False, exclude_unset=False, exclude_defaults=False, exclude_none=False, round_trip=False, warnings=True, serialize_as_any=False)

Usage docs: https://docs.pydantic.dev/2.9/concepts/serialization/#modelmodel_dump_json

Generates a JSON representation of the model using Pydantic’s to_json method.

Parameters:

indent (int | None) – Indentation to use in the JSON output. If None is passed, the output will be compact.
include (IncEx | None) – Field(s) to include in the JSON output.
exclude (IncEx | None) – Field(s) to exclude from the JSON output.
context (Any | None) – Additional context to pass to the serializer.
by_alias (bool) – Whether to serialize using field aliases.
exclude_unset (bool) – Whether to exclude fields that have not been explicitly set.
exclude_defaults (bool) – Whether to exclude fields that are set to their default value.
exclude_none (bool) – Whether to exclude fields that have a value of None.
round_trip (bool) – If True, dumped values should be valid as input for non-idempotent types such as Json[T].
warnings (bool | Literal['none', 'warn', 'error']) – How to handle serialization errors. False/”none” ignores them, True/”warn” logs errors, “error” raises a [PydanticSerializationError][pydantic_core.PydanticSerializationError].
serialize_as_any (bool) – Whether to serialize fields with duck-typing serialization behavior.

Returns:

A JSON string representation of the model.

Return type:

str

classmethod model_json_schema(by_alias=True, ref_template=DEFAULT_REF_TEMPLATE, schema_generator=GenerateJsonSchema, mode='validation')

Generates a JSON schema for a model class.

Parameters:

by_alias (bool) – Whether to use attribute aliases or not.
ref_template (str) – The reference template.
schema_generator (type[pydantic.json_schema.GenerateJsonSchema]) – To override the logic used to generate the JSON schema, as a subclass of GenerateJsonSchema with your desired modifications
mode (pydantic.json_schema.JsonSchemaMode) – The mode in which to generate the schema.

Returns:

The JSON schema for the given model class.

Return type:

dict[str, Any]

classmethod model_parametrized_name(params)

Compute the class name for parametrizations of generic classes.

This method can be overridden to achieve a custom naming scheme for generic BaseModels.

Parameters:: params (tuple[type[Any], Ellipsis]) – Tuple of types of the class. Given a generic class Model with 2 type variables and a concrete model Model[str, int], the value (str, int) would be passed to params.
Returns:: String representing the new class where `params` are passed to `cls` as type variables.
Raises:: TypeError – Raised when trying to generate concrete names for non-generic models.
Return type:: str

model_post_init(__context)

Override this method to perform additional initialization after __init__ and model_construct. This is useful if you want to do some validation that requires the entire model to be initialized.

Parameters:: __context (Any)
Return type:: None

classmethod model_rebuild(*, force=False, raise_errors=True, _parent_namespace_depth=2, _types_namespace=None)

Try to rebuild the pydantic-core schema for the model.

This may be necessary when one of the annotations is a ForwardRef which could not be resolved during the initial attempt to build the schema, and automatic rebuilding fails.

Parameters:

force (bool) – Whether to force the rebuilding of the model schema, defaults to False.
raise_errors (bool) – Whether to raise errors, defaults to True.
_parent_namespace_depth (int) – The depth level of the parent namespace, defaults to 2.
_types_namespace (dict[str, Any] | None) – The types namespace, defaults to None.

Returns:

Returns `None` if the schema is already “complete” and rebuilding was not required.
If rebuilding _was_ required, returns `True` if rebuilding was successful, otherwise `False`.

Return type:

bool | None

classmethod model_validate(obj, *, strict=None, from_attributes=None, context=None)

Validate a pydantic model instance.

Parameters:

obj (Any) – The object to validate.
strict (bool | None) – Whether to enforce types strictly.
from_attributes (bool | None) – Whether to extract data from object attributes.
context (Any | None) – Additional context to pass to the validator.

Raises:

ValidationError – If the object could not be validated.

Returns:

The validated model instance.

Return type:

typing_extensions.Self

classmethod model_validate_json(json_data, *, strict=None, context=None)

Usage docs: https://docs.pydantic.dev/2.9/concepts/json/#json-parsing

Validate the given JSON data against the Pydantic model.

Parameters:

json_data (str | bytes | bytearray) – The JSON data to validate.
strict (bool | None) – Whether to enforce types strictly.
context (Any | None) – Extra variables to pass to the validator.

Returns:

The validated Pydantic model.

Raises:

ValidationError – If json_data is not a JSON string or the object could not be validated.

Return type:

typing_extensions.Self

classmethod model_validate_strings(obj, *, strict=None, context=None)

Validate the given object with string data against the Pydantic model.

Parameters:

obj (Any) – The object containing string data to validate.
strict (bool | None) – Whether to enforce types strictly.
context (Any | None) – Extra variables to pass to the validator.

Returns:

The validated Pydantic model.

Return type:

typing_extensions.Self

classmethod __get_pydantic_core_schema__(source, handler, /)

Hook into generating the model’s CoreSchema.

Parameters:

source (type[BaseModel]) – The class we are generating a schema for. This will generally be the same as the cls argument if this is a classmethod.
handler (pydantic.annotated_handlers.GetCoreSchemaHandler) – A callable that calls into Pydantic’s internal CoreSchema generation logic.

Returns:

A `pydantic-core` `CoreSchema`.

Return type:

pydantic_core.CoreSchema

classmethod __get_pydantic_json_schema__(core_schema, handler, /)

Hook into generating the model’s JSON schema.

Parameters:

core_schema (pydantic_core.CoreSchema) – A pydantic-core CoreSchema. You can ignore this argument and call the handler with a new CoreSchema, wrap this CoreSchema ({‘type’: ‘nullable’, ‘schema’: current_schema}), or just call the handler with the original schema.
handler (pydantic.annotated_handlers.GetJsonSchemaHandler) – Call into Pydantic’s internal JSON schema generation. This will raise a pydantic.errors.PydanticInvalidForJsonSchema if JSON schema generation fails. Since this gets called by BaseModel.model_json_schema you can override the schema_generator argument to that function to change JSON schema generation globally for a type.

Returns:

A JSON schema, as a Python object.

Return type:

pydantic.json_schema.JsonSchemaValue

classmethod __pydantic_init_subclass__(**kwargs)

This is intended to behave just like __init_subclass__, but is called by ModelMetaclass only after the class is actually fully initialized. In particular, attributes like model_fields will be present when this is called.

This is necessary because __init_subclass__ will always be called by type.__new__, and it would require a prohibitively large refactor to the ModelMetaclass to ensure that type.__new__ was called in such a manner that the class would already be sufficiently initialized.

This will receive the same kwargs that would be passed to the standard __init_subclass__, namely, any kwargs passed to the class definition that aren’t used internally by pydantic.

Parameters:: **kwargs (Any) – Any keyword arguments passed to the class definition that aren’t used internally by pydantic.
Return type:: None

classmethod __class_getitem__(typevar_values)

Parameters:: typevar_values (type[Any] | tuple[type[Any], Ellipsis])
Return type:: type[BaseModel] | pydantic._internal._forward_ref.PydanticRecursiveRef

__copy__()

Returns a shallow copy of the model.

Return type:: typing_extensions.Self

__deepcopy__(memo=None)

Returns a deep copy of the model.

Parameters:: memo (dict[int, Any] | None)
Return type:: typing_extensions.Self

__getattr__(item)

Parameters:: item (str)
Return type:: Any

_check_frozen(name, value)

Parameters:

name (str)
value (Any)

Return type:

None

__getstate__()

Return type:: dict[Any, Any]

__setstate__(state)

Parameters:: state (dict[Any, Any])
Return type:: None

__eq__(other)

Parameters:: other (Any)
Return type:: bool

classmethod __init_subclass__(**kwargs)

This signature is included purely to help type-checkers check arguments to class declaration, which provides a way to conveniently set model_config key/value pairs.

```py from pydantic import BaseModel

class MyModel(BaseModel, extra=’allow’): … ```

However, this may be deceiving, since the _actual_ calls to __init_subclass__ will not receive any of the config arguments, and will only receive any keyword arguments passed during class initialization that are _not_ expected keys in ConfigDict. (This is due to the way ModelMetaclass.__new__ works.)

Parameters:: **kwargs (typing_extensions.Unpack[pydantic.config.ConfigDict]) – Keyword arguments passed to the class definition, which set model_config

Note

You may want to override __pydantic_init_subclass__ instead, which behaves similarly but is called after the class is fully initialized.

__iter__()

So dict(model) works.

Return type:: TupleGenerator

__repr__()

Return type:: str

__repr_args__()

Return type:: pydantic._internal._repr.ReprArgs

__repr_name__

__repr_str__

__pretty__

__rich_repr__

__str__()

Return type:: str

property __fields__: dict[str, pydantic.fields.FieldInfo]

Return type:: dict[str, pydantic.fields.FieldInfo]

property __fields_set__: set[str]

Return type:: set[str]

dict(*, include=None, exclude=None, by_alias=False, exclude_unset=False, exclude_defaults=False, exclude_none=False)

Parameters:

include (IncEx | None)
exclude (IncEx | None)
by_alias (bool)
exclude_unset (bool)
exclude_defaults (bool)
exclude_none (bool)

Return type:

Dict[str, Any]

json(*, include=None, exclude=None, by_alias=False, exclude_unset=False, exclude_defaults=False, exclude_none=False, encoder=PydanticUndefined, models_as_dict=PydanticUndefined, **dumps_kwargs)

Parameters:

include (IncEx | None)
exclude (IncEx | None)
by_alias (bool)
exclude_unset (bool)
exclude_defaults (bool)
exclude_none (bool)
encoder (Callable[[Any], Any] | None)
models_as_dict (bool)
dumps_kwargs (Any)

Return type:

str

classmethod parse_obj(obj)

Parameters:: obj (Any)
Return type:: typing_extensions.Self

classmethod parse_raw(b, *, content_type=None, encoding='utf8', proto=None, allow_pickle=False)

Parameters:

b (str | bytes)
content_type (str | None)
encoding (str)
proto (pydantic.deprecated.parse.Protocol | None)
allow_pickle (bool)

Return type:

typing_extensions.Self

classmethod parse_file(path, *, content_type=None, encoding='utf8', proto=None, allow_pickle=False)

Parameters:

path (str | pathlib.Path)
content_type (str | None)
encoding (str)
proto (pydantic.deprecated.parse.Protocol | None)
allow_pickle (bool)

Return type:

typing_extensions.Self

classmethod from_orm(obj)

Parameters:: obj (Any)
Return type:: typing_extensions.Self

classmethod construct(_fields_set=None, **values)

Parameters:

_fields_set (set[str] | None)
values (Any)

Return type:

typing_extensions.Self

copy(*, include=None, exclude=None, update=None, deep=False)

Returns a copy of the model.

!!! warning “Deprecated”: This method is now deprecated; use model_copy instead.

If you need include or exclude, use:

`py data = self.model_dump(include=include, exclude=exclude, round_trip=True) data = {**data, **(update or {})} copied = self.model_validate(data) `

Parameters:

include (pydantic._internal._utils.AbstractSetIntStr | pydantic._internal._utils.MappingIntStrAny | None) – Optional set or mapping specifying which fields to include in the copied model.
exclude (pydantic._internal._utils.AbstractSetIntStr | pydantic._internal._utils.MappingIntStrAny | None) – Optional set or mapping specifying which fields to exclude in the copied model.
update (Dict[str, Any] | None) – Optional dictionary of field-value pairs to override field values in the copied model.
deep (bool) – If True, the values of fields that are Pydantic models will be deep-copied.

Returns:

A copy of the model with included, excluded and updated fields as specified.

Return type:

typing_extensions.Self

classmethod schema(by_alias=True, ref_template=DEFAULT_REF_TEMPLATE)

Parameters:

by_alias (bool)
ref_template (str)

Return type:

Dict[str, Any]

classmethod schema_json(*, by_alias=True, ref_template=DEFAULT_REF_TEMPLATE, **dumps_kwargs)

Parameters:

by_alias (bool)
ref_template (str)
dumps_kwargs (Any)

Return type:

str

classmethod validate(value)

Parameters:: value (Any)
Return type:: typing_extensions.Self

classmethod update_forward_refs(**localns)

Parameters:: localns (Any)
Return type:: None

_iter(*args, **kwargs)

Parameters:

args (Any)
kwargs (Any)

Return type:

Any

_copy_and_set_values(*args, **kwargs)

Parameters:

args (Any)
kwargs (Any)

Return type:

Any

classmethod _get_value(*args, **kwargs)

Parameters:

args (Any)
kwargs (Any)

Return type:

Any

_calculate_keys(*args, **kwargs)

Parameters:

args (Any)
kwargs (Any)

Return type:

Any

class medcat.components.addons.relation_extraction.llama.model.RelExtrLlamaConfig(pretrained_model_name_or_path, **kwargs)

Bases: medcat.components.addons.relation_extraction.config.RelExtrBaseConfig

Class for LlamaConfig

name = 'llama-config'

pretrained_model_name_or_path = 'meta-llama/Llama-3.1-8B'

hf_model_config: transformers.LlamaConfig

classmethod load(pretrained_model_name_or_path, relcat_config, **kwargs)

Parameters:

pretrained_model_name_or_path (str)
relcat_config (medcat.config.config_rel_cat.ConfigRelCAT)

Return type:

RelExtrLlamaConfig

__init__(pretrained_model_name_or_path, **kwargs)

model_type = 'relcat'

to_dict()

Serializes this instance to a Python dictionary.

Returns:: `Dict[str, Any]` – Dictionary of all the attributes that make up this configuration instance.

save(save_path)

Parameters:: save_path (str)

base_config_key: str = ''

sub_configs: Dict[str, PretrainedConfig]

is_composition: bool = False

attribute_map: Dict[str, str]

base_model_tp_plan: Dict[str, Any] | None = None

_auto_class: str | None = None

__setattr__(key, value)

__getattribute__(key)

return_dict

output_hidden_states

output_attentions

torchscript

torch_dtype

use_bfloat16

tf_legacy_loss

pruned_heads

tie_word_embeddings

chunk_size_feed_forward

is_encoder_decoder

is_decoder

cross_attention_hidden_size

add_cross_attention

tie_encoder_decoder

architectures

finetuning_task

id2label

label2id

tokenizer_class

prefix

bos_token_id

pad_token_id

eos_token_id

sep_token_id

decoder_start_token_id

task_specific_params

problem_type

_name_or_path = ''

_commit_hash

_attn_implementation_internal

_attn_implementation_autoset = False

transformers_version

property name_or_path: str

Return type:: str

property use_return_dict: bool

Whether or not return [~utils.ModelOutput] instead of tuples.

Type:: bool
Return type:: bool

property num_labels: int

The number of labels for classification models.

Type:: int
Return type:: int

property _attn_implementation

save_pretrained(save_directory, push_to_hub=False, **kwargs)

Save a configuration object to the directory save_directory, so that it can be re-loaded using the [~PretrainedConfig.from_pretrained] class method.

Parameters:

save_directory (str or os.PathLike) – Directory where the configuration JSON file will be saved (will be created if it does not exist).
push_to_hub (bool, optional, defaults to False) – Whether or not to push your model to the Hugging Face model hub after saving it. You can specify the repository you want to push to with repo_id (will default to the name of save_directory in your namespace).
kwargs (Dict[str, Any], optional) – Additional key word arguments passed along to the [~utils.PushToHubMixin.push_to_hub] method.

static _set_token_in_kwargs(kwargs, token=None)

Temporary method to deal with token and use_auth_token.

This method is to avoid apply the same changes in all model config classes that overwrite from_pretrained.

Need to clean up use_auth_token in a follow PR.

classmethod from_pretrained(pretrained_model_name_or_path, cache_dir=None, force_download=False, local_files_only=False, token=None, revision='main', **kwargs)

Instantiate a [PretrainedConfig] (or a derived class) from a pretrained model configuration.

Parameters:

pretrained_model_name_or_path (str or os.PathLike) –
This can be either:
- a string, the model id of a pretrained model configuration hosted inside a model repo on huggingface.co.
- a path to a directory containing a configuration file saved using the [~PretrainedConfig.save_pretrained] method, e.g., ./my_model_directory/.
- a path or url to a saved configuration JSON file, e.g., ./my_model_directory/configuration.json.
cache_dir (str or os.PathLike, optional) – Path to a directory in which a downloaded pretrained model configuration should be cached if the standard cache should not be used.
force_download (bool, optional, defaults to False) – Whether or not to force to (re-)download the configuration files and override the cached versions if they exist.
resume_download – Deprecated and ignored. All downloads are now resumed by default when possible. Will be removed in v5 of Transformers.
proxies (Dict[str, str], optional) – A dictionary of proxy servers to use by protocol or endpoint, e.g., {‘http’: ‘foo.bar:3128’, ‘http://hostname’: ‘foo.bar:4012’}. The proxies are used on each request.
token (str or bool, optional) – The token to use as HTTP bearer authorization for remote files. If True, or not specified, will use the token generated when running huggingface-cli login (stored in ~/.huggingface).
revision (str, optional, defaults to “main”) –
The specific model version to use. It can be a branch name, a tag name, or a commit id, since we use a git-based system for storing models and other artifacts on huggingface.co, so revision can be any identifier allowed by git.

<Tip>

To test a pull request you made on the Hub, you can pass revision=”refs/pr/<pr_number>”.

</Tip>
return_unused_kwargs (bool, optional, defaults to False) –
If False, then this function returns just the final configuration object.

If True, then this functions returns a Tuple(config, unused_kwargs) where unused_kwargs is a dictionary consisting of the key/value pairs whose keys are not configuration attributes: i.e., the part of kwargs which has not been used to update config and is otherwise ignored.
subfolder (str, optional, defaults to “”) – In case the relevant files are located inside a subfolder of the model repo on huggingface.co, you can specify the folder name here.
kwargs (Dict[str, Any], optional) – The values in kwargs of any keys which are configuration attributes will be used to override the loaded values. Behavior concerning key/value pairs whose keys are not configuration attributes is controlled by the return_unused_kwargs keyword parameter.
local_files_only (bool)

Returns:

[`PretrainedConfig`] – The configuration object instantiated from this pretrained model.

Return type:

PretrainedConfig

Examples:

```python # We can’t instantiate directly the base class PretrainedConfig so let’s show the examples on a # derived class: BertConfig config = BertConfig.from_pretrained(

“google-bert/bert-base-uncased”

) # Download configuration from huggingface.co and cache. config = BertConfig.from_pretrained(

“./test/saved_model/”

) # E.g. config (or model) was saved using save_pretrained(‘./test/saved_model/’) config = BertConfig.from_pretrained(“./test/saved_model/my_configuration.json”) config = BertConfig.from_pretrained(“google-bert/bert-base-uncased”, output_attentions=True, foo=False) assert config.output_attentions == True config, unused_kwargs = BertConfig.from_pretrained(

“google-bert/bert-base-uncased”, output_attentions=True, foo=False, return_unused_kwargs=True

) assert config.output_attentions == True assert unused_kwargs == {“foo”: False} ```

classmethod get_config_dict(pretrained_model_name_or_path, **kwargs)

From a pretrained_model_name_or_path, resolve to a dictionary of parameters, to be used for instantiating a [PretrainedConfig] using from_dict.

