MCPcopy Create free account

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

Functions3,759 in github.com/huggingface/sentence-transformers

⨍ Functions 3,759◇ Types & classes 446↳ Endpoints 48
↓ 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:269
↓ 1 callersMethodget_config_dict
(self)
sentence_transformers/multi_vector_encoder/losses/cached_multiple_negatives_ranking.py:159
↓ 1 callersMethodget_config_dict
(self)
sentence_transformers/multi_vector_encoder/losses/margin_mse.py:106
↓ 1 callersMethodget_config_dict
(self)
sentence_transformers/multi_vector_encoder/evaluation/distillation.py:256
↓ 1 callersMethodget_config_dict
(self)
sentence_transformers/cross_encoder/losses/mse.py:104
↓ 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:2802
↓ 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:300
↓ 1 callersMethodget_data_collator
Load the data collator for the trainer. Args: model (:class:`~sentence_transformers.base.model.BaseModel`):
sentence_transformers/base/trainer.py:337
↓ 1 callersMethodget_default_activation_fn
(self)
sentence_transformers/cross_encoder/model.py:406
↓ 1 callersMethodget_default_loss
(self, model: BaseModel)
sentence_transformers/base/trainer.py:464
↓ 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:1909
↓ 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:528
↓ 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:934
↓ 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:312
↓ 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:448
↓ 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:1894
↓ 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:399
↓ 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:231
↓ 1 callersFunctionget_sample_text_pairs
Generate sample text pair data for cross-encoder style testing.
tests/base/modules/transformer/conftest.py:428
↓ 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_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:1883
↓ 1 callersMethodget_triplet_mask
Return a 3D mask where mask[a, p, n] is True iff the triplet (a, p, n) is valid. A triplet (i, j, k) is valid if: - i, j, k are di
sentence_transformers/sentence_transformer/losses/batch_hard_triplet.py:202
↓ 1 callersFunctiongrads
(scale: float)
tests/sentence_transformer/losses/test_mega_batch_margin.py:200
↓ 1 callersFunctiongrads
(scale: float)
tests/sentence_transformer/losses/test_gradcache.py:143
↓ 1 callersFunctiongrads
(scale: float)
tests/cross_encoder/losses/test_cached_multiple_negatives_ranking.py:132
↓ 1 callersFunctionhas_overlap
(sample_values: set[str], batch_values: set[str])
tests/base/samplers/test_no_duplicates_batch_sampler.py:91
↓ 1 callersMethodhas_peft_compatible_model
(self)
sentence_transformers/base/peft_mixin.py:37
↓ 1 callersFunctionhighlight
Invert the terminal's own foreground and background. Inverting rather than picking a colour keeps the highlight legible on light and dark themes a
examples/multi_vector_encoder/interpretability/text_similarity_map.py:26
↓ 1 callersMethodinfer_datasets
(self, dataset: Dataset | DatasetDict, dataset_name: str | None = None)
sentence_transformers/base/model_card.py:966
↓ 1 callersMethodinfer_modalities
Infer the modality configuration and module output name from the model and processor. First checks :meth:`infer_modalities_edge_cases` for ha
sentence_transformers/base/modules/transformer.py:2396
↓ 1 callersMethodis_better
(self, new_metric: float)
sentence_transformers/sentence_transformer/fit_mixin.py:57
↓ 1 callersMethodis_better
(self, new_metric: float)
sentence_transformers/cross_encoder/fit_mixin.py:54
↓ 1 callersMethodis_singular_input
Check if the input is a single example rather than a batch. Redeclared with :class:`~typing_extensions.TypeIs` so type checkers narrow the bra
sentence_transformers/multi_vector_encoder/model.py:216
↓ 1 callersMethodis_singular_input
Check if the input represents a single example or a batch of examples. Declared with :class:`~typing_extensions.TypeIs` so type check
sentence_transformers/cross_encoder/model.py:868
↓ 1 callersFunctionk
(t,r)
docs/_static/js/custom.js:28
↓ 1 callersFunctionlistwise_mapper
(batch, max_docs: int | None = 10)
examples/cross_encoder/training/ms_marco/training_ms_marco_plistmle.py:42
↓ 1 callersFunctionlistwise_mapper
(batch, max_docs: int | None = 10)
examples/cross_encoder/training/ms_marco/training_ms_marco_lambda.py:44
↓ 1 callersFunctionlistwise_mapper
(batch, max_docs: int | None = 10)
examples/cross_encoder/training/ms_marco/training_ms_marco_listnet.py:41
↓ 1 callersFunctionlistwise_mapper
(batch, max_docs: int | None = 10)
examples/cross_encoder/training/ms_marco/training_ms_marco_listmle.py:42
↓ 1 callersFunctionlistwise_mapper
(batch, max_docs: int | None = 10)
examples/cross_encoder/training/ms_marco/training_ms_marco_lambda_hard_neg.py:46
↓ 1 callersFunctionlistwise_mapper
(batch, max_docs: int | None = 10)
examples/cross_encoder/training/ms_marco/training_ms_marco_ranknet.py:46
↓ 1 callersMethodload
Load the SparseStaticEmbedding module with its tokenizer. Args: model_name_or_path (str): Path to the directory containi
sentence_transformers/sparse_encoder/modules/sparse_static_embedding.py:158
↓ 1 callersMethodload_adapter
Load adapter weights from file or remote Hub folder." If you are not familiar with adapters and PEFT methods, we invite you to read m
sentence_transformers/base/peft_mixin.py:47
↓ 1 callersMethodload_config
Load the module config, trying several legacy config filenames for backward compatibility. Handles deserialization of ``modality_config`` tup
sentence_transformers/base/modules/transformer.py:2707
↓ 1 callersMethodload_dir_path
A utility function to load a directory from a model checkpoint. The checkpoint can be either a local directory or a model id on Hugging Face.
