MCPcopy Create free account

hub / github.com/huggingface/sentence-transformers / functions

Functions4,575 in github.com/huggingface/sentence-transformers

↓ 1 callersMethodcompute_loss_from_embeddings
(self, embeddings: list[Tensor], labels: Tensor)
sentence_transformers/sentence_transformer/losses/batch_hard_triplet.py:160
↓ 1 callersMethodcompute_loss_from_embeddings
Compute the CSRReconstruction loss from embeddings. Args: outputs: List of dictionaries containing embeddings and their
sentence_transformers/sparse_encoder/losses/csr.py:75
↓ 1 callersMethodcompute_metrics
Computes the evaluation metrics for the given model. Args: model (SentenceTransformer): The SentenceTransformer model to
sentence_transformers/sentence_transformer/evaluation/reranking.py:211
↓ 1 callersMethodcompute_metrics
(self, queries_result_list: list[object])
sentence_transformers/sentence_transformer/evaluation/information_retrieval.py:497
↓ 1 callersMethodcompute_metrics
(self, y_true, y_pred, num_positives: int | None = None)
sentence_transformers/cross_encoder/evaluation/reranking.py:308
↓ 1 callersMethodcompute_metrics_batched
Computes the evaluation metrics in a batched way, by batching all queries and all documents together. Args: model (Sente
sentence_transformers/sentence_transformer/evaluation/reranking.py:227
↓ 1 callersMethodcompute_metrics_individual
Computes the evaluation metrics individually by embedding every (query, positive, negative) tuple individually. Args: mo
sentence_transformers/sentence_transformer/evaluation/reranking.py:301
↓ 1 callersFunctioncompute_uniqueness
Run uniqueness checks concurrently with a bounded thread pool.
examples/sentence_transformer/evaluation/evaluation_no_dup_batch_sampler_speed.py:388
↓ 1 callersFunctionconnected_nodes
(matrix)
examples/sentence_transformer/applications/text-summarization/lex_rank.py:62
↓ 1 callersMethodcosine_distance
Compute the 2D matrix of cosine distances (1-cosine_similarity) between all embeddings.
sentence_transformers/sentence_transformer/losses/batch_hard_triplet.py:17
↓ 1 callersFunctioncreate_and_ingest_index
(os_client, index_name, corpus, embeddings)
examples/sentence_transformer/applications/semantic-search/semantic_search_nq_opensearch.py:51
↓ 1 callersMethodcreate_collection
(self, **kwargs)
tests/sparse_encoder/test_search_engines.py:102
↓ 1 callersMethodcreate_dense_text_model
Return a dense text model instance for the concrete test class. Subclasses should use ``request.getfixturevalue(...)`` to obtain the
tests/base/test_model.py:60
↓ 1 callersFunctioncreate_markov_matrix_discrete
(weights_matrix, threshold)
examples/sentence_transformer/applications/text-summarization/lex_rank.py:88
↓ 1 callersFunctioncreate_sparse_tensor
Create a sparse tensor of shape (rows, cols) with num_nonzero values per row.
tests/util/test_similarity.py:138
↓ 1 callersMethodcreate_text_inputs
(self)
tests/base/test_model.py:71
↓ 1 callersMethoddecode
Args: latents: autoencoder latents (shape: [batch, hidden_dim]) info: Normalization metadata returned by ``prepare``,
sentence_transformers/sparse_encoder/modules/sparse_auto_encoder.py:158
↓ 1 callersFunctiondeduplicate
(dataset)
examples/sentence_transformer/training/distillation/model_distillation_layer_reduction.py:107
↓ 1 callersFunctiondeduplicate
(dataset)
examples/sentence_transformer/training/distillation/model_distillation.py:81
↓ 1 callersFunctiondegree_centrality_scores
(similarity_matrix, threshold=None, increase_power=True)
examples/sentence_transformer/applications/text-summarization/lex_rank.py:15
↓ 1 callersFunctiondevice
(request: pytest.FixtureRequest)
tests/sentence_transformer/modules/test_pooling.py:28
↓ 1 callersMethoddisable_adapters
Disable all adapters that are attached to the model. This leads to inferring with the base model only.
sentence_transformers/base/peft_mixin.py:100
↓ 1 callersFunctiondisable_datasets_caching
A context manager that will disable caching in the datasets library.