Parameters:: pretrained_model_name_or_path (str or os.PathLike) – The identifier of the pre-trained checkpoint from which we want the dictionary of parameters.
Returns:: `Tuple[Dict, Dict]` – The dictionary(ies) that will be used to instantiate the configuration object.
Return type:: Tuple[Dict[str, Any], Dict[str, Any]]

classmethod _get_config_dict(pretrained_model_name_or_path, **kwargs)

Parameters:: pretrained_model_name_or_path (Union[str, os.PathLike])
Return type:: Tuple[Dict[str, Any], Dict[str, Any]]

classmethod from_dict(config_dict, **kwargs)

Instantiates a [PretrainedConfig] from a Python dictionary of parameters.

Parameters:

config_dict (Dict[str, Any]) – Dictionary that will be used to instantiate the configuration object. Such a dictionary can be retrieved from a pretrained checkpoint by leveraging the [~PretrainedConfig.get_config_dict] method.
kwargs (Dict[str, Any]) – Additional parameters from which to initialize the configuration object.

Returns:

[`PretrainedConfig`] – The configuration object instantiated from those parameters.

Return type:

PretrainedConfig

classmethod from_json_file(json_file)

Instantiates a [PretrainedConfig] from the path to a JSON file of parameters.

Parameters:: json_file (str or os.PathLike) – Path to the JSON file containing the parameters.
Returns:: [`PretrainedConfig`] – The configuration object instantiated from that JSON file.
Return type:: PretrainedConfig

classmethod _dict_from_json_file(json_file)

Parameters:: json_file (Union[str, os.PathLike])

__eq__(other)

__repr__()

__iter__()

to_diff_dict()

Removes all attributes from config which correspond to the default config attributes for better readability and serializes to a Python dictionary.

Returns:: `Dict[str, Any]` – Dictionary of all the attributes that make up this configuration instance,
Return type:: Dict[str, Any]

to_json_string(use_diff=True)

Serializes this instance to a JSON string.

Parameters:: use_diff (bool, optional, defaults to True) – If set to True, only the difference between the config instance and the default PretrainedConfig() is serialized to JSON string.
Returns:: `str` – String containing all the attributes that make up this configuration instance in JSON format.
Return type:: str

to_json_file(json_file_path, use_diff=True)

Save this instance to a JSON file.

Parameters:

json_file_path (str or os.PathLike) – Path to the JSON file in which this configuration instance’s parameters will be saved.
use_diff (bool, optional, defaults to True) – If set to True, only the difference between the config instance and the default PretrainedConfig() is serialized to JSON file.

update(config_dict)

Updates attributes of this class with attributes from config_dict.

Parameters:: config_dict (Dict[str, Any]) – Dictionary of attributes that should be updated for this class.

update_from_string(update_str)

Updates attributes of this class with attributes from update_str.

The expected format is ints, floats and strings as is, and for booleans use true or false. For example: “n_embd=10,resid_pdrop=0.2,scale_attn_weights=false,summary_type=cls_index”

The keys to change have to already exist in the config object.

Parameters:: update_str (str) – String with attributes that should be updated for this class.

dict_torch_dtype_to_str(d)

Checks whether the passed dictionary and its nested dicts have a torch_dtype key and if it’s not None, converts torch.dtype to a string of just the type. For example, torch.float32 get converted into “float32” string, which can then be stored in the json format.

Parameters:: d (Dict[str, Any])
Return type:: None

classmethod register_for_auto_class(auto_class='AutoConfig')

Register this class with a given auto class. This should only be used for custom configurations as the ones in the library are already mapped with AutoConfig.

This API is experimental and may have some slight breaking changes in the next releases.

</Tip>

Parameters:: auto_class (str or type, optional, defaults to “AutoConfig”) – The auto class to register this new configuration with.

static _get_global_generation_defaults()

Return type:: Dict[str, Any]

_get_non_default_generation_parameters()

Gets the non-default generation parameters on the PretrainedConfig instance

Return type:: Dict[str, Any]

get_text_config(decoder=False)

Returns the config that is meant to be used with text IO. On most models, it is the original config instance itself. On specific composite models, it is under a set of valid names.

If decoder is set to True, then only search for decoder config names.

Return type:: PretrainedConfig

_create_repo(repo_id, private=None, token=None, repo_url=None, organization=None)

Create the repo if needed, cleans up repo_id with deprecated kwargs repo_url and organization, retrieves the token.

Parameters:

repo_id (str)
private (Optional[bool])
token (Optional[Union[bool, str]])
repo_url (Optional[str])
organization (Optional[str])

Return type:

str

_get_files_timestamps(working_dir)

Returns the list of files with their last modification timestamp.

Parameters:: working_dir (Union[str, os.PathLike])

_upload_modified_files(working_dir, repo_id, files_timestamps, commit_message=None, token=None, create_pr=False, revision=None, commit_description=None)

Uploads all modified files in working_dir to repo_id, based on files_timestamps.

Parameters:

working_dir (Union[str, os.PathLike])
repo_id (str)
files_timestamps (Dict[str, float])
commit_message (Optional[str])
token (Optional[Union[bool, str]])
create_pr (bool)
revision (str)
commit_description (str)

push_to_hub(repo_id, use_temp_dir=None, commit_message=None, private=None, token=None, max_shard_size='5GB', create_pr=False, safe_serialization=True, revision=None, commit_description=None, tags=None, **deprecated_kwargs)

Upload the {object_files} to the 🤗 Model Hub.

Parameters:

repo_id (str) – The name of the repository you want to push your {object} to. It should contain your organization name when pushing to a given organization.
use_temp_dir (bool, optional) – Whether or not to use a temporary directory to store the files saved before they are pushed to the Hub. Will default to True if there is no directory named like repo_id, False otherwise.
commit_message (str, optional) – Message to commit while pushing. Will default to “Upload {object}”.
private (bool, optional) – Whether to make the repo private. If None (default), the repo will be public unless the organization’s default is private. This value is ignored if the repo already exists.
token (bool or str, optional) – The token to use as HTTP bearer authorization for remote files. If True, will use the token generated when running huggingface-cli login (stored in ~/.huggingface). Will default to True if repo_url is not specified.
max_shard_size (int or str, optional, defaults to “5GB”) – Only applicable for models. The maximum size for a checkpoint before being sharded. Checkpoints shard will then be each of size lower than this size. If expressed as a string, needs to be digits followed by a unit (like “5MB”). We default it to “5GB” so that users can easily load models on free-tier Google Colab instances without any CPU OOM issues.
create_pr (bool, optional, defaults to False) – Whether or not to create a PR with the uploaded files or directly commit.
safe_serialization (bool, optional, defaults to True) – Whether or not to convert the model weights in safetensors format for safer serialization.
revision (str, optional) – Branch to push the uploaded files to.
commit_description (str, optional) – The description of the commit that will be created
tags (List[str], optional) – List of tags to push on the Hub.

Return type:

str

Examples:

```python from transformers import {object_class}

{object} = {object_class}.from_pretrained(“google-bert/bert-base-cased”)

# Push the {object} to your namespace with the name “my-finetuned-bert”. {object}.push_to_hub(“my-finetuned-bert”)

# Push the {object} to an organization with the name “my-finetuned-bert”. {object}.push_to_hub(“huggingface/my-finetuned-bert”) ```

class medcat.components.addons.relation_extraction.llama.model.RelExtrBaseModel(relcat_config, model_config, pretrained_model_name_or_path)

Bases: BaseModelBluePrint

Base class for the RelCAT models

Parameters:

relcat_config (medcat.config.config_rel_cat.ConfigRelCAT)
model_config (medcat.components.addons.relation_extraction.config.RelExtrBaseConfig)

name = 'basemodel_relcat'

__init__(relcat_config, model_config, pretrained_model_name_or_path)

Class to hold the HF model + model_config

Parameters:

pretrained_model_name_or_path (str) – path to load the model from, this can be a HF model i.e: “bert-base-uncased”, if left empty, it is normally assumed that a model is loaded from ‘model.dat’ using the RelCAT.load() method. So if you are initializing/training a model from scratch be sure to base it on some model.
relcat_config (ConfigRelCAT) – relcat config.
model_config (PretrainedConfig) – HF bert config for model.

relcat_config: medcat.config.config_rel_cat.ConfigRelCAT

model_config: medcat.components.addons.relation_extraction.config.RelExtrBaseConfig

hf_model

pretrained_model_name_or_path: str

_reinitialize_dense_and_frozen_layers(relcat_config)

Reinitialize the dense layers of the model

Parameters:: relcat_config (ConfigRelCAT) – relcat config.
Return type:: None

forward(input_ids=None, attention_mask=None, token_type_ids=None, position_ids=None, head_mask=None, encoder_hidden_states=None, encoder_attention_mask=None, Q=None, e1_e2_start=None, pooled_output=None)

Forward pass for the model

Parameters:

input_ids (torch.Tensor) – input token ids. Defaults to None.
attention_mask (torch.Tensor) – attention mask for the input ids. Defaults to None.
token_type_ids (torch.Tensor) – token type ids for the input ids. Defaults to None.
position_ids (Any) – The position IDs. Defaults to None.
head_mask (Any) – The head mask. Defaults to None.
encoder_hidden_states (Any) – Encoder hidden states. Defaults to None.
encoder_attention_mask (Any) – Encoder attention mask. Defaults to None.
Q (Any) –
1. Defaults to None.
e1_e2_start (Any) – Start and end indices for the entities in the input ids. Defaults to None.
pooled_output (Any) – The pooled output. Defaults to None.

Returns:

Optional[tuple[torch.Tensor, torch.Tensor]] – Logits for the relation classification task.

Return type:

tuple[torch.Tensor, torch.Tensor]

output2logits(pooled_output, sequence_output, input_ids, e1_e2_start)

Parameters:

pooled_output (torch.Tensor) – embedding of the CLS token
sequence_output (torch.Tensor) – hidden states/embeddings for each token in the input text
input_ids (torch.Tensor) – input token ids.
e1_e2_start (torch.Tensor) – annotation tags token position

Returns:

torch.Tensor – classification probabilities for each token.

Return type:

torch.Tensor

classmethod load(pretrained_model_name_or_path, relcat_config, model_config)

Load the model from the given path

Parameters:

pretrained_model_name_or_path (str) – path to load the model from.
relcat_config (ConfigRelCAT) – relcat config.
model_config (RelExtrBaseConfig) – The model-specific config.

Returns:

RelExtrBaseModel – The loaded model.

Return type:

RelExtrBaseModel

drop_out: torch.nn.Dropout

fc1: torch.nn.Linear

fc2: torch.nn.Linear

fc3: torch.nn.Linear

dump_patches: bool = False

_version: int = 1

This allows better BC support for load_state_dict(). In state_dict(), the version number will be saved as in the attribute _metadata of the returned state dict, and thus pickled. _metadata is a dictionary with keys that follow the naming convention of state dict. See _load_from_state_dict on how to use this information in loading.

If new parameters/buffers are added/removed from a module, this number shall be bumped, and the module’s _load_from_state_dict method can compare the version number and do appropriate changes if the state dict is from before the change.

training: bool

_parameters: Dict[str, torch.nn.parameter.Parameter | None]

_buffers: Dict[str, torch.Tensor | None]

_non_persistent_buffers_set: Set[str]

_backward_pre_hooks: Dict[int, Callable]

_backward_hooks: Dict[int, Callable]

_is_full_backward_hook: bool | None

_forward_hooks: Dict[int, Callable]

_forward_hooks_with_kwargs: Dict[int, bool]

_forward_hooks_always_called: Dict[int, bool]

_forward_pre_hooks: Dict[int, Callable]

_forward_pre_hooks_with_kwargs: Dict[int, bool]

_state_dict_hooks: Dict[int, Callable]

_load_state_dict_pre_hooks: Dict[int, Callable]

_state_dict_pre_hooks: Dict[int, Callable]

_load_state_dict_post_hooks: Dict[int, Callable]

_modules: Dict[str, Module | None]

call_super_init: bool = False

_compiled_call_impl: Callable | None = None

register_buffer(name, tensor, persistent=True)

Add a buffer to the module.

This is typically used to register a buffer that should not to be considered a model parameter. For example, BatchNorm’s running_mean is not a parameter, but is part of the module’s state. Buffers, by default, are persistent and will be saved alongside parameters. This behavior can be changed by setting persistent to False. The only difference between a persistent buffer and a non-persistent buffer is that the latter will not be a part of this module’s state_dict.

Buffers can be accessed as attributes using given names.

Parameters:

name (str) – name of the buffer. The buffer can be accessed from this module using the given name
tensor (Tensor or None) – buffer to be registered. If None, then operations that run on buffers, such as cuda, are ignored. If None, the buffer is not included in the module’s state_dict.
persistent (bool) – whether the buffer is part of this module’s state_dict.

Return type:

None

Example:

>>> # xdoctest: +SKIP("undefined vars")
>>> self.register_buffer('running_mean', torch.zeros(num_features))

register_parameter(name, param)

Add a parameter to the module.

The parameter can be accessed as an attribute using given name.

Parameters:

name (str) – name of the parameter. The parameter can be accessed from this module using the given name
param (Parameter or None) – parameter to be added to the module. If None, then operations that run on parameters, such as cuda, are ignored. If None, the parameter is not included in the module’s state_dict.

Return type:

None

add_module(name, module)

Add a child module to the current module.

The module can be accessed as an attribute using the given name.

Parameters:

name (str) – name of the child module. The child module can be accessed from this module using the given name
module (Module) – child module to be added to the module.

Return type:

None

register_module(name, module)

Alias for add_module().

Parameters:

name (str)
module (Optional[Module])

Return type:

None

get_submodule(target)

Return the submodule given by target if it exists, otherwise throw an error.

For example, let’s say you have an nn.Module A that looks like this:

A(
    (net_b): Module(
        (net_c): Module(
            (conv): Conv2d(16, 33, kernel_size=(3, 3), stride=(2, 2))
        )
        (linear): Linear(in_features=100, out_features=200, bias=True)
    )
)

(The diagram shows an nn.Module A. A has a nested submodule net_b, which itself has two submodules net_c and linear. net_c then has a submodule conv.)

To check whether or not we have the linear submodule, we would call get_submodule("net_b.linear"). To check whether we have the conv submodule, we would call get_submodule("net_b.net_c.conv").

The runtime of get_submodule is bounded by the degree of module nesting in target. A query against named_modules achieves the same result, but it is O(N) in the number of transitive modules. So, for a simple check to see if some submodule exists, get_submodule should always be used.

Parameters:: target (str) – The fully-qualified string name of the submodule to look for. (See above example for how to specify a fully-qualified string.)
Returns:: torch.nn.Module – The submodule referenced by target
Raises:: AttributeError – If the target string references an invalid path or resolves to something that is not an nn.Module
Return type:: Module

set_submodule(target, module)

Set the submodule given by target if it exists, otherwise throw an error.

For example, let’s say you have an nn.Module A that looks like this:

A(
    (net_b): Module(
        (net_c): Module(
            (conv): Conv2d(16, 33, kernel_size=(3, 3), stride=(2, 2))
        )
        (linear): Linear(in_features=100, out_features=200, bias=True)
    )
)

(The diagram shows an nn.Module A. A has a nested submodule net_b, which itself has two submodules net_c and linear. net_c then has a submodule conv.)

To overide the Conv2d with a new submodule Linear, you would call set_submodule("net_b.net_c.conv", nn.Linear(33, 16)).

Parameters:

target (str) – The fully-qualified string name of the submodule to look for. (See above example for how to specify a fully-qualified string.)
module (Module) – The module to set the submodule to.

Raises:

ValueError – If the target string is empty
AttributeError – If the target string references an invalid path or resolves to something that is not an nn.Module

Return type:

None

get_parameter(target)

Return the parameter given by target if it exists, otherwise throw an error.

See the docstring for get_submodule for a more detailed explanation of this method’s functionality as well as how to correctly specify target.

Parameters:: target (str) – The fully-qualified string name of the Parameter to look for. (See get_submodule for how to specify a fully-qualified string.)
Returns:: torch.nn.Parameter – The Parameter referenced by target
Raises:: AttributeError – If the target string references an invalid path or resolves to something that is not an nn.Parameter
Return type:: torch.nn.parameter.Parameter

get_buffer(target)

Return the buffer given by target if it exists, otherwise throw an error.

See the docstring for get_submodule for a more detailed explanation of this method’s functionality as well as how to correctly specify target.

Parameters:: target (str) – The fully-qualified string name of the buffer to look for. (See get_submodule for how to specify a fully-qualified string.)
Returns:: torch.Tensor – The buffer referenced by target
Raises:: AttributeError – If the target string references an invalid path or resolves to something that is not a buffer
Return type:: torch.Tensor

get_extra_state()

Return any extra state to include in the module’s state_dict.

Implement this and a corresponding set_extra_state() for your module if you need to store extra state. This function is called when building the module’s state_dict().

Note that extra state should be picklable to ensure working serialization of the state_dict. We only provide provide backwards compatibility guarantees for serializing Tensors; other objects may break backwards compatibility if their serialized pickled form changes.

Returns:: object – Any extra state to store in the module’s state_dict
Return type:: Any

set_extra_state(state)

Set extra state contained in the loaded state_dict.

This function is called from load_state_dict() to handle any extra state found within the state_dict. Implement this function and a corresponding get_extra_state() for your module if you need to store extra state within its state_dict.

Parameters:: state (dict) – Extra state from the state_dict
Return type:: None

_apply(fn, recurse=True)

apply(fn)

Apply fn recursively to every submodule (as returned by .children()) as well as self.

Typical use includes initializing the parameters of a model (see also nn-init-doc).

Parameters:: fn (Module -> None) – function to be applied to each submodule
Returns:: Module – self
Return type:: T

Example:

>>> @torch.no_grad()
>>> def init_weights(m):
>>>     print(m)
>>>     if type(m) == nn.Linear:
>>>         m.weight.fill_(1.0)
>>>         print(m.weight)
>>> net = nn.Sequential(nn.Linear(2, 2), nn.Linear(2, 2))
>>> net.apply(init_weights)
Linear(in_features=2, out_features=2, bias=True)
Parameter containing:
tensor([[1., 1.],
        [1., 1.]], requires_grad=True)
Linear(in_features=2, out_features=2, bias=True)
Parameter containing:
tensor([[1., 1.],
        [1., 1.]], requires_grad=True)
Sequential(
  (0): Linear(in_features=2, out_features=2, bias=True)
  (1): Linear(in_features=2, out_features=2, bias=True)
)

cuda(device=None)

Move all model parameters and buffers to the GPU.

This also makes associated parameters and buffers different objects. So it should be called before constructing optimizer if the module will live on GPU while being optimized.

Note

This method modifies the module in-place.

Parameters:: device (int, optional) – if specified, all parameters will be copied to that device
Returns:: Module – self
Return type:: T

ipu(device=None)

Move all model parameters and buffers to the IPU.

This also makes associated parameters and buffers different objects. So it should be called before constructing optimizer if the module will live on IPU while being optimized.

Note

This method modifies the module in-place.

Parameters:: device (int, optional) – if specified, all parameters will be copied to that device
Returns:: Module – self
Return type:: T

xpu(device=None)

Move all model parameters and buffers to the XPU.

This also makes associated parameters and buffers different objects. So it should be called before constructing optimizer if the module will live on XPU while being optimized.

Note

This method modifies the module in-place.

Parameters:: device (int, optional) – if specified, all parameters will be copied to that device
Returns:: Module – self
Return type:: T

mtia(device=None)

Move all model parameters and buffers to the MTIA.

This also makes associated parameters and buffers different objects. So it should be called before constructing optimizer if the module will live on MTIA while being optimized.

Note

This method modifies the module in-place.

Parameters:: device (int, optional) – if specified, all parameters will be copied to that device
Returns:: Module – self
Return type:: T

cpu()

Move all model parameters and buffers to the CPU.

Note

This method modifies the module in-place.

Returns:: Module – self
Return type:: T

type(dst_type)

Casts all parameters and buffers to dst_type.

Note

This method modifies the module in-place.

Parameters:: dst_type (type or string) – the desired type
Returns:: Module – self
Return type:: T

float()

Casts all floating point parameters and buffers to float datatype.

Note

This method modifies the module in-place.

Returns:: Module – self
Return type:: T

double()

Casts all floating point parameters and buffers to double datatype.

Note

This method modifies the module in-place.

Returns:: Module – self
Return type:: T

half()

Casts all floating point parameters and buffers to half datatype.

Note

This method modifies the module in-place.

Returns:: Module – self
Return type:: T

bfloat16()

Casts all floating point parameters and buffers to bfloat16 datatype.

Note

This method modifies the module in-place.

Returns:: Module – self
Return type:: T

to_empty(*, device, recurse=True)

Move the parameters and buffers to the specified device without copying storage.

Parameters:

device (torch.device) – The desired device of the parameters and buffers in this module.
recurse (bool) – Whether parameters and buffers of submodules should be recursively moved to the specified device.

Returns:

Module – self

Return type:

T

to(device: torch._prims_common.DeviceLikeType | None = ..., dtype: Module.to.dtype | None = ..., non_blocking: bool = ...) → typing_extensions.Self

to(dtype: Module.to.dtype, non_blocking: bool = ...) → typing_extensions.Self

to(tensor: torch.Tensor, non_blocking: bool = ...) → typing_extensions.Self

Move and/or cast the parameters and buffers.

This can be called as

to(device=None, dtype=None, non_blocking=False)

to(dtype, non_blocking=False)

to(tensor, non_blocking=False)

to(memory_format=torch.channels_last)

Its signature is similar to torch.Tensor.to(), but only accepts floating point or complex dtypes. In addition, this method will only cast the floating point or complex parameters and buffers to dtype (if given). The integral parameters and buffers will be moved device, if that is given, but with dtypes unchanged. When non_blocking is set, it tries to convert/move asynchronously with respect to the host if possible, e.g., moving CPU Tensors with pinned memory to CUDA devices.

See below for examples.

Note

This method modifies the module in-place.

Parameters:

device (torch.device) – the desired device of the parameters and buffers in this module
dtype (torch.dtype) – the desired floating point or complex dtype of the parameters and buffers in this module
tensor (torch.Tensor) – Tensor whose dtype and device are the desired dtype and device for all parameters and buffers in this module
memory_format (torch.memory_format) – the desired memory format for 4D parameters and buffers in this module (keyword only argument)

Returns:

Module – self

Examples:

>>> # xdoctest: +IGNORE_WANT("non-deterministic")
>>> linear = nn.Linear(2, 2)
>>> linear.weight
Parameter containing:
tensor([[ 0.1913, -0.3420],
        [-0.5113, -0.2325]])
>>> linear.to(torch.double)
Linear(in_features=2, out_features=2, bias=True)
>>> linear.weight
Parameter containing:
tensor([[ 0.1913, -0.3420],
        [-0.5113, -0.2325]], dtype=torch.float64)
>>> # xdoctest: +REQUIRES(env:TORCH_DOCTEST_CUDA1)
>>> gpu1 = torch.device("cuda:1")
>>> linear.to(gpu1, dtype=torch.half, non_blocking=True)
Linear(in_features=2, out_features=2, bias=True)
>>> linear.weight
Parameter containing:
tensor([[ 0.1914, -0.3420],
        [-0.5112, -0.2324]], dtype=torch.float16, device='cuda:1')
>>> cpu = torch.device("cpu")
>>> linear.to(cpu)
Linear(in_features=2, out_features=2, bias=True)
>>> linear.weight
Parameter containing:
tensor([[ 0.1914, -0.3420],
        [-0.5112, -0.2324]], dtype=torch.float16)

>>> linear = nn.Linear(2, 2, bias=None).to(torch.cdouble)
>>> linear.weight
Parameter containing:
tensor([[ 0.3741+0.j,  0.2382+0.j],
        [ 0.5593+0.j, -0.4443+0.j]], dtype=torch.complex128)
>>> linear(torch.ones(3, 2, dtype=torch.cdouble))
tensor([[0.6122+0.j, 0.1150+0.j],
        [0.6122+0.j, 0.1150+0.j],
        [0.6122+0.j, 0.1150+0.j]], dtype=torch.complex128)

register_full_backward_pre_hook(hook, prepend=False)

Register a backward pre-hook on the module.

The hook will be called every time the gradients for the module are computed. The hook should have the following signature:

hook(module, grad_output) -> tuple[Tensor] or None

The grad_output is a tuple. The hook should not modify its arguments, but it can optionally return a new gradient with respect to the output that will be used in place of grad_output in subsequent computations. Entries in grad_output will be None for all non-Tensor arguments.

For technical reasons, when this hook is applied to a Module, its forward function will receive a view of each Tensor passed to the Module. Similarly the caller will receive a view of each Tensor returned by the Module’s forward function.

Warning

Modifying inputs inplace is not allowed when using backward hooks and will raise an error.

Parameters:

hook (Callable) – The user-defined hook to be registered.
prepend (bool) – If true, the provided hook will be fired before all existing backward_pre hooks on this torch.nn.modules.Module. Otherwise, the provided hook will be fired after all existing backward_pre hooks on this torch.nn.modules.Module. Note that global backward_pre hooks registered with register_module_full_backward_pre_hook() will fire before all hooks registered by this method.

Returns:

:class:`torch.utils.hooks.RemovableHandle` – a handle that can be used to remove the added hook by calling handle.remove()

Return type:

torch.utils.hooks.RemovableHandle

register_backward_hook(hook)

Register a backward hook on the module.

This function is deprecated in favor of register_full_backward_hook() and the behavior of this function will change in future versions.

