Given a list of (anchor, positive) pairs or (anchor, positive, negative) triplets, this loss optimizes the following: * Given an anc

Computes the Cross Entropy Loss for a CrossEncoder model. This loss is used to train a model to predict the correct class label for a

Initialize a lambda weight for PListMLE loss. Args: rank_discount_fn: Function that computes a discount for each rank po

Boosted version of :class:`~sentence_transformers.cross_encoder.losses.MultipleNegativesRankingLoss` that caches the gradients of the

ListNet loss for learning to rank. This loss function implements the ListNet ranking algorithm which uses a list-wise approach to lea

Computes the MSE loss between the predicted margin ``sim(Query, Pos) - sim(Query, Neg)`` and the gold margin ``gold_sim(Query, Pos) -

RankNet loss implementation for learning to rank. This loss function implements the RankNet algorithm, which learns a ranking functio

r""" ADR-MSE (Approx Discounted Rank Mean Squared Error) listwise ranking loss for cross-encoders. This loss directly minimizes the er

Computes the Binary Cross Entropy Loss for a CrossEncoder model. This loss is used to train a model to predict a high logit for posit

Callback that updates the query_regularizer_weight and document_regularizer_weight parameters of SpladeLoss based on a schedule.

FlopsLoss implements a regularization technique to promote sparsity in sparse encoder models. It calculates the squared L2 norm of th

Given a dataset of (anchor, positive) pairs, (anchor, positive, negative) triplets, or (anchor, positive, negative_1, ..., negative_n)

Cached version of :class:`SpladeLoss` that uses the GradCache technique to allow for much larger effective batch sizes without additi

This class implements AnglE (Angle Optimized). This is a modification of :class:`SparseCoSENTLoss`, designed to address the following

Compute the MSE loss between the predicted margin ``sim(Query, Pos) - sim(Query, Neg)`` and the gold margin ``gold_sim(Query, Pos) -

This class implements triplet loss. Given a triplet of (anchor, positive, negative), the loss minimizes the distance between anchor a

SparseCosineSimilarityLoss expects that the inputs consists of a pair of inputs (e.g., texts) and a float label. It computes the vect

SpladeLoss implements the loss function for the SPLADE (Sparse Lexical and Expansion) model, which combines a main loss function with

Computes the MSE loss between the computed embedding and a target embedding. This loss is used when extending embeddings to new langu

Compute the KL divergence loss between probability distributions derived from student and teacher models' similarity scores. By defau

This class implements CoSENT (Cosine Sentence). It expects that each of the inputs consists of a pair of inputs (e.g., texts) and a f

CSRReconstructionLoss implements the reconstruction loss component for Contrastive Sparse Representation (CSR) models. This loss ens

This sampler creates batches such that each batch contains samples where the values are unique, even across columns. This is useful w

r""" This model allows creating flexible SentenceTransformer models that dynamically route inputs to different processing modules base

Iterate over the remaining non-yielded indices. For each index, check if the sample values are already in the batch. If not, add the

Yield batches from the underlying datasets in a specific order.