sentence_transformers/util/misc.py:265
↓ 1 callersFunctiondisable_logging
A context manager that will prevent any logging messages triggered during the body from being processed. Args: highest_level: th
sentence_transformers/util/misc.py:283
↓ 1 callersMethodembed_inputs
( self, model: SentenceTransformer, sentences: str | list[str] | np.ndarray, *
sentence_transformers/sentence_transformer/evaluation/binary_classification.py:301
↓ 1 callersMethodembed_inputs
( self, model: SentenceTransformer, sentences: SingleInput | Sequence[SingleInput] | n
sentence_transformers/sentence_transformer/evaluation/information_retrieval.py:471
↓ 1 callersMethodembed_inputs
( self, model: SentenceTransformer, sentences: SingleInput | Sequence[SingleInput] | n
sentence_transformers/sentence_transformer/evaluation/triplet.py:241
↓ 1 callersMethodembed_inputs
( self, model: SentenceTransformer, sentences: str | list[str] | np.ndarray, *
sentence_transformers/sentence_transformer/evaluation/translation.py:172
↓ 1 callersMethodembed_inputs
( self, model: SentenceTransformer, sentences: str | list[str] | np.ndarray, *
sentence_transformers/sentence_transformer/evaluation/embedding_similarity.py:256
↓ 1 callersMethodembed_minibatch
Do forward pass on a minibatch of the input features and return corresponding embeddings.
sentence_transformers/sentence_transformer/losses/cached_gist_embed.py:178
↓ 1 callersMethodembed_minibatch
( self, sentence_feature: dict[str, Tensor], begin: int, end: int, wit
sentence_transformers/multi_vector_encoder/losses/cached_multiple_negatives_ranking.py:166
↓ 1 callersMethodembed_minibatch_iter
Do forward pass on all the minibatches of the input features and yield corresponding embeddings.
sentence_transformers/sentence_transformer/losses/cached_gist_embed.py:215
↓ 1 callersMethodembed_minibatch_iter
( self, sentence_feature: dict[str, Tensor], with_grad: bool, copy_random_stat
sentence_transformers/multi_vector_encoder/losses/cached_multiple_negatives_ranking.py:193
↓ 1 callersMethodenable_adapters
Enable adapters that are attached to the model. The model will use `self.active_adapter()`
sentence_transformers/base/peft_mixin.py:107
↓ 1 callersMethodeuclidean_distance
Compute the 2D matrix of euclidean distances between all the embeddings. Args: embeddings: tensor of shape (batch_size, e
sentence_transformers/sentence_transformer/losses/batch_hard_triplet.py:24
↓ 1 callersFunctionevaluate
(model: SentenceTransformer, name: str)
examples/sentence_transformer/training/distillation/model_quantization.py:107
↓ 1 callersMethodevaluation_loop
( self, dataloader: DataLoader, description: str, prediction_loss_only: bool |
sentence_transformers/base/trainer.py:642
↓ 1 callersFunctionexport_function
(save_dir)
tests/backend/test_utils.py:157
↓ 1 callersFunctionexport_optimized_onnx_model
Export an optimized ONNX model from a SentenceTransformer, SparseEncoder, CrossEncoder, or MultiVectorEncoder model. The O1-O4 optimizat
sentence_transformers/backend/optimize.py:19
↓ 1 callersMethodextract_dataset_metadata
( self, dataset: Dataset | DatasetDict, dataset_metadata: list[dict[str, Any]],
sentence_transformers/base/model_card.py:1268
↓ 1 callersFunctionfeatures
()
tests/sentence_transformer/losses/test_gradcache.py:362
↓ 1 callersFunctionfile_open
(filepath)
examples/sentence_transformer/applications/parallel-sentence-mining/bitext_mining_utils.py:52
↓ 1 callersFunctionfind_model_for_architecture
Find a tiny model for the given architecture, preferring huggingface-mic by default. If multiple models exist for an author, prefer the one e
tests/base/modules/transformer/update_transformers_tiny_models.py:19
↓ 1 callersFunctionflattened_column
(seed: int, batch: int = 3)
tests/sentence_transformer/losses/test_merged_forward.py:315
↓ 1 callersFunctionfloat_features
()
tests/multi_vector_encoder/losses/test_misc.py:648
↓ 1 callersFunctionformat_document
Helper function to format documents with the template.