Returns:: :class:`torch.utils.hooks.RemovableHandle` – a handle that can be used to remove the added hook by calling handle.remove()
Parameters:: hook (Callable[[Module, _grad_t, _grad_t], Union[None, _grad_t]])
Return type:: torch.utils.hooks.RemovableHandle

register_full_backward_hook(hook, prepend=False)

Register a backward hook on the module.

The hook will be called every time the gradients with respect to a module are computed, i.e. the hook will execute if and only if the gradients with respect to module outputs are computed. The hook should have the following signature:

hook(module, grad_input, grad_output) -> tuple(Tensor) or None

The grad_input and grad_output are tuples that contain the gradients with respect to the inputs and outputs respectively. The hook should not modify its arguments, but it can optionally return a new gradient with respect to the input that will be used in place of grad_input in subsequent computations. grad_input will only correspond to the inputs given as positional arguments and all kwarg arguments are ignored. Entries in grad_input and grad_output will be None for all non-Tensor arguments.

For technical reasons, when this hook is applied to a Module, its forward function will receive a view of each Tensor passed to the Module. Similarly the caller will receive a view of each Tensor returned by the Module’s forward function.

Warning

Modifying inputs or outputs inplace is not allowed when using backward hooks and will raise an error.

Parameters:

hook (Callable) – The user-defined hook to be registered.
prepend (bool) – If true, the provided hook will be fired before all existing backward hooks on this torch.nn.modules.Module. Otherwise, the provided hook will be fired after all existing backward hooks on this torch.nn.modules.Module. Note that global backward hooks registered with register_module_full_backward_hook() will fire before all hooks registered by this method.

Returns:

:class:`torch.utils.hooks.RemovableHandle` – a handle that can be used to remove the added hook by calling handle.remove()

Return type:

torch.utils.hooks.RemovableHandle

_get_backward_hooks()

Return the backward hooks for use in the call function.

It returns two lists, one with the full backward hooks and one with the non-full backward hooks.

_get_backward_pre_hooks()

_maybe_warn_non_full_backward_hook(inputs, result, grad_fn)

register_forward_pre_hook(hook, *, prepend=False, with_kwargs=False)

Register a forward pre-hook on the module.

The hook will be called every time before forward() is invoked.

If with_kwargs is false or not specified, the input contains only the positional arguments given to the module. Keyword arguments won’t be passed to the hooks and only to the forward. The hook can modify the input. User can either return a tuple or a single modified value in the hook. We will wrap the value into a tuple if a single value is returned (unless that value is already a tuple). The hook should have the following signature:

hook(module, args) -> None or modified input

If with_kwargs is true, the forward pre-hook will be passed the kwargs given to the forward function. And if the hook modifies the input, both the args and kwargs should be returned. The hook should have the following signature:

hook(module, args, kwargs) -> None or a tuple of modified input and kwargs

Parameters:

hook (Callable) – The user defined hook to be registered.
prepend (bool) – If true, the provided hook will be fired before all existing forward_pre hooks on this torch.nn.modules.Module. Otherwise, the provided hook will be fired after all existing forward_pre hooks on this torch.nn.modules.Module. Note that global forward_pre hooks registered with register_module_forward_pre_hook() will fire before all hooks registered by this method. Default: False
with_kwargs (bool) – If true, the hook will be passed the kwargs given to the forward function. Default: False

Returns:

:class:`torch.utils.hooks.RemovableHandle` – a handle that can be used to remove the added hook by calling handle.remove()

Return type:

torch.utils.hooks.RemovableHandle

register_forward_hook(hook, *, prepend=False, with_kwargs=False, always_call=False)

Register a forward hook on the module.

The hook will be called every time after forward() has computed an output.

If with_kwargs is False or not specified, the input contains only the positional arguments given to the module. Keyword arguments won’t be passed to the hooks and only to the forward. The hook can modify the output. It can modify the input inplace but it will not have effect on forward since this is called after forward() is called. The hook should have the following signature:

hook(module, args, output) -> None or modified output

If with_kwargs is True, the forward hook will be passed the kwargs given to the forward function and be expected to return the output possibly modified. The hook should have the following signature:

hook(module, args, kwargs, output) -> None or modified output

Parameters:

hook (Callable) – The user defined hook to be registered.
prepend (bool) – If True, the provided hook will be fired before all existing forward hooks on this torch.nn.modules.Module. Otherwise, the provided hook will be fired after all existing forward hooks on this torch.nn.modules.Module. Note that global forward hooks registered with register_module_forward_hook() will fire before all hooks registered by this method. Default: False
with_kwargs (bool) – If True, the hook will be passed the kwargs given to the forward function. Default: False
always_call (bool) – If True the hook will be run regardless of whether an exception is raised while calling the Module. Default: False

Returns:

:class:`torch.utils.hooks.RemovableHandle` – a handle that can be used to remove the added hook by calling handle.remove()

Return type:

torch.utils.hooks.RemovableHandle

_slow_forward(*input, **kwargs)

_wrapped_call_impl(*args, **kwargs)

_call_impl(*args, **kwargs)

__call__: Callable[Ellipsis, Any]

__getstate__()

__setstate__(state)

__getattr__(name)

Parameters:: name (str)
Return type:: Any

__setattr__(name, value)

Parameters:

name (str)
value (Union[torch.Tensor, Module])

Return type:

None

__delattr__(name)

_register_state_dict_hook(hook)

Register a post-hook for the state_dict() method.

It should have the following signature::: hook(module, state_dict, prefix, local_metadata) -> None or state_dict

The registered hooks can modify the state_dict inplace or return a new one. If a new state_dict is returned, it will only be respected if it is the root module that state_dict() is called from.

register_state_dict_post_hook(hook)

Register a post-hook for the state_dict() method.

It should have the following signature::: hook(module, state_dict, prefix, local_metadata) -> None

The registered hooks can modify the state_dict inplace.

register_state_dict_pre_hook(hook)

Register a pre-hook for the state_dict() method.

It should have the following signature::: hook(module, prefix, keep_vars) -> None

The registered hooks can be used to perform pre-processing before the state_dict call is made.

_save_to_state_dict(destination, prefix, keep_vars)

Save module state to the destination dictionary.

The destination dictionary will contain the state of the module, but not its descendants. This is called on every submodule in state_dict().

In rare cases, subclasses can achieve class-specific behavior by overriding this method with custom logic.

Parameters:

destination (dict) – a dict where state will be stored
prefix (str) – the prefix for parameters and buffers used in this module

T_destination

state_dict(*, destination: T_destination, prefix: str = ..., keep_vars: bool = ...) → T_destination

state_dict(*, prefix: str = ..., keep_vars: bool = ...) → Dict[str, Any]

Return a dictionary containing references to the whole state of the module.

Both parameters and persistent buffers (e.g. running averages) are included. Keys are corresponding parameter and buffer names. Parameters and buffers set to None are not included.

Note

The returned object is a shallow copy. It contains references to the module’s parameters and buffers.

Warning

Currently state_dict() also accepts positional arguments for destination, prefix and keep_vars in order. However, this is being deprecated and keyword arguments will be enforced in future releases.

Warning

Please avoid the use of argument destination as it is not designed for end-users.

Parameters:

destination (dict, optional) – If provided, the state of module will be updated into the dict and the same object is returned. Otherwise, an OrderedDict will be created and returned. Default: None.
prefix (str, optional) – a prefix added to parameter and buffer names to compose the keys in state_dict. Default: ''.
keep_vars (bool, optional) – by default the Tensor s returned in the state dict are detached from autograd. If it’s set to True, detaching will not be performed. Default: False.

Returns:

dict – a dictionary containing a whole state of the module

Example:

>>> # xdoctest: +SKIP("undefined vars")
>>> module.state_dict().keys()
['bias', 'weight']

_register_load_state_dict_pre_hook(hook, with_module=False)

See register_load_state_dict_pre_hook() for details.

A subtle difference is that if with_module is set to False, then the hook will not take the module as the first argument whereas register_load_state_dict_pre_hook() always takes the module as the first argument.

Parameters:

hook (Callable) – Callable hook that will be invoked before loading the state dict.
with_module (bool, optional) – Whether or not to pass the module instance to the hook as the first parameter.

register_load_state_dict_pre_hook(hook)

Register a pre-hook to be run before module’s load_state_dict() is called.

It should have the following signature::: hook(module, state_dict, prefix, local_metadata, strict, missing_keys, unexpected_keys, error_msgs) -> None # noqa: B950

Parameters:: hook (Callable) – Callable hook that will be invoked before loading the state dict.

register_load_state_dict_post_hook(hook)

Register a post-hook to be run after module’s load_state_dict() is called.

It should have the following signature::: hook(module, incompatible_keys) -> None

The module argument is the current module that this hook is registered on, and the incompatible_keys argument is a NamedTuple consisting of attributes missing_keys and unexpected_keys. missing_keys is a list of str containing the missing keys and unexpected_keys is a list of str containing the unexpected keys.

The given incompatible_keys can be modified inplace if needed.

Note that the checks performed when calling load_state_dict() with strict=True are affected by modifications the hook makes to missing_keys or unexpected_keys, as expected. Additions to either set of keys will result in an error being thrown when strict=True, and clearing out both missing and unexpected keys will avoid an error.

Returns:: :class:`torch.utils.hooks.RemovableHandle` – a handle that can be used to remove the added hook by calling handle.remove()

_load_from_state_dict(state_dict, prefix, local_metadata, strict, missing_keys, unexpected_keys, error_msgs)

Copy parameters and buffers from state_dict into only this module, but not its descendants.

This is called on every submodule in load_state_dict(). Metadata saved for this module in input state_dict is provided as local_metadata. For state dicts without metadata, local_metadata is empty. Subclasses can achieve class-specific backward compatible loading using the version number at local_metadata.get(“version”, None). Additionally, local_metadata can also contain the key assign_to_params_buffers that indicates whether keys should be assigned their corresponding tensor in the state_dict.

Note

state_dict is not the same object as the input state_dict to load_state_dict(). So it can be modified.

Parameters:

state_dict (dict) – a dict containing parameters and persistent buffers.
prefix (str) – the prefix for parameters and buffers used in this module
local_metadata (dict) – a dict containing the metadata for this module. See
strict (bool) – whether to strictly enforce that the keys in state_dict with prefix match the names of parameters and buffers in this module
missing_keys (list of str) – if strict=True, add missing keys to this list
unexpected_keys (list of str) – if strict=True, add unexpected keys to this list
error_msgs (list of str) – error messages should be added to this list, and will be reported together in load_state_dict()

load_state_dict(state_dict, strict=True, assign=False)

Copy parameters and buffers from state_dict into this module and its descendants.

If strict is True, then the keys of state_dict must exactly match the keys returned by this module’s state_dict() function.

Warning

If assign is True the optimizer must be created after the call to load_state_dict unless get_swap_module_params_on_conversion() is True.

Parameters:

state_dict (dict) – a dict containing parameters and persistent buffers.
strict (bool, optional) – whether to strictly enforce that the keys in state_dict match the keys returned by this module’s state_dict() function. Default: True
assign (bool, optional) – When False, the properties of the tensors in the current module are preserved while when True, the properties of the Tensors in the state dict are preserved. The only exception is the requires_grad field of Default: ``False`

Returns:

``NamedTuple`` with ``missing_keys`` and ``unexpected_keys`` fields –

missing_keys is a list of str containing any keys that are expected
by this module but missing from the provided state_dict.
unexpected_keys is a list of str containing the keys that are not
expected by this module but present in the provided state_dict.

Note

If a parameter or buffer is registered as None and its corresponding key exists in state_dict, load_state_dict() will raise a RuntimeError.

_named_members(get_members_fn, prefix='', recurse=True, remove_duplicate=True)

Help yield various names + members of modules.

Parameters:: remove_duplicate (bool)

parameters(recurse=True)

Return an iterator over module parameters.

This is typically passed to an optimizer.

Parameters:: recurse (bool) – if True, then yields parameters of this module and all submodules. Otherwise, yields only parameters that are direct members of this module.
Yields:: Parameter – module parameter
Return type:: Iterator[torch.nn.parameter.Parameter]

Example:

>>> # xdoctest: +SKIP("undefined vars")
>>> for param in model.parameters():
>>>     print(type(param), param.size())
<class 'torch.Tensor'> (20L,)
<class 'torch.Tensor'> (20L, 1L, 5L, 5L)

named_parameters(prefix='', recurse=True, remove_duplicate=True)

Return an iterator over module parameters, yielding both the name of the parameter as well as the parameter itself.

Parameters:

prefix (str) – prefix to prepend to all parameter names.
recurse (bool) – if True, then yields parameters of this module and all submodules. Otherwise, yields only parameters that are direct members of this module.
remove_duplicate (bool, optional) – whether to remove the duplicated parameters in the result. Defaults to True.

Yields:

(str, Parameter) – Tuple containing the name and parameter

Return type:

Iterator[Tuple[str, torch.nn.parameter.Parameter]]

Example:

>>> # xdoctest: +SKIP("undefined vars")
>>> for name, param in self.named_parameters():
>>>     if name in ['bias']:
>>>         print(param.size())

buffers(recurse=True)

Return an iterator over module buffers.

Parameters:: recurse (bool) – if True, then yields buffers of this module and all submodules. Otherwise, yields only buffers that are direct members of this module.
Yields:: torch.Tensor – module buffer
Return type:: Iterator[torch.Tensor]

Example:

>>> # xdoctest: +SKIP("undefined vars")
>>> for buf in model.buffers():
>>>     print(type(buf), buf.size())
<class 'torch.Tensor'> (20L,)
<class 'torch.Tensor'> (20L, 1L, 5L, 5L)

named_buffers(prefix='', recurse=True, remove_duplicate=True)

Return an iterator over module buffers, yielding both the name of the buffer as well as the buffer itself.

Parameters:

prefix (str) – prefix to prepend to all buffer names.
recurse (bool, optional) – if True, then yields buffers of this module and all submodules. Otherwise, yields only buffers that are direct members of this module. Defaults to True.
remove_duplicate (bool, optional) – whether to remove the duplicated buffers in the result. Defaults to True.

Yields:

(str, torch.Tensor) – Tuple containing the name and buffer

Return type:

Iterator[Tuple[str, torch.Tensor]]

Example:

>>> # xdoctest: +SKIP("undefined vars")
>>> for name, buf in self.named_buffers():
>>>     if name in ['running_var']:
>>>         print(buf.size())

children()

Return an iterator over immediate children modules.

Yields:: Module – a child module
Return type:: Iterator[Module]

named_children()

Return an iterator over immediate children modules, yielding both the name of the module as well as the module itself.

Yields:: (str, Module) – Tuple containing a name and child module
Return type:: Iterator[Tuple[str, Module]]

Example:

>>> # xdoctest: +SKIP("undefined vars")
>>> for name, module in model.named_children():
>>>     if name in ['conv4', 'conv5']:
>>>         print(module)

modules()

Return an iterator over all modules in the network.

Yields:: Module – a module in the network
Return type:: Iterator[Module]

Note

Duplicate modules are returned only once. In the following example, l will be returned only once.

Example:

>>> l = nn.Linear(2, 2)
>>> net = nn.Sequential(l, l)
>>> for idx, m in enumerate(net.modules()):
...     print(idx, '->', m)

0 -> Sequential(
  (0): Linear(in_features=2, out_features=2, bias=True)
  (1): Linear(in_features=2, out_features=2, bias=True)
)
1 -> Linear(in_features=2, out_features=2, bias=True)

named_modules(memo=None, prefix='', remove_duplicate=True)

Return an iterator over all modules in the network, yielding both the name of the module as well as the module itself.

Parameters:

memo (Optional[Set[Module]]) – a memo to store the set of modules already added to the result
prefix (str) – a prefix that will be added to the name of the module
remove_duplicate (bool) – whether to remove the duplicated module instances in the result or not

Yields:

(str, Module) – Tuple of name and module

Note

Duplicate modules are returned only once. In the following example, l will be returned only once.

Example:

>>> l = nn.Linear(2, 2)
>>> net = nn.Sequential(l, l)
>>> for idx, m in enumerate(net.named_modules()):
...     print(idx, '->', m)

0 -> ('', Sequential(
  (0): Linear(in_features=2, out_features=2, bias=True)
  (1): Linear(in_features=2, out_features=2, bias=True)
))
1 -> ('0', Linear(in_features=2, out_features=2, bias=True))

train(mode=True)

Set the module in training mode.

This has any effect only on certain modules. See documentations of particular modules for details of their behaviors in training/evaluation mode, if they are affected, e.g. Dropout, BatchNorm, etc.

Parameters:: mode (bool) – whether to set training mode (True) or evaluation mode (False). Default: True.
Returns:: Module – self
Return type:: T

eval()

Set the module in evaluation mode.

This has any effect only on certain modules. See documentations of particular modules for details of their behaviors in training/evaluation mode, if they are affected, e.g. Dropout, BatchNorm, etc.

This is equivalent with self.train(False).

See locally-disable-grad-doc for a comparison between .eval() and several similar mechanisms that may be confused with it.

Returns:: Module – self
Return type:: T

requires_grad_(requires_grad=True)

Change if autograd should record operations on parameters in this module.

This method sets the parameters’ requires_grad attributes in-place.

This method is helpful for freezing part of the module for finetuning or training parts of a model individually (e.g., GAN training).

See locally-disable-grad-doc for a comparison between .requires_grad_() and several similar mechanisms that may be confused with it.

Parameters:: requires_grad (bool) – whether autograd should record operations on parameters in this module. Default: True.
Returns:: Module – self
Return type:: T

zero_grad(set_to_none=True)

Reset gradients of all model parameters.

