kazu.training.modelling¶

Functions

multi_label_forward(model, outputs, ...[, ...])

Classes

`BertForMultiLabelTokenClassification`
`DebertaForMultiLabelTokenClassification`
`DistilBertForMultiLabelTokenClassification`

class kazu.training.modelling.BertForMultiLabelTokenClassification[source]¶

Bases: BertForTokenClassification

__init__(config)[source]¶

Initialize internal Module state, shared by both nn.Module and ScriptModule.

Parameters:: config (PretrainedConfig)
Return type:: None

forward(input_ids=None, attention_mask=None, token_type_ids=None, position_ids=None, head_mask=None, inputs_embeds=None, labels=None, output_attentions=None, output_hidden_states=None, return_dict=None)[source]¶

Parameters:

input_ids (Tensor | None)
attention_mask (Tensor | None)
token_type_ids (Tensor | None)
position_ids (Tensor | None)
head_mask (Tensor | None)
inputs_embeds (Tensor | None)
labels (Tensor | None)
output_attentions (bool | None)
output_hidden_states (bool | None)
return_dict (bool | None)

Returns:

Return type:

TokenClassifierOutput | Tuple[Tensor, …]

class kazu.training.modelling.DebertaForMultiLabelTokenClassification[source]¶

Bases: DebertaV2ForTokenClassification

__init__(config)[source]¶

Initialize internal Module state, shared by both nn.Module and ScriptModule.

Parameters:: config (PretrainedConfig)
Return type:: None

forward(input_ids=None, attention_mask=None, token_type_ids=None, position_ids=None, inputs_embeds=None, labels=None, output_attentions=None, output_hidden_states=None, return_dict=None)[source]¶

Parameters:

input_ids (Tensor | None)
attention_mask (Tensor | None)
token_type_ids (Tensor | None)
position_ids (Tensor | None)
inputs_embeds (Tensor | None)
labels (Tensor | None)
output_attentions (bool | None)
output_hidden_states (bool | None)
return_dict (bool | None)

Returns:

Return type:

Tuple | TokenClassifierOutput

class kazu.training.modelling.DistilBertForMultiLabelTokenClassification[source]¶

Bases: DistilBertForTokenClassification

__init__(config)[source]¶

Initialize internal Module state, shared by both nn.Module and ScriptModule.

Parameters:: config (PretrainedConfig)
Return type:: None

forward(input_ids=None, attention_mask=None, head_mask=None, inputs_embeds=None, labels=None, output_attentions=None, output_hidden_states=None, return_dict=None)[source]¶

Parameters:

input_ids (Tensor | None)
attention_mask (Tensor | None)
head_mask (Tensor | None)
inputs_embeds (Tensor | None)
labels (LongTensor | None)
output_attentions (bool | None)
output_hidden_states (bool | None)
return_dict (bool | None)

Returns:

Return type:

TokenClassifierOutput | Tuple[Tensor, …]

kazu.training.modelling.multi_label_forward(model, outputs, return_dict, device, ignore_index, labels=None)[source]¶

Parameters:

model (Module)
outputs (BaseModelOutput)
return_dict (bool)
device (device)
ignore_index (int)
labels (Tensor | None)

Return type:

TokenClassifierOutput | Tuple[Tensor, …]