Code
Hub
Workspaces
Following
Trending
Connect
MCP
copy
Create free account
hub
/
github.com/huggingface/sentence-transformers
/ functions
Functions
3,759 in github.com/huggingface/sentence-transformers
⨍
Functions
3,759
◇
Types & classes
446
↳
Endpoints
48
Function
id_to_text_map
(batch)
examples/sentence_transformer/training/ms_marco/train_bi_encoder_margin_mse.py:81
Function
id_to_text_map
(batch)
examples/cross_encoder/training/distillation/train_cross_encoder_kd_margin_mse.py:44
Function
id_to_text_map
(batch)
examples/cross_encoder/training/distillation/train_cross_encoder_kd_mse.py:44
Function
id_to_text_map
(batch)
examples/cross_encoder/training/ms_marco/training_ms_marco_bce_preprocessed.py:47
Function
id_to_text_map
(batch)
examples/sparse_encoder/training/distillation/train_splade_msmarco_margin_mse.py:62
Function
id_to_text_map
(batch)
examples/sparse_encoder/training/ms_marco/train_splade_msmarco_mnrl.py:63
Method
identity
(batch)
sentence_transformers/sentence_transformer/fit_mixin.py:249
Method
identity
(batch)
sentence_transformers/cross_encoder/fit_mixin.py:258
Function
ids_to_text_transform
(batch)
examples/sentence_transformer/training/ms_marco/train_bi_encoder_margin_mse_mnrl.py:152
Function
ids_to_text_transform
(batch)
examples/sentence_transformer/training/ms_marco/train_bi_encoder_mnrl.py:147
Function
ids_to_text_transform
(batch)
examples/cross_encoder/training/ms_marco/training_ms_marco_adrmse.py:49
Function
imbalanced_dataset
140 samples: label 0 has 90, label 1 has 30, label 2 has 20.
tests/base/samplers/test_group_by_label_batch_sampler.py:34
Function
inference_free_splade_bert_tiny_model
(_inference_free_splade_bert_tiny_model: SparseEncoder)
tests/conftest.py:174
Function
information_retrieval
This function is deprecated. Use semantic_search instead
sentence_transformers/util/retrieval.py:162
Function
inherit_class_docstrings
Inherit parent class docstrings for classes that don't define their own. ``autodoc_inherit_docstrings`` only applies to methods, not classes.
docs/conf.py:310
Function
install_logger
Configures the given logger: format, logging level, style, etc
sentence_transformers/util/logging.py:23
Function
is_sentence_transformer_model
Checks if the given model name or path corresponds to a SentenceTransformer model. Args: model_name_or_path (str): The name or path
sentence_transformers/util/file_io.py:34
Function
it_to_text_transform
(batch)
examples/cross_encoder/training/ms_marco/training_ms_marco_lambda_preprocessed.py:48
Method
join_list
(losses: list[str])
sentence_transformers/base/model_card.py:501
Function
kd_dataset
()
tests/multi_vector_encoder/test_trainer.py:53
Method
keep_first_two
(emb: Tensor)
tests/multi_vector_encoder/test_token_pooling.py:251
Function
linkcode_resolve
(domain, info)
docs/conf.py:129
Method
load
Deprecated: Use SentenceTransformer(input_path) instead.
sentence_transformers/sentence_transformer/model.py:1311
Method
load
( cls, model_name_or_path: str, subfolder: str = "", token: bool | str | None
sentence_transformers/sentence_transformer/modules/cnn.py:71
Method
load
( cls, model_name_or_path: str, subfolder: str = "", token: bool | str | None
sentence_transformers/sentence_transformer/modules/weighted_layer_pooling.py:55
Method
load
( cls, model_name_or_path: str, subfolder: str = "", token: bool | str | None
sentence_transformers/sentence_transformer/modules/word_embeddings.py:109
Method
load
( cls, model_name_or_path: str, subfolder: str = "", token: bool | str | None
sentence_transformers/sentence_transformer/modules/static_embedding.py:140
Method
load
(cls, model_name_or_path: str, **kwargs)
sentence_transformers/sentence_transformer/modules/clip_model.py:31
Method
load
( cls, model_name_or_path: str, subfolder: str = "", token: bool | str | None
sentence_transformers/sentence_transformer/modules/layer_norm.py:33
Method
load
( cls, model_name_or_path: str, subfolder: str = "", token: bool | str | None
sentence_transformers/sentence_transformer/modules/lstm.py:77
Method
load
(input_path: str)
sentence_transformers/sentence_transformer/modules/tokenizer/word.py:417
Method
load
(input_path: str)
sentence_transformers/sentence_transformer/modules/tokenizer/word.py:440
Method
load
(input_path: str)
sentence_transformers/sentence_transformer/modules/tokenizer/phrase.py:118
Method
load
(input_path: str)
sentence_transformers/sentence_transformer/modules/tokenizer/whitespace.py:74
Method
load
(cls, model_name_or_path: str, **kwargs)
sentence_transformers/sparse_encoder/modules/mlm_transformer.py:35
Method
load
( cls, model_name_or_path: str, subfolder: str = "", token: bool | str | None
sentence_transformers/sparse_encoder/modules/sparse_auto_encoder.py:207
Method
load
( cls, model_name_or_path: str = "", subfolder: str = "", token: bool | str |
sentence_transformers/base/modules/normalize.py:49
Method
load
Load a Transformer module from a pretrained model directory or Hugging Face model name.