See similar function under torch.optim.Optimizer for more context.

Parameters:: set_to_none (bool) – instead of setting to zero, set the grads to None. See torch.optim.Optimizer.zero_grad() for details.
Return type:: None

share_memory()

See torch.Tensor.share_memory_().

Return type:: T

_get_name()

extra_repr()

Set the extra representation of the module.

To print customized extra information, you should re-implement this method in your own modules. Both single-line and multi-line strings are acceptable.

Return type:: str

__repr__()

__dir__()

_replicate_for_data_parallel()

compile(*args, **kwargs)

Compile this Module’s forward using torch.compile().

This Module’s __call__ method is compiled and all arguments are passed as-is to torch.compile().

See torch.compile() for details on the arguments for this function.

medcat.components.addons.relation_extraction.llama.model.create_dense_layers(relcat_config)

Parameters:: relcat_config (medcat.config.config_rel_cat.ConfigRelCAT)

medcat.components.addons.relation_extraction.llama.model.get_annotation_schema_tag(sequence_output, input_ids, special_tag)

Gets to token sequences from the sequence_ouput for the specific token: tag ids in self.relcat_config.general.annotation_schema_tag_ids.

Parameters:

sequence_output (torch.Tensor) – hidden states/embeddings for each token in the input text
input_ids (torch.Tensor) – input token ids
special_tag (list) – special annotation token id pairs

Returns:

torch.Tensor – new seq_tags

Return type:

torch.Tensor

medcat.components.addons.relation_extraction.llama.model.logger

class medcat.components.addons.relation_extraction.llama.model.RelExtrLlamaModel(pretrained_model_name_or_path, relcat_config, model_config)

Bases: medcat.components.addons.relation_extraction.models.RelExtrBaseModel

LlamaModel class for RelCAT

Parameters:

pretrained_model_name_or_path (str)
relcat_config (medcat.config.config_rel_cat.ConfigRelCAT)
model_config (medcat.components.addons.relation_extraction.llama.config.RelExtrLlamaConfig)

name = 'llamamodel_relcat'

__init__(pretrained_model_name_or_path, relcat_config, model_config)

Class to hold the Llama model + model_config

Parameters:

pretrained_model_name_or_path (str) – path to load the model from, this can be a HF model i.e: “bert-base-uncased”, if left empty, it is normally assumed that a model is loaded from ‘model.dat’ using the RelCAT.load() method. So if you are initializing/training a model from scratch be sure to base it on some model.
relcat_config (ConfigRelCAT) – relcat config.
model_config (Union[RelExtrBaseConfig | RelExtrLlamaConfig]) – HF bert config for model.

relcat_config

model_config

hf_model

drop_out

llama_pooler

output2logits(pooled_output, sequence_output, input_ids, e1_e2_start)

Parameters:

pooled_output (torch.Tensor) – embedding of the CLS token
sequence_output (torch.Tensor) – hidden states/embeddings for each token in the input text
input_ids (torch.Tensor) – input token ids.
e1_e2_start (torch.Tensor) – annotation tags token position

Returns:

torch.Tensor – classification probabilities for each token.

Return type:

torch.Tensor

forward(input_ids=None, attention_mask=None, token_type_ids=None, position_ids=None, head_mask=None, encoder_hidden_states=None, encoder_attention_mask=None, Q=None, e1_e2_start=None, pooled_output=None)

Forward pass for the model

Parameters:

input_ids (torch.Tensor) – input token ids. Defaults to None.
attention_mask (torch.Tensor) – attention mask for the input ids. Defaults to None.
token_type_ids (torch.Tensor) – token type ids for the input ids. Defaults to None.
position_ids (Any) – The position IDs. Defaults to None.
head_mask (Any) – The head mask. Defaults to None.
encoder_hidden_states (Any) – Encoder hidden states. Defaults to None.
encoder_attention_mask (Any) – Encoder attention mask. Defaults to None.
Q (Any) –
1. Defaults to None.
e1_e2_start (Any) – Start and end indices for the entities in the input ids. Defaults to None.
pooled_output (Any) – The pooled output. Defaults to None.

Returns:

Optional[tuple[torch.Tensor, torch.Tensor]] – Logits for the relation classification task.

Return type:

tuple[torch.Tensor, torch.Tensor]

classmethod load_specific(pretrained_model_name_or_path, relcat_config, model_config, **kwargs)

Parameters:

pretrained_model_name_or_path (str)
relcat_config (medcat.config.config_rel_cat.ConfigRelCAT)
model_config (medcat.components.addons.relation_extraction.llama.config.RelExtrLlamaConfig)

Return type:

RelExtrLlamaModel

pretrained_model_name_or_path: str

_reinitialize_dense_and_frozen_layers(relcat_config)

Reinitialize the dense layers of the model

Parameters:: relcat_config (ConfigRelCAT) – relcat config.
Return type:: None

classmethod load(pretrained_model_name_or_path, relcat_config, model_config)

Load the model from the given path

Parameters:

pretrained_model_name_or_path (str) – path to load the model from.
relcat_config (ConfigRelCAT) – relcat config.
model_config (RelExtrBaseConfig) – The model-specific config.

Returns:

RelExtrBaseModel – The loaded model.

Return type:

RelExtrBaseModel

fc1: torch.nn.Linear

fc2: torch.nn.Linear

fc3: torch.nn.Linear

dump_patches: bool = False

_version: int = 1

This allows better BC support for load_state_dict(). In state_dict(), the version number will be saved as in the attribute _metadata of the returned state dict, and thus pickled. _metadata is a dictionary with keys that follow the naming convention of state dict. See _load_from_state_dict on how to use this information in loading.

If new parameters/buffers are added/removed from a module, this number shall be bumped, and the module’s _load_from_state_dict method can compare the version number and do appropriate changes if the state dict is from before the change.

training: bool

_parameters: Dict[str, torch.nn.parameter.Parameter | None]

_buffers: Dict[str, torch.Tensor | None]

_non_persistent_buffers_set: Set[str]

_backward_pre_hooks: Dict[int, Callable]

_backward_hooks: Dict[int, Callable]

_is_full_backward_hook: bool | None

_forward_hooks: Dict[int, Callable]

_forward_hooks_with_kwargs: Dict[int, bool]

_forward_hooks_always_called: Dict[int, bool]

_forward_pre_hooks: Dict[int, Callable]

_forward_pre_hooks_with_kwargs: Dict[int, bool]

_state_dict_hooks: Dict[int, Callable]

_load_state_dict_pre_hooks: Dict[int, Callable]

_state_dict_pre_hooks: Dict[int, Callable]

_load_state_dict_post_hooks: Dict[int, Callable]

_modules: Dict[str, Module | None]

call_super_init: bool = False

_compiled_call_impl: Callable | None = None

register_buffer(name, tensor, persistent=True)

Add a buffer to the module.

This is typically used to register a buffer that should not to be considered a model parameter. For example, BatchNorm’s running_mean is not a parameter, but is part of the module’s state. Buffers, by default, are persistent and will be saved alongside parameters. This behavior can be changed by setting persistent to False. The only difference between a persistent buffer and a non-persistent buffer is that the latter will not be a part of this module’s state_dict.

Buffers can be accessed as attributes using given names.

Parameters:

name (str) – name of the buffer. The buffer can be accessed from this module using the given name
tensor (Tensor or None) – buffer to be registered. If None, then operations that run on buffers, such as cuda, are ignored. If None, the buffer is not included in the module’s state_dict.
persistent (bool) – whether the buffer is part of this module’s state_dict.

Return type:

None

Example:

>>> # xdoctest: +SKIP("undefined vars")
>>> self.register_buffer('running_mean', torch.zeros(num_features))

register_parameter(name, param)

Add a parameter to the module.

The parameter can be accessed as an attribute using given name.

Parameters:

name (str) – name of the parameter. The parameter can be accessed from this module using the given name
param (Parameter or None) – parameter to be added to the module. If None, then operations that run on parameters, such as cuda, are ignored. If None, the parameter is not included in the module’s state_dict.

Return type:

None

add_module(name, module)

Add a child module to the current module.

The module can be accessed as an attribute using the given name.

Parameters:

name (str) – name of the child module. The child module can be accessed from this module using the given name
module (Module) – child module to be added to the module.

Return type:

None

register_module(name, module)

Alias for add_module().

Parameters:

name (str)
module (Optional[Module])

Return type:

None

get_submodule(target)

Return the submodule given by target if it exists, otherwise throw an error.

For example, let’s say you have an nn.Module A that looks like this:

A(
    (net_b): Module(
        (net_c): Module(
            (conv): Conv2d(16, 33, kernel_size=(3, 3), stride=(2, 2))
        )
        (linear): Linear(in_features=100, out_features=200, bias=True)
    )
)

(The diagram shows an nn.Module A. A has a nested submodule net_b, which itself has two submodules net_c and linear. net_c then has a submodule conv.)

To check whether or not we have the linear submodule, we would call get_submodule("net_b.linear"). To check whether we have the conv submodule, we would call get_submodule("net_b.net_c.conv").

The runtime of get_submodule is bounded by the degree of module nesting in target. A query against named_modules achieves the same result, but it is O(N) in the number of transitive modules. So, for a simple check to see if some submodule exists, get_submodule should always be used.

Parameters:: target (str) – The fully-qualified string name of the submodule to look for. (See above example for how to specify a fully-qualified string.)
Returns:: torch.nn.Module – The submodule referenced by target
Raises:: AttributeError – If the target string references an invalid path or resolves to something that is not an nn.Module
Return type:: Module

set_submodule(target, module)

Set the submodule given by target if it exists, otherwise throw an error.

For example, let’s say you have an nn.Module A that looks like this:

A(
    (net_b): Module(
        (net_c): Module(
            (conv): Conv2d(16, 33, kernel_size=(3, 3), stride=(2, 2))
        )
        (linear): Linear(in_features=100, out_features=200, bias=True)
    )
)

(The diagram shows an nn.Module A. A has a nested submodule net_b, which itself has two submodules net_c and linear. net_c then has a submodule conv.)

To overide the Conv2d with a new submodule Linear, you would call set_submodule("net_b.net_c.conv", nn.Linear(33, 16)).

Parameters:

target (str) – The fully-qualified string name of the submodule to look for. (See above example for how to specify a fully-qualified string.)
module (Module) – The module to set the submodule to.

Raises:

ValueError – If the target string is empty
AttributeError – If the target string references an invalid path or resolves to something that is not an nn.Module

Return type:

None

get_parameter(target)

Return the parameter given by target if it exists, otherwise throw an error.

See the docstring for get_submodule for a more detailed explanation of this method’s functionality as well as how to correctly specify target.

Parameters:: target (str) – The fully-qualified string name of the Parameter to look for. (See get_submodule for how to specify a fully-qualified string.)
Returns:: torch.nn.Parameter – The Parameter referenced by target
Raises:: AttributeError – If the target string references an invalid path or resolves to something that is not an nn.Parameter
Return type:: torch.nn.parameter.Parameter

get_buffer(target)

Return the buffer given by target if it exists, otherwise throw an error.

See the docstring for get_submodule for a more detailed explanation of this method’s functionality as well as how to correctly specify target.

Parameters:: target (str) – The fully-qualified string name of the buffer to look for. (See get_submodule for how to specify a fully-qualified string.)
Returns:: torch.Tensor – The buffer referenced by target
Raises:: AttributeError – If the target string references an invalid path or resolves to something that is not a buffer
Return type:: torch.Tensor

get_extra_state()

Return any extra state to include in the module’s state_dict.

Implement this and a corresponding set_extra_state() for your module if you need to store extra state. This function is called when building the module’s state_dict().

Note that extra state should be picklable to ensure working serialization of the state_dict. We only provide provide backwards compatibility guarantees for serializing Tensors; other objects may break backwards compatibility if their serialized pickled form changes.

Returns:: object – Any extra state to store in the module’s state_dict
Return type:: Any

set_extra_state(state)

Set extra state contained in the loaded state_dict.

This function is called from load_state_dict() to handle any extra state found within the state_dict. Implement this function and a corresponding get_extra_state() for your module if you need to store extra state within its state_dict.

Parameters:: state (dict) – Extra state from the state_dict
Return type:: None

_apply(fn, recurse=True)

apply(fn)

Apply fn recursively to every submodule (as returned by .children()) as well as self.

Typical use includes initializing the parameters of a model (see also nn-init-doc).

Parameters:: fn (Module -> None) – function to be applied to each submodule
Returns:: Module – self
Return type:: T

Example:

>>> @torch.no_grad()
>>> def init_weights(m):
>>>     print(m)
>>>     if type(m) == nn.Linear:
>>>         m.weight.fill_(1.0)
>>>         print(m.weight)
>>> net = nn.Sequential(nn.Linear(2, 2), nn.Linear(2, 2))
>>> net.apply(init_weights)
Linear(in_features=2, out_features=2, bias=True)
Parameter containing:
tensor([[1., 1.],
        [1., 1.]], requires_grad=True)
Linear(in_features=2, out_features=2, bias=True)
Parameter containing:
tensor([[1., 1.],
        [1., 1.]], requires_grad=True)
Sequential(
  (0): Linear(in_features=2, out_features=2, bias=True)
  (1): Linear(in_features=2, out_features=2, bias=True)
)

cuda(device=None)

Move all model parameters and buffers to the GPU.

This also makes associated parameters and buffers different objects. So it should be called before constructing optimizer if the module will live on GPU while being optimized.

Note

This method modifies the module in-place.

Parameters:: device (int, optional) – if specified, all parameters will be copied to that device
Returns:: Module – self
Return type:: T

ipu(device=None)

Move all model parameters and buffers to the IPU.

This also makes associated parameters and buffers different objects. So it should be called before constructing optimizer if the module will live on IPU while being optimized.

Note

This method modifies the module in-place.

Parameters:: device (int, optional) – if specified, all parameters will be copied to that device
Returns:: Module – self
Return type:: T

xpu(device=None)

Move all model parameters and buffers to the XPU.

This also makes associated parameters and buffers different objects. So it should be called before constructing optimizer if the module will live on XPU while being optimized.

Note

This method modifies the module in-place.

Parameters:: device (int, optional) – if specified, all parameters will be copied to that device
Returns:: Module – self
Return type:: T

mtia(device=None)

Move all model parameters and buffers to the MTIA.

This also makes associated parameters and buffers different objects. So it should be called before constructing optimizer if the module will live on MTIA while being optimized.

Note

This method modifies the module in-place.

Parameters:: device (int, optional) – if specified, all parameters will be copied to that device
Returns:: Module – self
Return type:: T

cpu()

Move all model parameters and buffers to the CPU.

Note

This method modifies the module in-place.

Returns:: Module – self
Return type:: T

type(dst_type)

Casts all parameters and buffers to dst_type.

Note

This method modifies the module in-place.

Parameters:: dst_type (type or string) – the desired type
Returns:: Module – self
Return type:: T

float()

Casts all floating point parameters and buffers to float datatype.

Note

This method modifies the module in-place.

Returns:: Module – self
Return type:: T

double()

Casts all floating point parameters and buffers to double datatype.

Note

This method modifies the module in-place.

Returns:: Module – self
Return type:: T

half()

Casts all floating point parameters and buffers to half datatype.

Note

This method modifies the module in-place.

Returns:: Module – self
Return type:: T

bfloat16()

Casts all floating point parameters and buffers to bfloat16 datatype.

Note

This method modifies the module in-place.

Returns:: Module – self
Return type:: T

to_empty(*, device, recurse=True)

Move the parameters and buffers to the specified device without copying storage.

Parameters:

device (torch.device) – The desired device of the parameters and buffers in this module.
recurse (bool) – Whether parameters and buffers of submodules should be recursively moved to the specified device.

Returns:

Module – self

Return type:

T

to(device: torch._prims_common.DeviceLikeType | None = ..., dtype: Module.to.dtype | None = ..., non_blocking: bool = ...) → typing_extensions.Self

to(dtype: Module.to.dtype, non_blocking: bool = ...) → typing_extensions.Self

to(tensor: torch.Tensor, non_blocking: bool = ...) → typing_extensions.Self

Move and/or cast the parameters and buffers.

This can be called as

to(device=None, dtype=None, non_blocking=False)

to(dtype, non_blocking=False)

to(tensor, non_blocking=False)

to(memory_format=torch.channels_last)

Its signature is similar to torch.Tensor.to(), but only accepts floating point or complex dtypes. In addition, this method will only cast the floating point or complex parameters and buffers to dtype (if given). The integral parameters and buffers will be moved device, if that is given, but with dtypes unchanged. When non_blocking is set, it tries to convert/move asynchronously with respect to the host if possible, e.g., moving CPU Tensors with pinned memory to CUDA devices.

See below for examples.

Note

This method modifies the module in-place.

Parameters:

device (torch.device) – the desired device of the parameters and buffers in this module
dtype (torch.dtype) – the desired floating point or complex dtype of the parameters and buffers in this module
tensor (torch.Tensor) – Tensor whose dtype and device are the desired dtype and device for all parameters and buffers in this module
memory_format (torch.memory_format) – the desired memory format for 4D parameters and buffers in this module (keyword only argument)

Returns:

Module – self

Examples:

>>> # xdoctest: +IGNORE_WANT("non-deterministic")
>>> linear = nn.Linear(2, 2)
>>> linear.weight
Parameter containing:
tensor([[ 0.1913, -0.3420],
        [-0.5113, -0.2325]])
>>> linear.to(torch.double)
Linear(in_features=2, out_features=2, bias=True)
>>> linear.weight
Parameter containing:
tensor([[ 0.1913, -0.3420],
        [-0.5113, -0.2325]], dtype=torch.float64)
>>> # xdoctest: +REQUIRES(env:TORCH_DOCTEST_CUDA1)
>>> gpu1 = torch.device("cuda:1")
>>> linear.to(gpu1, dtype=torch.half, non_blocking=True)
Linear(in_features=2, out_features=2, bias=True)
>>> linear.weight
Parameter containing:
tensor([[ 0.1914, -0.3420],
        [-0.5112, -0.2324]], dtype=torch.float16, device='cuda:1')
>>> cpu = torch.device("cpu")
>>> linear.to(cpu)
Linear(in_features=2, out_features=2, bias=True)
>>> linear.weight
Parameter containing:
tensor([[ 0.1914, -0.3420],
        [-0.5112, -0.2324]], dtype=torch.float16)

>>> linear = nn.Linear(2, 2, bias=None).to(torch.cdouble)
>>> linear.weight
Parameter containing:
tensor([[ 0.3741+0.j,  0.2382+0.j],
        [ 0.5593+0.j, -0.4443+0.j]], dtype=torch.complex128)
>>> linear(torch.ones(3, 2, dtype=torch.cdouble))
tensor([[0.6122+0.j, 0.1150+0.j],
        [0.6122+0.j, 0.1150+0.j],
        [0.6122+0.j, 0.1150+0.j]], dtype=torch.complex128)

register_full_backward_pre_hook(hook, prepend=False)

Register a backward pre-hook on the module.

The hook will be called every time the gradients for the module are computed. The hook should have the following signature:

hook(module, grad_output) -> tuple[Tensor] or None

The grad_output is a tuple. The hook should not modify its arguments, but it can optionally return a new gradient with respect to the output that will be used in place of grad_output in subsequent computations. Entries in grad_output will be None for all non-Tensor arguments.

For technical reasons, when this hook is applied to a Module, its forward function will receive a view of each Tensor passed to the Module. Similarly the caller will receive a view of each Tensor returned by the Module’s forward function.

Warning

Modifying inputs inplace is not allowed when using backward hooks and will raise an error.

Parameters:

hook (Callable) – The user-defined hook to be registered.
prepend (bool) – If true, the provided hook will be fired before all existing backward_pre hooks on this torch.nn.modules.Module. Otherwise, the provided hook will be fired after all existing backward_pre hooks on this torch.nn.modules.Module. Note that global backward_pre hooks registered with register_module_full_backward_pre_hook() will fire before all hooks registered by this method.

Returns:

:class:`torch.utils.hooks.RemovableHandle` – a handle that can be used to remove the added hook by calling handle.remove()

Return type:

torch.utils.hooks.RemovableHandle

register_backward_hook(hook)

Register a backward hook on the module.

This function is deprecated in favor of register_full_backward_hook() and the behavior of this function will change in future versions.

Returns:: :class:`torch.utils.hooks.RemovableHandle` – a handle that can be used to remove the added hook by calling handle.remove()
Parameters:: hook (Callable[[Module, _grad_t, _grad_t], Union[None, _grad_t]])
Return type:: torch.utils.hooks.RemovableHandle

register_full_backward_hook(hook, prepend=False)

Register a backward hook on the module.

The hook will be called every time the gradients with respect to a module are computed, i.e. the hook will execute if and only if the gradients with respect to module outputs are computed. The hook should have the following signature:

hook(module, grad_input, grad_output) -> tuple(Tensor) or None

The grad_input and grad_output are tuples that contain the gradients with respect to the inputs and outputs respectively. The hook should not modify its arguments, but it can optionally return a new gradient with respect to the input that will be used in place of grad_input in subsequent computations. grad_input will only correspond to the inputs given as positional arguments and all kwarg arguments are ignored. Entries in grad_input and grad_output will be None for all non-Tensor arguments.

For technical reasons, when this hook is applied to a Module, its forward function will receive a view of each Tensor passed to the Module. Similarly the caller will receive a view of each Tensor returned by the Module’s forward function.

Warning

Modifying inputs or outputs inplace is not allowed when using backward hooks and will raise an error.

Parameters:

hook (Callable) – The user-defined hook to be registered.
prepend (bool) – If true, the provided hook will be fired before all existing backward hooks on this torch.nn.modules.Module. Otherwise, the provided hook will be fired after all existing backward hooks on this torch.nn.modules.Module. Note that global backward hooks registered with register_module_full_backward_hook() will fire before all hooks registered by this method.

Returns:

:class:`torch.utils.hooks.RemovableHandle` – a handle that can be used to remove the added hook by calling handle.remove()

Return type:

torch.utils.hooks.RemovableHandle

_get_backward_hooks()

Return the backward hooks for use in the call function.

It returns two lists, one with the full backward hooks and one with the non-full backward hooks.

_get_backward_pre_hooks()

_maybe_warn_non_full_backward_hook(inputs, result, grad_fn)

register_forward_pre_hook(hook, *, prepend=False, with_kwargs=False)

Register a forward pre-hook on the module.

The hook will be called every time before forward() is invoked.

If with_kwargs is false or not specified, the input contains only the positional arguments given to the module. Keyword arguments won’t be passed to the hooks and only to the forward. The hook can modify the input. User can either return a tuple or a single modified value in the hook. We will wrap the value into a tuple if a single value is returned (unless that value is already a tuple). The hook should have the following signature:

hook(module, args) -> None or modified input

If with_kwargs is true, the forward pre-hook will be passed the kwargs given to the forward function. And if the hook modifies the input, both the args and kwargs should be returned. The hook should have the following signature:

hook(module, args, kwargs) -> None or a tuple of modified input and kwargs

Parameters:

hook (Callable) – The user defined hook to be registered.
prepend (bool) – If true, the provided hook will be fired before all existing forward_pre hooks on this torch.nn.modules.Module. Otherwise, the provided hook will be fired after all existing forward_pre hooks on this torch.nn.modules.Module. Note that global forward_pre hooks registered with register_module_forward_pre_hook() will fire before all hooks registered by this method. Default: False
with_kwargs (bool) – If true, the hook will be passed the kwargs given to the forward function. Default: False

Returns:

:class:`torch.utils.hooks.RemovableHandle` – a handle that can be used to remove the added hook by calling handle.remove()

Return type:

torch.utils.hooks.RemovableHandle

register_forward_hook(hook, *, prepend=False, with_kwargs=False, always_call=False)

Register a forward hook on the module.

The hook will be called every time after forward() has computed an output.

If with_kwargs is False or not specified, the input contains only the positional arguments given to the module. Keyword arguments won’t be passed to the hooks and only to the forward. The hook can modify the output. It can modify the input inplace but it will not have effect on forward since this is called after forward() is called. The hook should have the following signature:

hook(module, args, output) -> None or modified output

If with_kwargs is True, the forward hook will be passed the kwargs given to the forward function and be expected to return the output possibly modified. The hook should have the following signature:

hook(module, args, kwargs, output) -> None or modified output

Parameters:

hook (Callable) – The user defined hook to be registered.
prepend (bool) – If True, the provided hook will be fired before all existing forward hooks on this torch.nn.modules.Module. Otherwise, the provided hook will be fired after all existing forward hooks on this torch.nn.modules.Module. Note that global forward hooks registered with register_module_forward_hook() will fire before all hooks registered by this method. Default: False
with_kwargs (bool) – If True, the hook will be passed the kwargs given to the forward function. Default: False
always_call (bool) – If True the hook will be run regardless of whether an exception is raised while calling the Module. Default: False

Returns:

:class:`torch.utils.hooks.RemovableHandle` – a handle that can be used to remove the added hook by calling handle.remove()

Return type:

torch.utils.hooks.RemovableHandle

_slow_forward(*input, **kwargs)

_wrapped_call_impl(*args, **kwargs)

_call_impl(*args, **kwargs)

__call__: Callable[Ellipsis, Any]

__getstate__()

__setstate__(state)

__getattr__(name)

Parameters:: name (str)
Return type:: Any

__setattr__(name, value)

Parameters:

name (str)
value (Union[torch.Tensor, Module])

Return type:

None

__delattr__(name)

_register_state_dict_hook(hook)

Register a post-hook for the state_dict() method.

It should have the following signature::: hook(module, state_dict, prefix, local_metadata) -> None or state_dict

The registered hooks can modify the state_dict inplace or return a new one. If a new state_dict is returned, it will only be respected if it is the root module that state_dict() is called from.

register_state_dict_post_hook(hook)

Register a post-hook for the state_dict() method.

It should have the following signature::: hook(module, state_dict, prefix, local_metadata) -> None

The registered hooks can modify the state_dict inplace.

register_state_dict_pre_hook(hook)

Register a pre-hook for the state_dict() method.

It should have the following signature::: hook(module, prefix, keep_vars) -> None

The registered hooks can be used to perform pre-processing before the state_dict call is made.

_save_to_state_dict(destination, prefix, keep_vars)

Save module state to the destination dictionary.

The destination dictionary will contain the state of the module, but not its descendants. This is called on every submodule in state_dict().

In rare cases, subclasses can achieve class-specific behavior by overriding this method with custom logic.

Parameters:

destination (dict) – a dict where state will be stored
prefix (str) – the prefix for parameters and buffers used in this module

T_destination

state_dict(*, destination: T_destination, prefix: str = ..., keep_vars: bool = ...) → T_destination

state_dict(*, prefix: str = ..., keep_vars: bool = ...) → Dict[str, Any]

Return a dictionary containing references to the whole state of the module.

Both parameters and persistent buffers (e.g. running averages) are included. Keys are corresponding parameter and buffer names. Parameters and buffers set to None are not included.

Note

The returned object is a shallow copy. It contains references to the module’s parameters and buffers.

Warning

Currently state_dict() also accepts positional arguments for destination, prefix and keep_vars in order. However, this is being deprecated and keyword arguments will be enforced in future releases.

Warning

Please avoid the use of argument destination as it is not designed for end-users.

Parameters:

destination (dict, optional) – If provided, the state of module will be updated into the dict and the same object is returned. Otherwise, an OrderedDict will be created and returned. Default: None.
prefix (str, optional) – a prefix added to parameter and buffer names to compose the keys in state_dict. Default: ''.
keep_vars (bool, optional) – by default the Tensor s returned in the state dict are detached from autograd. If it’s set to True, detaching will not be performed. Default: False.

Returns:

dict – a dictionary containing a whole state of the module

Example:

>>> # xdoctest: +SKIP("undefined vars")
>>> module.state_dict().keys()
['bias', 'weight']

_register_load_state_dict_pre_hook(hook, with_module=False)

See register_load_state_dict_pre_hook() for details.

A subtle difference is that if with_module is set to False, then the hook will not take the module as the first argument whereas register_load_state_dict_pre_hook() always takes the module as the first argument.

Parameters:

hook (Callable) – Callable hook that will be invoked before loading the state dict.
with_module (bool, optional) – Whether or not to pass the module instance to the hook as the first parameter.

register_load_state_dict_pre_hook(hook)

Register a pre-hook to be run before module’s load_state_dict() is called.

It should have the following signature::: hook(module, state_dict, prefix, local_metadata, strict, missing_keys, unexpected_keys, error_msgs) -> None # noqa: B950

Parameters:: hook (Callable) – Callable hook that will be invoked before loading the state dict.

register_load_state_dict_post_hook(hook)

Register a post-hook to be run after module’s load_state_dict() is called.

It should have the following signature::: hook(module, incompatible_keys) -> None

The module argument is the current module that this hook is registered on, and the incompatible_keys argument is a NamedTuple consisting of attributes missing_keys and unexpected_keys. missing_keys is a list of str containing the missing keys and unexpected_keys is a list of str containing the unexpected keys.

The given incompatible_keys can be modified inplace if needed.

Note that the checks performed when calling load_state_dict() with strict=True are affected by modifications the hook makes to missing_keys or unexpected_keys, as expected. Additions to either set of keys will result in an error being thrown when strict=True, and clearing out both missing and unexpected keys will avoid an error.

Returns:: :class:`torch.utils.hooks.RemovableHandle` – a handle that can be used to remove the added hook by calling handle.remove()

_load_from_state_dict(state_dict, prefix, local_metadata, strict, missing_keys, unexpected_keys, error_msgs)

Copy parameters and buffers from state_dict into only this module, but not its descendants.

This is called on every submodule in load_state_dict(). Metadata saved for this module in input state_dict is provided as local_metadata. For state dicts without metadata, local_metadata is empty. Subclasses can achieve class-specific backward compatible loading using the version number at local_metadata.get(“version”, None). Additionally, local_metadata can also contain the key assign_to_params_buffers that indicates whether keys should be assigned their corresponding tensor in the state_dict.

Note

state_dict is not the same object as the input state_dict to load_state_dict(). So it can be modified.

Parameters:

state_dict (dict) – a dict containing parameters and persistent buffers.
prefix (str) – the prefix for parameters and buffers used in this module
local_metadata (dict) – a dict containing the metadata for this module. See
strict (bool) – whether to strictly enforce that the keys in state_dict with prefix match the names of parameters and buffers in this module
missing_keys (list of str) – if strict=True, add missing keys to this list
unexpected_keys (list of str) – if strict=True, add unexpected keys to this list
error_msgs (list of str) – error messages should be added to this list, and will be reported together in load_state_dict()

load_state_dict(state_dict, strict=True, assign=False)

Copy parameters and buffers from state_dict into this module and its descendants.

If strict is True, then the keys of state_dict must exactly match the keys returned by this module’s state_dict() function.

Warning

If assign is True the optimizer must be created after the call to load_state_dict unless get_swap_module_params_on_conversion() is True.

Parameters:

state_dict (dict) – a dict containing parameters and persistent buffers.
strict (bool, optional) – whether to strictly enforce that the keys in state_dict match the keys returned by this module’s state_dict() function. Default: True
assign (bool, optional) – When False, the properties of the tensors in the current module are preserved while when True, the properties of the Tensors in the state dict are preserved. The only exception is the requires_grad field of Default: ``False`

Returns:

``NamedTuple`` with ``missing_keys`` and ``unexpected_keys`` fields –

missing_keys is a list of str containing any keys that are expected
by this module but missing from the provided state_dict.
unexpected_keys is a list of str containing the keys that are not
expected by this module but present in the provided state_dict.

Note

If a parameter or buffer is registered as None and its corresponding key exists in state_dict, load_state_dict() will raise a RuntimeError.

_named_members(get_members_fn, prefix='', recurse=True, remove_duplicate=True)

Help yield various names + members of modules.

Parameters:: remove_duplicate (bool)

parameters(recurse=True)

Return an iterator over module parameters.

This is typically passed to an optimizer.

Parameters:: recurse (bool) – if True, then yields parameters of this module and all submodules. Otherwise, yields only parameters that are direct members of this module.
Yields:: Parameter – module parameter
Return type:: Iterator[torch.nn.parameter.Parameter]

Example:

>>> # xdoctest: +SKIP("undefined vars")
>>> for param in model.parameters():
>>>     print(type(param), param.size())
<class 'torch.Tensor'> (20L,)
<class 'torch.Tensor'> (20L, 1L, 5L, 5L)

named_parameters(prefix='', recurse=True, remove_duplicate=True)

Return an iterator over module parameters, yielding both the name of the parameter as well as the parameter itself.

Parameters:

prefix (str) – prefix to prepend to all parameter names.
recurse (bool) – if True, then yields parameters of this module and all submodules. Otherwise, yields only parameters that are direct members of this module.
remove_duplicate (bool, optional) – whether to remove the duplicated parameters in the result. Defaults to True.

Yields:

(str, Parameter) – Tuple containing the name and parameter

Return type:

Iterator[Tuple[str, torch.nn.parameter.Parameter]]

Example:

>>> # xdoctest: +SKIP("undefined vars")
>>> for name, param in self.named_parameters():
>>>     if name in ['bias']:
>>>         print(param.size())

buffers(recurse=True)

Return an iterator over module buffers.

Parameters:: recurse (bool) – if True, then yields buffers of this module and all submodules. Otherwise, yields only buffers that are direct members of this module.
Yields:: torch.Tensor – module buffer
Return type:: Iterator[torch.Tensor]

Example:

>>> # xdoctest: +SKIP("undefined vars")
>>> for buf in model.buffers():
>>>     print(type(buf), buf.size())
<class 'torch.Tensor'> (20L,)
<class 'torch.Tensor'> (20L, 1L, 5L, 5L)

named_buffers(prefix='', recurse=True, remove_duplicate=True)

Return an iterator over module buffers, yielding both the name of the buffer as well as the buffer itself.

Parameters:

prefix (str) – prefix to prepend to all buffer names.
recurse (bool, optional) – if True, then yields buffers of this module and all submodules. Otherwise, yields only buffers that are direct members of this module. Defaults to True.
remove_duplicate (bool, optional) – whether to remove the duplicated buffers in the result. Defaults to True.

Yields:

(str, torch.Tensor) – Tuple containing the name and buffer

Return type:

Iterator[Tuple[str, torch.Tensor]]

Example:

>>> # xdoctest: +SKIP("undefined vars")
>>> for name, buf in self.named_buffers():
>>>     if name in ['running_var']:
>>>         print(buf.size())

children()

Return an iterator over immediate children modules.

Yields:: Module – a child module
Return type:: Iterator[Module]

named_children()

Return an iterator over immediate children modules, yielding both the name of the module as well as the module itself.

Yields:: (str, Module) – Tuple containing a name and child module
Return type:: Iterator[Tuple[str, Module]]

Example:

>>> # xdoctest: +SKIP("undefined vars")
>>> for name, module in model.named_children():
>>>     if name in ['conv4', 'conv5']:
>>>         print(module)

modules()

Return an iterator over all modules in the network.

Yields:: Module – a module in the network
Return type:: Iterator[Module]

Note

Duplicate modules are returned only once. In the following example, l will be returned only once.

Example:

>>> l = nn.Linear(2, 2)
>>> net = nn.Sequential(l, l)
>>> for idx, m in enumerate(net.modules()):
...     print(idx, '->', m)

0 -> Sequential(
  (0): Linear(in_features=2, out_features=2, bias=True)
  (1): Linear(in_features=2, out_features=2, bias=True)
)
1 -> Linear(in_features=2, out_features=2, bias=True)

named_modules(memo=None, prefix='', remove_duplicate=True)

Return an iterator over all modules in the network, yielding both the name of the module as well as the module itself.

Parameters:

memo (Optional[Set[Module]]) – a memo to store the set of modules already added to the result
prefix (str) – a prefix that will be added to the name of the module
remove_duplicate (bool) – whether to remove the duplicated module instances in the result or not

Yields:

(str, Module) – Tuple of name and module

Note

Duplicate modules are returned only once. In the following example, l will be returned only once.

Example:

>>> l = nn.Linear(2, 2)
>>> net = nn.Sequential(l, l)
>>> for idx, m in enumerate(net.named_modules()):
...     print(idx, '->', m)

0 -> ('', Sequential(
  (0): Linear(in_features=2, out_features=2, bias=True)
  (1): Linear(in_features=2, out_features=2, bias=True)
))
1 -> ('0', Linear(in_features=2, out_features=2, bias=True))

train(mode=True)

Set the module in training mode.