tests/cross_encoder/test_model.py:1127
↓ 1 callersFunctionformat_duration
Format a duration in seconds to a human-readable string, e.g. "23 minutes" or "1.6 hours".
sentence_transformers/base/model_card.py:300
↓ 1 callersMethodformat_eval_metrics
Format the evaluation metrics for the model card. The following keys will be returned: - eval_metrics: A list of dictionaries contain
sentence_transformers/base/model_card.py:1417
↓ 1 callersFunctionformat_queries
Helper function to format queries with the template.
tests/cross_encoder/test_model.py:1119
↓ 1 callersMethodformat_training_logs
(self)
sentence_transformers/base/model_card.py:1546
↓ 1 callersFunctionforward
(self, a, b, a_mask, b_mask)
tests/test_kernels.py:153
↓ 1 callersMethodforward
Return dense labels ``(B, T)`` and actual cluster counts ``(B,)`` for padded distances.
sentence_transformers/multi_vector_encoder/modules/token_pooling.py:229
↓ 1 callersMethodforward
(self, features: dict[str, Tensor])
sentence_transformers/base/modules/dense.py:90
↓ 1 callersMethodforward
Forward pass through the transformer model. Dispatches to the appropriate model method based on the ``modality`` key in ``features``
sentence_transformers/base/modules/transformer.py:1636
↓ 1 callersMethodforward
(self, features, token_scale=1.0)
tests/multi_vector_encoder/test_model.py:299
↓ 1 callersMethodfrom_input_examples
(cls, examples: list[InputExample], **kwargs)
sentence_transformers/cross_encoder/evaluation/deprecated.py:64
↓ 1 callersMethodgenerate_data
(self)
sentence_transformers/sentence_transformer/datasets/parallel_sentences.py:152
↓ 1 callersFunctionget_arch_kwargs
Get model_kwargs, config_kwargs, processor_kwargs, processing_kwargs for a given architecture. Returns: Tuple of (model_kwargs, config_kw
tests/base/modules/transformer/conftest.py:660
↓ 1 callersFunctionget_batches
(seed: int)
tests/sentence_transformer/test_trainer.py:946
↓ 1 callersMethodget_codecarbon_data
(self)
sentence_transformers/base/model_card.py:1902
↓ 1 callersMethodget_config_dict
(self)
sentence_transformers/sentence_transformer/modules/word_embeddings.py:101
↓ 1 callersMethodget_config_dict
(self)
sentence_transformers/sentence_transformer/losses/adaptive_layer.py:283
↓ 1 callersMethodget_config_dict
(self)
sentence_transformers/sentence_transformer/losses/embed_distill.py:285
↓ 1 callersMethodget_config_dict
(self)
sentence_transformers/sentence_transformer/losses/mse.py:98
↓ 1 callersMethodget_config_dict
(self)
sentence_transformers/sentence_transformer/losses/distill_kl_div.py:212
↓ 1 callersMethodget_config_dict
(self)
sentence_transformers/sentence_transformer/evaluation/triplet.py:271
↓ 1 callersMethodget_config_dict
(self)
sentence_transformers/sentence_transformer/evaluation/paraphrase_mining.py:279
↓ 1 callersMethodget_config_dict
(self)
sentence_transformers/multi_vector_encoder/losses/matryoshka.py:187
↓ 1 callersMethodget_config_dict
(self)
sentence_transformers/multi_vector_encoder/losses/cached_multiple_negatives_ranking.py:156
↓ 1 callersMethodget_config_dict
(self)
sentence_transformers/multi_vector_encoder/losses/margin_mse.py:101
↓ 1 callersMethodget_config_dict
(self)
sentence_transformers/multi_vector_encoder/evaluation/reranking.py:133
↓ 1 callersMethodget_config_dict
(self)
sentence_transformers/multi_vector_encoder/evaluation/nano_beir.py:132
↓ 1 callersMethodget_config_dict
(self)
sentence_transformers/cross_encoder/losses/mse.py:111
↓ 1 callersMethodget_config_dict
Return the config dict for serialization, with tuple modality keys joined as plus-separated strings.
