Struct BertForSequenceClassification 

pub struct BertForSequenceClassification {
    pub bert: Bert,
    pub dropout: Dropout,
    pub classifier: Linear,
    pub num_labels: usize,
}

BERT for sequence classification.

Fields

bert: Bert

Base BERT model

dropout: Dropout

Dropout

classifier: Linear

Classification head

num_labels: usize

Number of labels

Implementations

impl BertForSequenceClassification

pub fn new(config: &BertConfig, num_labels: usize) -> Self

Creates a new BERT for sequence classification.

pub fn forward_classification( &self, input_ids: &Tensor<u32>, ) -> LLMResult<Variable>

Forward pass for classification.

Errors

Returns an error if the BERT model does not have a pooler configured.

Trait Implementations

impl Debug for BertForSequenceClassification

fn fmt(&self, f: &mut Formatter<'_>) -> Result

Formats the value using the given formatter.

impl Module for BertForSequenceClassification

fn forward(&self, input: &Variable) -> Variable

Performs the forward pass.

fn parameters(&self) -> Vec<Parameter>

Returns all parameters of this module.

fn train(&mut self)

Sets the module to training mode.

fn eval(&mut self)

Sets the module to evaluation mode.

fn named_parameters(&self) -> HashMap<String, Parameter>

Returns named parameters of this module.

fn num_parameters(&self) -> usize

Returns the number of trainable parameters.

fn set_training(&mut self, _training: bool)

Sets the training mode.

fn is_training(&self) -> bool

Returns whether the module is in training mode.

fn zero_grad(&self)

Zeros all gradients of parameters.

fn name(&self) -> &'static str

Returns the module name for debugging.