This has any effect only on certain modules. See documentations of particular modules for details of their behaviors in training/evaluation mode, if they are affected, e.g. Dropout, BatchNorm, etc.

Parameters:: mode (bool) – whether to set training mode (True) or evaluation mode (False). Default: True.
Returns:: Module – self
Return type:: T

eval()

Set the module in evaluation mode.

This has any effect only on certain modules. See documentations of particular modules for details of their behaviors in training/evaluation mode, if they are affected, e.g. Dropout, BatchNorm, etc.

This is equivalent with self.train(False).

See locally-disable-grad-doc for a comparison between .eval() and several similar mechanisms that may be confused with it.

Returns:: Module – self
Return type:: T

requires_grad_(requires_grad=True)

Change if autograd should record operations on parameters in this module.

This method sets the parameters’ requires_grad attributes in-place.

This method is helpful for freezing part of the module for finetuning or training parts of a model individually (e.g., GAN training).

See locally-disable-grad-doc for a comparison between .requires_grad_() and several similar mechanisms that may be confused with it.

Parameters:: requires_grad (bool) – whether autograd should record operations on parameters in this module. Default: True.
Returns:: Module – self
Return type:: T

zero_grad(set_to_none=True)

Reset gradients of all model parameters.

See similar function under torch.optim.Optimizer for more context.

Parameters:: set_to_none (bool) – instead of setting to zero, set the grads to None. See torch.optim.Optimizer.zero_grad() for details.
Return type:: None

share_memory()

See torch.Tensor.share_memory_().

Return type:: T

_get_name()

extra_repr()

Set the extra representation of the module.

To print customized extra information, you should re-implement this method in your own modules. Both single-line and multi-line strings are acceptable.

Return type:: str

__repr__()

__dir__()

_replicate_for_data_parallel()

compile(*args, **kwargs)

Compile this Module’s forward using torch.compile().

This Module’s __call__ method is compiled and all arguments are passed as-is to torch.compile().

See torch.compile() for details on the arguments for this function.

class medcat.components.addons.relation_extraction.llama.model.LlamaPooler(hidden_size)

Bases: torch.nn.Module

An attempt to copy the BERT pooling technique for an increase in performance.

Parameters:: hidden_size (int)

__init__(hidden_size)

Initialises the pooler with a linear layer of size:: self.model_config.hidden_size x self.model_config.hidden_size

Parameters:: hidden_size (int) – size of tensor

dense

activation

forward(hidden_states)

Parameters:: hidden_states (torch.Tensor)
Return type:: torch.Tensor

dump_patches: bool = False

_version: int = 1

This allows better BC support for load_state_dict(). In state_dict(), the version number will be saved as in the attribute _metadata of the returned state dict, and thus pickled. _metadata is a dictionary with keys that follow the naming convention of state dict. See _load_from_state_dict on how to use this information in loading.

If new parameters/buffers are added/removed from a module, this number shall be bumped, and the module’s _load_from_state_dict method can compare the version number and do appropriate changes if the state dict is from before the change.

training: bool

_parameters: Dict[str, torch.nn.parameter.Parameter | None]

_buffers: Dict[str, torch.Tensor | None]

_non_persistent_buffers_set: Set[str]

_backward_pre_hooks: Dict[int, Callable]

_backward_hooks: Dict[int, Callable]

_is_full_backward_hook: bool | None

_forward_hooks: Dict[int, Callable]

_forward_hooks_with_kwargs: Dict[int, bool]

_forward_hooks_always_called: Dict[int, bool]

_forward_pre_hooks: Dict[int, Callable]

_forward_pre_hooks_with_kwargs: Dict[int, bool]

_state_dict_hooks: Dict[int, Callable]

_load_state_dict_pre_hooks: Dict[int, Callable]

_state_dict_pre_hooks: Dict[int, Callable]

_load_state_dict_post_hooks: Dict[int, Callable]

_modules: Dict[str, Module | None]

call_super_init: bool = False

_compiled_call_impl: Callable | None = None

register_buffer(name, tensor, persistent=True)

Add a buffer to the module.

This is typically used to register a buffer that should not to be considered a model parameter. For example, BatchNorm’s running_mean is not a parameter, but is part of the module’s state. Buffers, by default, are persistent and will be saved alongside parameters. This behavior can be changed by setting persistent to False. The only difference between a persistent buffer and a non-persistent buffer is that the latter will not be a part of this module’s state_dict.

Buffers can be accessed as attributes using given names.

Parameters:

name (str) – name of the buffer. The buffer can be accessed from this module using the given name
tensor (Tensor or None) – buffer to be registered. If None, then operations that run on buffers, such as cuda, are ignored. If None, the buffer is not included in the module’s state_dict.
persistent (bool) – whether the buffer is part of this module’s state_dict.

Return type:

None

Example:

>>> # xdoctest: +SKIP("undefined vars")
>>> self.register_buffer('running_mean', torch.zeros(num_features))

register_parameter(name, param)

Add a parameter to the module.

The parameter can be accessed as an attribute using given name.

Parameters:

name (str) – name of the parameter. The parameter can be accessed from this module using the given name
param (Parameter or None) – parameter to be added to the module. If None, then operations that run on parameters, such as cuda, are ignored. If None, the parameter is not included in the module’s state_dict.

Return type:

None

add_module(name, module)

Add a child module to the current module.

The module can be accessed as an attribute using the given name.

Parameters:

name (str) – name of the child module. The child module can be accessed from this module using the given name
module (Module) – child module to be added to the module.

Return type:

None

register_module(name, module)

Alias for add_module().

Parameters:

name (str)
module (Optional[Module])

Return type:

None

get_submodule(target)

Return the submodule given by target if it exists, otherwise throw an error.

For example, let’s say you have an nn.Module A that looks like this:

A(
    (net_b): Module(
        (net_c): Module(
            (conv): Conv2d(16, 33, kernel_size=(3, 3), stride=(2, 2))
        )
        (linear): Linear(in_features=100, out_features=200, bias=True)
    )
)

(The diagram shows an nn.Module A. A has a nested submodule net_b, which itself has two submodules net_c and linear. net_c then has a submodule conv.)

To check whether or not we have the linear submodule, we would call get_submodule("net_b.linear"). To check whether we have the conv submodule, we would call get_submodule("net_b.net_c.conv").

The runtime of get_submodule is bounded by the degree of module nesting in target. A query against named_modules achieves the same result, but it is O(N) in the number of transitive modules. So, for a simple check to see if some submodule exists, get_submodule should always be used.

Parameters:: target (str) – The fully-qualified string name of the submodule to look for. (See above example for how to specify a fully-qualified string.)
Returns:: torch.nn.Module – The submodule referenced by target
Raises:: AttributeError – If the target string references an invalid path or resolves to something that is not an nn.Module
Return type:: Module

set_submodule(target, module)

Set the submodule given by target if it exists, otherwise throw an error.

For example, let’s say you have an nn.Module A that looks like this:

A(
    (net_b): Module(
        (net_c): Module(
            (conv): Conv2d(16, 33, kernel_size=(3, 3), stride=(2, 2))
        )
        (linear): Linear(in_features=100, out_features=200, bias=True)
    )
)

(The diagram shows an nn.Module A. A has a nested submodule net_b, which itself has two submodules net_c and linear. net_c then has a submodule conv.)

To overide the Conv2d with a new submodule Linear, you would call set_submodule("net_b.net_c.conv", nn.Linear(33, 16)).

Parameters:

target (str) – The fully-qualified string name of the submodule to look for. (See above example for how to specify a fully-qualified string.)
module (Module) – The module to set the submodule to.

Raises:

ValueError – If the target string is empty
AttributeError – If the target string references an invalid path or resolves to something that is not an nn.Module

Return type:

None

get_parameter(target)

Return the parameter given by target if it exists, otherwise throw an error.

See the docstring for get_submodule for a more detailed explanation of this method’s functionality as well as how to correctly specify target.

Parameters:: target (str) – The fully-qualified string name of the Parameter to look for. (See get_submodule for how to specify a fully-qualified string.)
Returns:: torch.nn.Parameter – The Parameter referenced by target
Raises:: AttributeError – If the target string references an invalid path or resolves to something that is not an nn.Parameter
Return type:: torch.nn.parameter.Parameter

get_buffer(target)

Return the buffer given by target if it exists, otherwise throw an error.

See the docstring for get_submodule for a more detailed explanation of this method’s functionality as well as how to correctly specify target.

Parameters:: target (str) – The fully-qualified string name of the buffer to look for. (See get_submodule for how to specify a fully-qualified string.)
Returns:: torch.Tensor – The buffer referenced by target
Raises:: AttributeError – If the target string references an invalid path or resolves to something that is not a buffer
Return type:: torch.Tensor

get_extra_state()

Return any extra state to include in the module’s state_dict.

Implement this and a corresponding set_extra_state() for your module if you need to store extra state. This function is called when building the module’s state_dict().

Note that extra state should be picklable to ensure working serialization of the state_dict. We only provide provide backwards compatibility guarantees for serializing Tensors; other objects may break backwards compatibility if their serialized pickled form changes.

Returns:: object – Any extra state to store in the module’s state_dict
Return type:: Any

set_extra_state(state)

Set extra state contained in the loaded state_dict.

This function is called from load_state_dict() to handle any extra state found within the state_dict. Implement this function and a corresponding get_extra_state() for your module if you need to store extra state within its state_dict.

Parameters:: state (dict) – Extra state from the state_dict
Return type:: None

_apply(fn, recurse=True)

apply(fn)

Apply fn recursively to every submodule (as returned by .children()) as well as self.

Typical use includes initializing the parameters of a model (see also nn-init-doc).

Parameters:: fn (Module -> None) – function to be applied to each submodule
Returns:: Module – self
Return type:: T

Example:

>>> @torch.no_grad()
>>> def init_weights(m):
>>>     print(m)
>>>     if type(m) == nn.Linear:
>>>         m.weight.fill_(1.0)
>>>         print(m.weight)
>>> net = nn.Sequential(nn.Linear(2, 2), nn.Linear(2, 2))
>>> net.apply(init_weights)
Linear(in_features=2, out_features=2, bias=True)
Parameter containing:
tensor([[1., 1.],
        [1., 1.]], requires_grad=True)
Linear(in_features=2, out_features=2, bias=True)
Parameter containing:
tensor([[1., 1.],
        [1., 1.]], requires_grad=True)
Sequential(
  (0): Linear(in_features=2, out_features=2, bias=True)
  (1): Linear(in_features=2, out_features=2, bias=True)
)

cuda(device=None)

Move all model parameters and buffers to the GPU.

This also makes associated parameters and buffers different objects. So it should be called before constructing optimizer if the module will live on GPU while being optimized.

Note

This method modifies the module in-place.

Parameters:: device (int, optional) – if specified, all parameters will be copied to that device
Returns:: Module – self
Return type:: T

ipu(device=None)

Move all model parameters and buffers to the IPU.

This also makes associated parameters and buffers different objects. So it should be called before constructing optimizer if the module will live on IPU while being optimized.

Note

This method modifies the module in-place.

Parameters:: device (int, optional) – if specified, all parameters will be copied to that device
Returns:: Module – self
Return type:: T

xpu(device=None)

Move all model parameters and buffers to the XPU.

This also makes associated parameters and buffers different objects. So it should be called before constructing optimizer if the module will live on XPU while being optimized.

Note

This method modifies the module in-place.

Parameters:: device (int, optional) – if specified, all parameters will be copied to that device
Returns:: Module – self
Return type:: T

mtia(device=None)

Move all model parameters and buffers to the MTIA.

This also makes associated parameters and buffers different objects. So it should be called before constructing optimizer if the module will live on MTIA while being optimized.

Note

This method modifies the module in-place.

Parameters:: device (int, optional) – if specified, all parameters will be copied to that device
Returns:: Module – self
Return type:: T

cpu()

Move all model parameters and buffers to the CPU.

Note

This method modifies the module in-place.

Returns:: Module – self
Return type:: T

type(dst_type)

Casts all parameters and buffers to dst_type.

Note

This method modifies the module in-place.

Parameters:: dst_type (type or string) – the desired type
Returns:: Module – self
Return type:: T

float()

Casts all floating point parameters and buffers to float datatype.

Note

This method modifies the module in-place.

Returns:: Module – self
Return type:: T

double()

Casts all floating point parameters and buffers to double datatype.

Note

This method modifies the module in-place.

Returns:: Module – self
Return type:: T

half()

Casts all floating point parameters and buffers to half datatype.

Note

This method modifies the module in-place.

Returns:: Module – self
Return type:: T

bfloat16()

Casts all floating point parameters and buffers to bfloat16 datatype.

Note

This method modifies the module in-place.

Returns:: Module – self
Return type:: T

to_empty(*, device, recurse=True)

Move the parameters and buffers to the specified device without copying storage.

Parameters:

device (torch.device) – The desired device of the parameters and buffers in this module.
recurse (bool) – Whether parameters and buffers of submodules should be recursively moved to the specified device.

Returns:

Module – self

Return type:

T

to(device: torch._prims_common.DeviceLikeType | None = ..., dtype: Module.to.dtype | None = ..., non_blocking: bool = ...) → typing_extensions.Self

to(dtype: Module.to.dtype, non_blocking: bool = ...) → typing_extensions.Self

to(tensor: torch.Tensor, non_blocking: bool = ...) → typing_extensions.Self

Move and/or cast the parameters and buffers.

This can be called as

to(device=None, dtype=None, non_blocking=False)

to(dtype, non_blocking=False)

to(tensor, non_blocking=False)

to(memory_format=torch.channels_last)

Its signature is similar to torch.Tensor.to(), but only accepts floating point or complex dtypes. In addition, this method will only cast the floating point or complex parameters and buffers to dtype (if given). The integral parameters and buffers will be moved device, if that is given, but with dtypes unchanged. When non_blocking is set, it tries to convert/move asynchronously with respect to the host if possible, e.g., moving CPU Tensors with pinned memory to CUDA devices.

See below for examples.

Note

This method modifies the module in-place.

Parameters:

device (torch.device) – the desired device of the parameters and buffers in this module
dtype (torch.dtype) – the desired floating point or complex dtype of the parameters and buffers in this module
tensor (torch.Tensor) – Tensor whose dtype and device are the desired dtype and device for all parameters and buffers in this module
memory_format (torch.memory_format) – the desired memory format for 4D parameters and buffers in this module (keyword only argument)

Returns:

Module – self

Examples:

>>> # xdoctest: +IGNORE_WANT("non-deterministic")
>>> linear = nn.Linear(2, 2)
>>> linear.weight
Parameter containing:
tensor([[ 0.1913, -0.3420],
        [-0.5113, -0.2325]])
>>> linear.to(torch.double)
Linear(in_features=2, out_features=2, bias=True)
>>> linear.weight
Parameter containing:
tensor([[ 0.1913, -0.3420],
        [-0.5113, -0.2325]], dtype=torch.float64)
>>> # xdoctest: +REQUIRES(env:TORCH_DOCTEST_CUDA1)
>>> gpu1 = torch.device("cuda:1")
>>> linear.to(gpu1, dtype=torch.half, non_blocking=True)
Linear(in_features=2, out_features=2, bias=True)
>>> linear.weight
Parameter containing:
tensor([[ 0.1914, -0.3420],
        [-0.5112, -0.2324]], dtype=torch.float16, device='cuda:1')
>>> cpu = torch.device("cpu")
>>> linear.to(cpu)
Linear(in_features=2, out_features=2, bias=True)
>>> linear.weight
Parameter containing:
tensor([[ 0.1914, -0.3420],
        [-0.5112, -0.2324]], dtype=torch.float16)

>>> linear = nn.Linear(2, 2, bias=None).to(torch.cdouble)
>>> linear.weight
Parameter containing:
tensor([[ 0.3741+0.j,  0.2382+0.j],
        [ 0.5593+0.j, -0.4443+0.j]], dtype=torch.complex128)
>>> linear(torch.ones(3, 2, dtype=torch.cdouble))
tensor([[0.6122+0.j, 0.1150+0.j],
        [0.6122+0.j, 0.1150+0.j],
        [0.6122+0.j, 0.1150+0.j]], dtype=torch.complex128)

register_full_backward_pre_hook(hook, prepend=False)

Register a backward pre-hook on the module.

The hook will be called every time the gradients for the module are computed. The hook should have the following signature:

hook(module, grad_output) -> tuple[Tensor] or None

The grad_output is a tuple. The hook should not modify its arguments, but it can optionally return a new gradient with respect to the output that will be used in place of grad_output in subsequent computations. Entries in grad_output will be None for all non-Tensor arguments.

For technical reasons, when this hook is applied to a Module, its forward function will receive a view of each Tensor passed to the Module. Similarly the caller will receive a view of each Tensor returned by the Module’s forward function.

Warning

Modifying inputs inplace is not allowed when using backward hooks and will raise an error.

Parameters:

hook (Callable) – The user-defined hook to be registered.
prepend (bool) – If true, the provided hook will be fired before all existing backward_pre hooks on this torch.nn.modules.Module. Otherwise, the provided hook will be fired after all existing backward_pre hooks on this torch.nn.modules.Module. Note that global backward_pre hooks registered with register_module_full_backward_pre_hook() will fire before all hooks registered by this method.

Returns:

:class:`torch.utils.hooks.RemovableHandle` – a handle that can be used to remove the added hook by calling handle.remove()

Return type:

torch.utils.hooks.RemovableHandle

register_backward_hook(hook)

Register a backward hook on the module.

This function is deprecated in favor of register_full_backward_hook() and the behavior of this function will change in future versions.

Returns:: :class:`torch.utils.hooks.RemovableHandle` – a handle that can be used to remove the added hook by calling handle.remove()
Parameters:: hook (Callable[[Module, _grad_t, _grad_t], Union[None, _grad_t]])
Return type:: torch.utils.hooks.RemovableHandle

register_full_backward_hook(hook, prepend=False)

Register a backward hook on the module.

The hook will be called every time the gradients with respect to a module are computed, i.e. the hook will execute if and only if the gradients with respect to module outputs are computed. The hook should have the following signature:

hook(module, grad_input, grad_output) -> tuple(Tensor) or None