sentence_transformers/base/modules/transformer.py:2854
↓ 1 callersMethodget_corpus_id_ranks
Position of each corpus entry in the ascending ``corpus_ids`` order, cached across calls.
sentence_transformers/sentence_transformer/evaluation/information_retrieval.py:317
↓ 1 callersMethodget_data_collator
Load the data collator for the trainer. Args: model (:class:`~sentence_transformers.base.model.BaseModel`):
sentence_transformers/base/trainer.py:353
↓ 1 callersMethodget_default_activation_fn
(self)
sentence_transformers/cross_encoder/model.py:371
↓ 1 callersMethodget_default_loss
(self, model: BaseModel)
sentence_transformers/base/trainer.py:469
↓ 1 callersMethodget_default_model_name
(self)
sentence_transformers/multi_vector_encoder/model_card.py:194
↓ 1 callersMethodget_default_model_name
(self)
sentence_transformers/base/model_card.py:1944
↓ 1 callersFunctionget_duplicate_set
(ids_set)
examples/sentence_transformer/training/quora_duplicate_questions/create_splits.py:389
↓ 1 callersMethodget_embedding_dimension
(self)
sentence_transformers/sentence_transformer/modules/bow.py:70
↓ 1 callersMethodget_embedding_dimension
(self)
sentence_transformers/base/modules/router.py:529
↓ 1 callersMethodget_embeddings
(self, sentences)
sentence_transformers/sentence_transformer/datasets/parallel_sentences.py:179
↓ 1 callersMethodget_embeddings
(self)
sentence_transformers/sentence_transformer/losses/adaptive_layer.py:78
↓ 1 callersMethodget_eval_dataloader
Returns the evaluation [`~torch.utils.data.DataLoader`]. Subclass and override this method if you want to inject some custom behavio
sentence_transformers/base/trainer.py:951
↓ 1 callersMethodget_layer_weight
(self, layer_idx: int)
sentence_transformers/sentence_transformer/losses/adaptive_layer.py:204
↓ 1 callersFunctionget_losses
(loss: nn.Module | dict[str, nn.Module])
sentence_transformers/base/model_card.py:320
↓ 1 callersMethodget_max_seq_length
.. deprecated:: Use the :attr:`max_seq_length` property instead. Returns the maximal sequence length that the first modu
sentence_transformers/base/model.py:521
↓ 1 callersFunctionget_memory_size
(tensor)
examples/sparse_encoder/applications/computing_embeddings/compute_embeddings.py:77
↓ 1 callersMethodget_model_specific_metadata
(self)
sentence_transformers/base/model_card.py:1929
↓ 1 callersFunctionget_sample_messages
Generate sample message data (chat format with text). Args: n: Number of messages to generate text_format: Text format to use - "
tests/base/modules/transformer/conftest.py:404
↓ 1 callersFunctionget_sample_text
Generate sample text data. Returns: Dict with format names as keys and lists of text samples as values. Format: 'text' only (for
tests/base/modules/transformer/conftest.py:236
↓ 1 callersFunctionget_sample_text_pairs
Generate sample text pair data for cross-encoder style testing.
tests/base/modules/transformer/conftest.py:433
↓ 1 callersMethodget_sentence_embedding_dimension
(self)
sentence_transformers/sentence_transformer/model.py:1196
↓ 1 callersMethodget_sentence_features
( self, tokenized_texts: list[list[int]], pad_seq_length: int = 0 )
sentence_transformers/sentence_transformer/modules/bow.py:73
↓ 1 callersMethodget_train_dataloader
Returns the training [`~torch.utils.data.DataLoader`]. Will use no sampler if `train_dataset` does not implement `__len__`, a random
sentence_transformers/base/trainer.py:930
↓ 1 callersMethodget_train_objective_info
(dataloader, loss)
sentence_transformers/sentence_transformer/deprecated_model_card_templates.py:160
↓ 1 callersMethodget_training_duration_data
(self)
sentence_transformers/base/model_card.py:1918
↓ 1 callersMethodgradient_checkpointing_enable
Alias for :meth:`activation_checkpointing_enable` using the legacy argument name.
sentence_transformers/base/model.py:1695
← previousnext →801–900 of 4,575, ranked by callers