sentence_transformers/base/modules/module.py:274
↓ 1 callersFunctionload_onnx_model
Load and perhaps export an ONNX model using the Optimum library. Args: model_name_or_path (str): The model name on Hugging Face (e.g
sentence_transformers/backend/load.py:14
↓ 1 callersFunctionload_openvino_model
Load and perhaps export an OpenVINO model using the Optimum library. Args: model_name_or_path (str): The model name on Hugging Face
sentence_transformers/backend/load.py:92
↓ 1 callersFunctionload_pair_dataset
Load a contrastive-pair dataset for training. StaticEmbedding starts from random initialization, so it needs *a lot* of contrastive signal to
skills/train-sentence-transformers/scripts/train_sentence_transformer_static_embedding_example.py:132
↓ 1 callersFunctionload_parallel_data
Load (en, target_lang) parallel pairs for each target language as a DatasetDict.
skills/train-sentence-transformers/scripts/train_sentence_transformer_make_multilingual_example.py:121
↓ 1 callersFunctionload_resolved_dataset
Load (query, positive, negative, score) rows. The MSMARCO subset is keyed by passage_id / query_id. Resolve to text once and cache to disk so reru
skills/train-sentence-transformers/scripts/train_sparse_encoder_distillation_example.py:111
↓ 1 callersFunctionload_resolved_dataset
Load (query, positive, negative, score) rows. The MSMARCO subset is keyed by passage_id / query_id. Resolve to text once and cache to disk so reru
skills/train-sentence-transformers/scripts/train_cross_encoder_distillation_example.py:114
↓ 1 callersFunctionlog_trackio_dashboard
Surface the Trackio dashboard URL so the user can watch training live.
skills/train-sentence-transformers/scripts/train_sentence_transformer_make_multilingual_example.py:72
↓ 1 callersFunctionlog_trackio_dashboard
Surface the Trackio dashboard URL so the user can watch training live.
skills/train-sentence-transformers/scripts/train_cross_encoder_example.py:64
↓ 1 callersFunctionlog_trackio_dashboard
Surface the Trackio dashboard URL so the user can watch training live.
skills/train-sentence-transformers/scripts/train_sparse_encoder_distillation_example.py:67
↓ 1 callersFunctionlog_trackio_dashboard
Surface the Trackio dashboard URL so the user can watch training live.
skills/train-sentence-transformers/scripts/train_sentence_transformer_with_lora_example.py:120
↓ 1 callersFunctionlog_trackio_dashboard
Surface the Trackio dashboard URL so the user can watch training live.
skills/train-sentence-transformers/scripts/train_sentence_transformer_example.py:77
↓ 1 callersFunctionlog_trackio_dashboard
Surface the Trackio dashboard URL so the user can watch training live.
skills/train-sentence-transformers/scripts/train_sentence_transformer_matryoshka_example.py:58
↓ 1 callersFunctionlog_trackio_dashboard
Surface the Trackio dashboard URL so the user can watch training live.
skills/train-sentence-transformers/scripts/train_cross_encoder_distillation_example.py:73
↓ 1 callersFunctionlog_trackio_dashboard
Surface the Trackio dashboard URL so the user can watch training live.
skills/train-sentence-transformers/scripts/train_multi_vector_encoder_example.py:77
↓ 1 callersFunctionlog_trackio_dashboard
Surface the Trackio dashboard URL so the user can watch training live.