The grad_input and grad_output are tuples that contain the gradients with respect to the inputs and outputs respectively. The hook should not modify its arguments, but it can optionally return a new gradient with respect to the input that will be used in place of grad_input in subsequent computations. grad_input will only correspond to the inputs given as positional arguments and all kwarg arguments are ignored. Entries in grad_input and grad_output will be None for all non-Tensor arguments.

For technical reasons, when this hook is applied to a Module, its forward function will receive a view of each Tensor passed to the Module. Similarly the caller will receive a view of each Tensor returned by the Module’s forward function.

Warning

Modifying inputs or outputs inplace is not allowed when using backward hooks and will raise an error.

Parameters:

hook (Callable) – The user-defined hook to be registered.
prepend (bool) – If true, the provided hook will be fired before all existing backward hooks on this torch.nn.modules.Module. Otherwise, the provided hook will be fired after all existing backward hooks on this torch.nn.modules.Module. Note that global backward hooks registered with register_module_full_backward_hook() will fire before all hooks registered by this method.

Returns:

:class:`torch.utils.hooks.RemovableHandle` – a handle that can be used to remove the added hook by calling handle.remove()

Return type:

torch.utils.hooks.RemovableHandle

_get_backward_hooks()

Return the backward hooks for use in the call function.

It returns two lists, one with the full backward hooks and one with the non-full backward hooks.

_get_backward_pre_hooks()

_maybe_warn_non_full_backward_hook(inputs, result, grad_fn)

register_forward_pre_hook(hook, *, prepend=False, with_kwargs=False)

Register a forward pre-hook on the module.

The hook will be called every time before forward() is invoked.

If with_kwargs is false or not specified, the input contains only the positional arguments given to the module. Keyword arguments won’t be passed to the hooks and only to the forward. The hook can modify the input. User can either return a tuple or a single modified value in the hook. We will wrap the value into a tuple if a single value is returned (unless that value is already a tuple). The hook should have the following signature:

hook(module, args) -> None or modified input

If with_kwargs is true, the forward pre-hook will be passed the kwargs given to the forward function. And if the hook modifies the input, both the args and kwargs should be returned. The hook should have the following signature:

hook(module, args, kwargs) -> None or a tuple of modified input and kwargs

Parameters:

hook (Callable) – The user defined hook to be registered.
prepend (bool) – If true, the provided hook will be fired before all existing forward_pre hooks on this torch.nn.modules.Module. Otherwise, the provided hook will be fired after all existing forward_pre hooks on this torch.nn.modules.Module. Note that global forward_pre hooks registered with register_module_forward_pre_hook() will fire before all hooks registered by this method. Default: False
with_kwargs (bool) – If true, the hook will be passed the kwargs given to the forward function. Default: False

Returns:

:class:`torch.utils.hooks.RemovableHandle` – a handle that can be used to remove the added hook by calling handle.remove()

Return type:

torch.utils.hooks.RemovableHandle

register_forward_hook(hook, *, prepend=False, with_kwargs=False, always_call=False)

Register a forward hook on the module.

The hook will be called every time after forward() has computed an output.

If with_kwargs is False or not specified, the input contains only the positional arguments given to the module. Keyword arguments won’t be passed to the hooks and only to the forward. The hook can modify the output. It can modify the input inplace but it will not have effect on forward since this is called after forward() is called. The hook should have the following signature:

hook(module, args, output) -> None or modified output

If with_kwargs is True, the forward hook will be passed the kwargs given to the forward function and be expected to return the output possibly modified. The hook should have the following signature:

hook(module, args, kwargs, output) -> None or modified output

Parameters:

hook (Callable) – The user defined hook to be registered.
prepend (bool) – If True, the provided hook will be fired before all existing forward hooks on this torch.nn.modules.Module. Otherwise, the provided hook will be fired after all existing forward hooks on this torch.nn.modules.Module. Note that global forward hooks registered with register_module_forward_hook() will fire before all hooks registered by this method. Default: False
with_kwargs (bool) – If True, the hook will be passed the kwargs given to the forward function. Default: False
always_call (bool) – If True the hook will be run regardless of whether an exception is raised while calling the Module. Default: False

Returns:

:class:`torch.utils.hooks.RemovableHandle` – a handle that can be used to remove the added hook by calling handle.remove()

Return type:

torch.utils.hooks.RemovableHandle

_slow_forward(*input, **kwargs)

_wrapped_call_impl(*args, **kwargs)

_call_impl(*args, **kwargs)

__call__: Callable[Ellipsis, Any]

__getstate__()

__setstate__(state)

__getattr__(name)

Parameters:: name (str)
Return type:: Any

__setattr__(name, value)

Parameters:

name (str)
value (Union[torch.Tensor, Module])

Return type:

None

__delattr__(name)

_register_state_dict_hook(hook)

Register a post-hook for the state_dict() method.

It should have the following signature::: hook(module, state_dict, prefix, local_metadata) -> None or state_dict

The registered hooks can modify the state_dict inplace or return a new one. If a new state_dict is returned, it will only be respected if it is the root module that state_dict() is called from.

register_state_dict_post_hook(hook)

Register a post-hook for the state_dict() method.

It should have the following signature::: hook(module, state_dict, prefix, local_metadata) -> None

The registered hooks can modify the state_dict inplace.

register_state_dict_pre_hook(hook)

Register a pre-hook for the state_dict() method.

It should have the following signature::: hook(module, prefix, keep_vars) -> None

The registered hooks can be used to perform pre-processing before the state_dict call is made.

_save_to_state_dict(destination, prefix, keep_vars)

Save module state to the destination dictionary.

The destination dictionary will contain the state of the module, but not its descendants. This is called on every submodule in state_dict().

In rare cases, subclasses can achieve class-specific behavior by overriding this method with custom logic.

Parameters:

destination (dict) – a dict where state will be stored
prefix (str) – the prefix for parameters and buffers used in this module

T_destination

state_dict(*, destination: T_destination, prefix: str = ..., keep_vars: bool = ...) → T_destination

state_dict(*, prefix: str = ..., keep_vars: bool = ...) → Dict[str, Any]

Return a dictionary containing references to the whole state of the module.

Both parameters and persistent buffers (e.g. running averages) are included. Keys are corresponding parameter and buffer names. Parameters and buffers set to None are not included.

Note

The returned object is a shallow copy. It contains references to the module’s parameters and buffers.

Warning

Currently state_dict() also accepts positional arguments for destination, prefix and keep_vars in order. However, this is being deprecated and keyword arguments will be enforced in future releases.

Warning

Please avoid the use of argument destination as it is not designed for end-users.

Parameters:

destination (dict, optional) – If provided, the state of module will be updated into the dict and the same object is returned. Otherwise, an OrderedDict will be created and returned. Default: None.
prefix (str, optional) – a prefix added to parameter and buffer names to compose the keys in state_dict. Default: ''.
keep_vars (bool, optional) – by default the Tensor s returned in the state dict are detached from autograd. If it’s set to True, detaching will not be performed. Default: False.

Returns:

dict – a dictionary containing a whole state of the module

Example:

>>> # xdoctest: +SKIP("undefined vars")
>>> module.state_dict().keys()
['bias', 'weight']

_register_load_state_dict_pre_hook(hook, with_module=False)

See register_load_state_dict_pre_hook() for details.

A subtle difference is that if with_module is set to False, then the hook will not take the module as the first argument whereas register_load_state_dict_pre_hook() always takes the module as the first argument.

Parameters:

hook (Callable) – Callable hook that will be invoked before loading the state dict.
with_module (bool, optional) – Whether or not to pass the module instance to the hook as the first parameter.

register_load_state_dict_pre_hook(hook)

Register a pre-hook to be run before module’s load_state_dict() is called.

It should have the following signature::: hook(module, state_dict, prefix, local_metadata, strict, missing_keys, unexpected_keys, error_msgs) -> None # noqa: B950

Parameters:: hook (Callable) – Callable hook that will be invoked before loading the state dict.

register_load_state_dict_post_hook(hook)

Register a post-hook to be run after module’s load_state_dict() is called.

It should have the following signature::: hook(module, incompatible_keys) -> None

The module argument is the current module that this hook is registered on, and the incompatible_keys argument is a NamedTuple consisting of attributes missing_keys and unexpected_keys. missing_keys is a list of str containing the missing keys and unexpected_keys is a list of str containing the unexpected keys.

The given incompatible_keys can be modified inplace if needed.

Note that the checks performed when calling load_state_dict() with strict=True are affected by modifications the hook makes to missing_keys or unexpected_keys, as expected. Additions to either set of keys will result in an error being thrown when strict=True, and clearing out both missing and unexpected keys will avoid an error.

Returns:: :class:`torch.utils.hooks.RemovableHandle` – a handle that can be used to remove the added hook by calling handle.remove()

_load_from_state_dict(state_dict, prefix, local_metadata, strict, missing_keys, unexpected_keys, error_msgs)

Copy parameters and buffers from state_dict into only this module, but not its descendants.

This is called on every submodule in load_state_dict(). Metadata saved for this module in input state_dict is provided as local_metadata. For state dicts without metadata, local_metadata is empty. Subclasses can achieve class-specific backward compatible loading using the version number at local_metadata.get(“version”, None). Additionally, local_metadata can also contain the key assign_to_params_buffers that indicates whether keys should be assigned their corresponding tensor in the state_dict.

Note

state_dict is not the same object as the input state_dict to load_state_dict(). So it can be modified.

Parameters:

state_dict (dict) – a dict containing parameters and persistent buffers.
prefix (str) – the prefix for parameters and buffers used in this module
local_metadata (dict) – a dict containing the metadata for this module. See
strict (bool) – whether to strictly enforce that the keys in state_dict with prefix match the names of parameters and buffers in this module
missing_keys (list of str) – if strict=True, add missing keys to this list
unexpected_keys (list of str) – if strict=True, add unexpected keys to this list
error_msgs (list of str) – error messages should be added to this list, and will be reported together in load_state_dict()

load_state_dict(state_dict, strict=True, assign=False)

Copy parameters and buffers from state_dict into this module and its descendants.

If strict is True, then the keys of state_dict must exactly match the keys returned by this module’s state_dict() function.

Warning

If assign is True the optimizer must be created after the call to load_state_dict unless get_swap_module_params_on_conversion() is True.

Parameters:

state_dict (dict) – a dict containing parameters and persistent buffers.
strict (bool, optional) – whether to strictly enforce that the keys in state_dict match the keys returned by this module’s state_dict() function. Default: True
assign (bool, optional) – When False, the properties of the tensors in the current module are preserved while when True, the properties of the Tensors in the state dict are preserved. The only exception is the requires_grad field of Default: ``False`

Returns:

``NamedTuple`` with ``missing_keys`` and ``unexpected_keys`` fields –

missing_keys is a list of str containing any keys that are expected
by this module but missing from the provided state_dict.
unexpected_keys is a list of str containing the keys that are not
expected by this module but present in the provided state_dict.

Note

If a parameter or buffer is registered as None and its corresponding key exists in state_dict, load_state_dict() will raise a RuntimeError.

_named_members(get_members_fn, prefix='', recurse=True, remove_duplicate=True)

Help yield various names + members of modules.

Parameters:: remove_duplicate (bool)

parameters(recurse=True)

Return an iterator over module parameters.

This is typically passed to an optimizer.

Parameters:: recurse (bool) – if True, then yields parameters of this module and all submodules. Otherwise, yields only parameters that are direct members of this module.
Yields:: Parameter – module parameter
Return type:: Iterator[torch.nn.parameter.Parameter]

Example:

>>> # xdoctest: +SKIP("undefined vars")
>>> for param in model.parameters():
>>>     print(type(param), param.size())
<class 'torch.Tensor'> (20L,)
<class 'torch.Tensor'> (20L, 1L, 5L, 5L)

named_parameters(prefix='', recurse=True, remove_duplicate=True)

Return an iterator over module parameters, yielding both the name of the parameter as well as the parameter itself.

Parameters:

prefix (str) – prefix to prepend to all parameter names.
recurse (bool) – if True, then yields parameters of this module and all submodules. Otherwise, yields only parameters that are direct members of this module.
remove_duplicate (bool, optional) – whether to remove the duplicated parameters in the result. Defaults to True.

Yields:

(str, Parameter) – Tuple containing the name and parameter

Return type:

Iterator[Tuple[str, torch.nn.parameter.Parameter]]

Example:

>>> # xdoctest: +SKIP("undefined vars")
>>> for name, param in self.named_parameters():
>>>     if name in ['bias']:
>>>         print(param.size())

buffers(recurse=True)

Return an iterator over module buffers.

Parameters:: recurse (bool) – if True, then yields buffers of this module and all submodules. Otherwise, yields only buffers that are direct members of this module.
Yields:: torch.Tensor – module buffer
Return type:: Iterator[torch.Tensor]

Example:

>>> # xdoctest: +SKIP("undefined vars")
>>> for buf in model.buffers():
>>>     print(type(buf), buf.size())
<class 'torch.Tensor'> (20L,)
<class 'torch.Tensor'> (20L, 1L, 5L, 5L)

named_buffers(prefix='', recurse=True, remove_duplicate=True)

Return an iterator over module buffers, yielding both the name of the buffer as well as the buffer itself.

Parameters:

prefix (str) – prefix to prepend to all buffer names.
recurse (bool, optional) – if True, then yields buffers of this module and all submodules. Otherwise, yields only buffers that are direct members of this module. Defaults to True.
remove_duplicate (bool, optional) – whether to remove the duplicated buffers in the result. Defaults to True.

Yields:

(str, torch.Tensor) – Tuple containing the name and buffer

Return type:

Iterator[Tuple[str, torch.Tensor]]

Example:

>>> # xdoctest: +SKIP("undefined vars")
>>> for name, buf in self.named_buffers():
>>>     if name in ['running_var']:
>>>         print(buf.size())

children()

Return an iterator over immediate children modules.

Yields:: Module – a child module
Return type:: Iterator[Module]

named_children()

Return an iterator over immediate children modules, yielding both the name of the module as well as the module itself.

Yields:: (str, Module) – Tuple containing a name and child module
Return type:: Iterator[Tuple[str, Module]]

Example:

>>> # xdoctest: +SKIP("undefined vars")
>>> for name, module in model.named_children():
>>>     if name in ['conv4', 'conv5']:
>>>         print(module)

modules()

Return an iterator over all modules in the network.

Yields:: Module – a module in the network
Return type:: Iterator[Module]

Note

Duplicate modules are returned only once. In the following example, l will be returned only once.

Example:

>>> l = nn.Linear(2, 2)
>>> net = nn.Sequential(l, l)
>>> for idx, m in enumerate(net.modules()):
...     print(idx, '->', m)

0 -> Sequential(
  (0): Linear(in_features=2, out_features=2, bias=True)
  (1): Linear(in_features=2, out_features=2, bias=True)
)
1 -> Linear(in_features=2, out_features=2, bias=True)

named_modules(memo=None, prefix='', remove_duplicate=True)

Return an iterator over all modules in the network, yielding both the name of the module as well as the module itself.

Parameters:

memo (Optional[Set[Module]]) – a memo to store the set of modules already added to the result
prefix (str) – a prefix that will be added to the name of the module
remove_duplicate (bool) – whether to remove the duplicated module instances in the result or not

Yields:

(str, Module) – Tuple of name and module

Note

Duplicate modules are returned only once. In the following example, l will be returned only once.

Example:

>>> l = nn.Linear(2, 2)
>>> net = nn.Sequential(l, l)
>>> for idx, m in enumerate(net.named_modules()):
...     print(idx, '->', m)

0 -> ('', Sequential(
  (0): Linear(in_features=2, out_features=2, bias=True)
  (1): Linear(in_features=2, out_features=2, bias=True)
))
1 -> ('0', Linear(in_features=2, out_features=2, bias=True))

train(mode=True)

Set the module in training mode.

This has any effect only on certain modules. See documentations of particular modules for details of their behaviors in training/evaluation mode, if they are affected, e.g. Dropout, BatchNorm, etc.

Parameters:: mode (bool) – whether to set training mode (True) or evaluation mode (False). Default: True.
Returns:: Module – self
Return type:: T

eval()

Set the module in evaluation mode.

This has any effect only on certain modules. See documentations of particular modules for details of their behaviors in training/evaluation mode, if they are affected, e.g. Dropout, BatchNorm, etc.

This is equivalent with self.train(False).

See locally-disable-grad-doc for a comparison between .eval() and several similar mechanisms that may be confused with it.

Returns:: Module – self
Return type:: T

requires_grad_(requires_grad=True)

Change if autograd should record operations on parameters in this module.

This method sets the parameters’ requires_grad attributes in-place.

This method is helpful for freezing part of the module for finetuning or training parts of a model individually (e.g., GAN training).

See locally-disable-grad-doc for a comparison between .requires_grad_() and several similar mechanisms that may be confused with it.

Parameters:: requires_grad (bool) – whether autograd should record operations on parameters in this module. Default: True.
Returns:: Module – self
Return type:: T

zero_grad(set_to_none=True)

Reset gradients of all model parameters.

See similar function under torch.optim.Optimizer for more context.

Parameters:: set_to_none (bool) – instead of setting to zero, set the grads to None. See torch.optim.Optimizer.zero_grad() for details.
Return type:: None

share_memory()

See torch.Tensor.share_memory_().

Return type:: T

_get_name()

extra_repr()

Set the extra representation of the module.

To print customized extra information, you should re-implement this method in your own modules. Both single-line and multi-line strings are acceptable.

Return type:: str

__repr__()

__dir__()

_replicate_for_data_parallel()

compile(*args, **kwargs)

Compile this Module’s forward using torch.compile().

This Module’s __call__ method is compiled and all arguments are passed as-is to torch.compile().

See torch.compile() for details on the arguments for this function.