RoFormerForSequenceClassification

class lucid.models.RoFormerForSequenceClassification(config: RoFormerConfig, num_labels: int = 2)

The RoFormerForSequenceClassification class applies a classification head to pooled RoFormer representations.

Class Signature

class RoFormerForSequenceClassification(config: RoFormerConfig, num_labels: int = 2)

Parameters

• config (RoFormerConfig): RoFormer configuration with pooling enabled.

• num_labels (int, optional): Number of target classes. Default is 2.

Methods

RoFormerForSequenceClassification.forward(input_ids: LongTensor | None = None, attention_mask: Tensor | None = None, token_type_ids: LongTensor | None = None, position_ids: LongTensor | None = None, inputs_embeds: FloatTensor | None = None) → Tensor

RoFormerForSequenceClassification.get_loss(labels: Tensor, input_ids: LongTensor | None = None, attention_mask: Tensor | None = None, token_type_ids: LongTensor | None = None, position_ids: LongTensor | None = None, inputs_embeds: FloatTensor | None = None, *, reduction: str | None = 'mean') → Tensor

RoFormerForSequenceClassification.predict_labels(input_ids: LongTensor | None = None, attention_mask: Tensor | None = None, token_type_ids: LongTensor | None = None, position_ids: LongTensor | None = None, inputs_embeds: FloatTensor | None = None) → Tensor

RoFormerForSequenceClassification.predict_proba(input_ids: LongTensor | None = None, attention_mask: Tensor | None = None, token_type_ids: LongTensor | None = None, position_ids: LongTensor | None = None, inputs_embeds: FloatTensor | None = None) → Tensor

RoFormerForSequenceClassification.get_accuracy(labels: Tensor, input_ids: LongTensor | None = None, attention_mask: Tensor | None = None, token_type_ids: LongTensor | None = None, position_ids: LongTensor | None = None, inputs_embeds: FloatTensor | None = None) → Tensor

RoFormerForSequenceClassification.get_loss_from_text(tokenizer: BERTTokenizerFast, text_a: str, text_b: str | None = None, labels: int | Tensor = 0, *, device: Literal['cpu', 'gpu'] = 'cpu', reduction: str | None = 'mean') → Tensor

RoFormerForSequenceClassification.predict_labels_from_text(tokenizer: BERTTokenizerFast, text_a: str, text_b: str | None = None, *, device: Literal['cpu', 'gpu'] = 'cpu') → Tensor

RoFormerForSequenceClassification.predict_proba_from_text(tokenizer: BERTTokenizerFast, text_a: str, text_b: str | None = None, *, device: Literal['cpu', 'gpu'] = 'cpu') → Tensor

Examples

>>> import lucid.models as models
>>> config = models.RoFormerConfig.base(vocab_size=50000)
>>> model = models.RoFormerForSequenceClassification(config, num_labels=3)
>>> print(model)
RoFormerForSequenceClassification(...)