Logo Sentence Transformers

Getting Started

  • Installation
  • Quickstart

Sentence Transformer

  • Usage
    • Computing Embeddings
    • Semantic Textual Similarity
    • Semantic Search
    • Retrieve & Re-Rank
    • Clustering
    • Paraphrase Mining
    • Translated Sentence Mining
    • Image Search
    • Embedding Quantization
    • Speeding up Inference
    • Creating Custom Models
  • Pretrained Models
    • Original Models
    • Semantic Search Models
    • Multilingual Models
    • Image & Text-Models
    • INSTRUCTOR models
    • Scientific Similarity Models
  • Training Overview
    • Why Finetune?
    • Training Components
    • Dataset
    • Loss Function
    • Training Arguments
    • Evaluator
    • Trainer
    • Multi-Dataset Training
    • Deprecated Training
    • Best Base Embedding Models
  • Dataset Overview
    • Datasets on the Hugging Face Hub
    • Pre-existing Datasets
  • Loss Overview
    • Loss modifiers
    • Distillation
    • Commonly used Loss Functions
    • Custom Loss Functions
  • Training Examples
    • Semantic Textual Similarity
    • Natural Language Inference
    • Paraphrase Data
    • Quora Duplicate Questions
    • MS MARCO
    • Matryoshka Embeddings
    • Adaptive Layers
    • Multilingual Models
    • Model Distillation
    • Augmented SBERT
    • Training with Prompts
    • Unsupervised Learning
    • Domain Adaptation
    • Hyperparameter Optimization
    • Distributed Training

Cross Encoder

  • Usage
    • Retrieve & Re-Rank
  • Pretrained Models
    • MS MARCO
    • SQuAD (QNLI)
    • STSbenchmark
    • Quora Duplicate Questions
    • NLI
    • Community Models
  • Training Overview
  • Training Examples
    • MS MARCO

Package Reference

  • Sentence Transformer
    • SentenceTransformer
      • SentenceTransformer
      • SentenceTransformerModelCardData
      • SimilarityFunction
    • Trainer
      • SentenceTransformerTrainer
    • Training Arguments
      • SentenceTransformerTrainingArguments
    • Losses
      • BatchAllTripletLoss
      • BatchHardSoftMarginTripletLoss
      • BatchHardTripletLoss
      • BatchSemiHardTripletLoss
      • ContrastiveLoss
      • OnlineContrastiveLoss
      • ContrastiveTensionLoss
      • ContrastiveTensionLossInBatchNegatives
      • CoSENTLoss
      • AnglELoss
      • CosineSimilarityLoss
      • DenoisingAutoEncoderLoss
      • GISTEmbedLoss
      • CachedGISTEmbedLoss
      • MSELoss
      • MarginMSELoss
      • MatryoshkaLoss
      • Matryoshka2dLoss
      • AdaptiveLayerLoss
      • MegaBatchMarginLoss
      • MultipleNegativesRankingLoss
      • CachedMultipleNegativesRankingLoss
      • MultipleNegativesSymmetricRankingLoss
      • CachedMultipleNegativesSymmetricRankingLoss
      • SoftmaxLoss
      • TripletLoss
    • Samplers
      • BatchSamplers
      • MultiDatasetBatchSamplers
    • Evaluation
      • BinaryClassificationEvaluator
      • EmbeddingSimilarityEvaluator
      • InformationRetrievalEvaluator
      • NanoBEIREvaluator
      • MSEEvaluator
      • ParaphraseMiningEvaluator
      • RerankingEvaluator
      • SentenceEvaluator
      • SequentialEvaluator
      • TranslationEvaluator
      • TripletEvaluator
    • Datasets
      • ParallelSentencesDataset
      • SentenceLabelDataset
      • DenoisingAutoEncoderDataset
      • NoDuplicatesDataLoader
    • Models
      • Main Classes
      • Further Classes
    • quantization
  • Cross Encoder
    • CrossEncoder
      • CrossEncoder
      • Training Inputs
    • Evaluation
      • CEBinaryAccuracyEvaluator
      • CEBinaryClassificationEvaluator
      • CECorrelationEvaluator
      • CEF1Evaluator
      • CESoftmaxAccuracyEvaluator
      • CERerankingEvaluator
  • util
    • Helper Functions
    • Model Optimization
    • Similarity Metrics
Sentence Transformers
  • »
  • Search

© Copyright 2024

Built with Sphinx using a theme provided by Read the Docs.