skills/train-sentence-transformers/scripts/train_sparse_encoder_example.py:64
↓ 1 callersFunctionlog_trackio_dashboard
Surface the Trackio dashboard URL so the user can watch training live.
skills/train-sentence-transformers/scripts/train_cross_encoder_listwise_example.py:81
↓ 1 callersFunctionlog_trackio_dashboard
Surface the Trackio dashboard URL so the user can watch training live.
skills/train-sentence-transformers/scripts/train_sentence_transformer_multi_dataset_example.py:106
↓ 1 callersFunctionlog_trackio_dashboard
Surface the Trackio dashboard URL so the user can watch training live.
skills/train-sentence-transformers/scripts/train_sentence_transformer_static_embedding_example.py:87
↓ 1 callersFunctionlog_trackio_dashboard
Surface the Trackio dashboard URL so the user can watch training live.
skills/train-sentence-transformers/scripts/train_sentence_transformer_distillation_example.py:102
↓ 1 callersMethodlogits_from_pairs
Computes the logits for a list of pairs using the model. Args: pairs (list[tuple[str, str]]): A list of pairs of strings
sentence_transformers/cross_encoder/losses/margin_mse.py:148
↓ 1 callersFunctionloss_and_grads
(loss_fn: torch.nn.Module)
tests/sentence_transformer/losses/test_cached_mnsrl.py:28
↓ 1 callersFunctionloss_and_grads
(loss_fn: torch.nn.Module)
tests/cross_encoder/losses/test_cached_multiple_negatives_ranking.py:172
↓ 1 callersFunctionloss_and_grads
(cached: bool)
tests/sparse_encoder/losses/test_cached_splade.py:176
↓ 1 callersFunctionlosses
(loss_fn_first: torch.nn.Module, loss_fn_second: torch.nn.Module)
tests/cross_encoder/losses/test_cached_multiple_negatives_ranking.py:102
↓ 1 callersFunctionmain
()
examples/sentence_transformer/training/ms_marco/train_bi_encoder_margin_mse.py:48
↓ 1 callersFunctionmain
()
examples/sentence_transformer/training/ms_marco/train_kldiv.py:28
↓ 1 callersFunctionmain
()
examples/sentence_transformer/training/ms_marco/train_bi_encoder_margin_mse_mnrl.py:72
↓ 1 callersFunctionmain
()
examples/sentence_transformer/training/ms_marco/train_bi_encoder_mnrl.py:68
↓ 1 callersFunctionmain
()
examples/sentence_transformer/evaluation/evaluation_no_dup_batch_sampler_speed.py:417
↓ 1 callersFunctionmain
()
examples/multi_vector_encoder/applications/retrieve_rerank.py:19
↓ 1 callersFunctionmain
()
examples/multi_vector_encoder/applications/semantic_search.py:20
↓ 1 callersFunctionmain
()
examples/multi_vector_encoder/training/miriad/training_contrastive.py:76
↓ 1 callersFunctionmain
()
examples/multi_vector_encoder/training/xtr/training_contrastive.py:35
↓ 1 callersFunctionmain
()
examples/multi_vector_encoder/training/msmarco/training_cached_contrastive.py:43
↓ 1 callersFunctionmain
()
examples/multi_vector_encoder/training/msmarco/training_kd.py:57
↓ 1 callersFunctionmain
()
examples/multi_vector_encoder/training/msmarco/training_contrastive.py:41
↓ 1 callersFunctionmain
()
examples/multi_vector_encoder/training/multimodal/finetuning_colqwen2.py:49
↓ 1 callersFunctionmain
()
examples/multi_vector_encoder/training/peft/training_msmarco_lora.py:45
↓ 1 callersFunctionmain
()
examples/multi_vector_encoder/interpretability/heatmap.py:38
↓ 1 callersFunctionmain
()
examples/multi_vector_encoder/interpretability/text_similarity_map.py:95
↓ 1 callersFunctionmain
()
examples/multi_vector_encoder/compression/token_pooling.py:22
↓ 1 callersFunctionmain
()
examples/multi_vector_encoder/evaluation/nano_beir.py:16
↓ 1 callersFunctionmain
()
examples/cross_encoder/training/distillation/train_cross_encoder_kd_margin_mse.py:13
↓ 1 callersFunctionmain
()
examples/cross_encoder/training/distillation/train_cross_encoder_kd_mse.py:13
↓ 1 callersFunctionmain
()
examples/cross_encoder/training/ms_marco/training_ms_marco_cmnrl.py:17
↓ 1 callersFunctionmain
()
examples/cross_encoder/training/ms_marco/training_ms_marco_plistmle.py:14
← previousnext →701–800 of 3,759, ranked by callers