sentence_transformers/base/modules/transformer.py:2600
Method
load
( cls, model_name_or_path: str, subfolder: str = "", token: bool | str | None
sentence_transformers/base/modules/router.py:638
Method
load_data
Reads in a tab-separated .txt/.csv/.tsv or .gz file. The different columns contain the different translations of the sentence in the first co
sentence_transformers/sentence_transformer/datasets/parallel_sentences.py:74
Function
low_precision_embeddings
()
tests/util/test_similarity.py:417
Function
map_embeddings
(batch)
examples/sentence_transformer/training/distillation/model_distillation_layer_reduction.py:141
Function
map_embeddings
(batch)
examples/sentence_transformer/training/distillation/model_distillation.py:129
Method
mapper
( sample, corpus_mapping: dict[str, str], query_mapping: dict[str, str],
sentence_transformers/cross_encoder/evaluation/nano_beir.py:356
Method
mask_false_negatives
(guided_sim_mat, sim_mat, positive_mask: Tensor | None = None)
sentence_transformers/sentence_transformer/losses/cached_gist_embed.py:302
Method
mask_false_negatives
(guided_sim_mat, sim_mat, positive_mask: Tensor | None = None)
sentence_transformers/sentence_transformer/losses/gist_embed.py:199
Method
max_length
(self)
sentence_transformers/cross_encoder/model.py:454
Method
max_seq_length
(self)
sentence_transformers/sentence_transformer/modules/static_embedding.py:126
Method
max_seq_length
Returns the maximal input sequence length for the model. Longer inputs will be truncated. Returns: int: The maximal inpu
sentence_transformers/sparse_encoder/model.py:1290
Method
max_seq_length
Returns the maximal input sequence length for the model. Longer inputs will be truncated. Returns: Optional[int]: The ma
sentence_transformers/base/model.py:1654
Method
max_seq_length
The maximum input sequence length. Reads from the tokenizer if available, otherwise falls back to ``max_position_embeddings`` from the model c
sentence_transformers/base/modules/transformer.py:1138
Method
max_seq_length
(self)
sentence_transformers/base/modules/router.py:720
Method
maybe_to_float
(value: Any)
sentence_transformers/base/evaluation/evaluator.py:49
Function
mean_colbert_kd_scores
MeanMaxSim listwise KD scoring, the :func:`colbert_kd_scores` counterpart of :func:`mean_colbert_scores`. Use it as :class:`MultiVectorDistillKLDi
sentence_transformers/multi_vector_encoder/scoring/colbert.py:188
Function
mean_colbert_scores
MeanMaxSim contrastive scoring: :func:`colbert_scores` divided by each query's real token count. Pair it with ``model.similarity_fn_name = "meanm
sentence_transformers/multi_vector_encoder/scoring/colbert.py:141
Function
mean_colbert_scores_pairwise
MeanMaxSim pairwise scoring, the :func:`colbert_scores_pairwise` counterpart of :func:`mean_colbert_scores`. Use it as :class:`MultiVectorMarginMS
sentence_transformers/multi_vector_encoder/scoring/colbert.py:166
Method
mixed_modality_features
(self)
tests/sentence_transformer/losses/test_cmnrl.py:219
Function
mnrl_mapper
(batch)
examples/cross_encoder/training/ms_marco/training_ms_marco_cmnrl.py:39
Function
mock_apply_chat_template
(messages, **kwargs)
tests/base/modules/test_transformer.py:1024
Method
mock_apply_chat_template
(messages, **kwargs)
tests/base/modules/test_transformer.py:1110
Function
mock_create_branch
(self, repo_id, branch, revision=None, **kwargs)
tests/sentence_transformer/test_model.py:146
Function
mock_create_branch
(self, repo_id, branch, revision=None, **kwargs)
tests/cross_encoder/test_model.py:481
Function
mock_create_branch
(self, repo_id, branch, revision=None, **kwargs)
tests/base/test_model.py:712
Function
mock_create_repo
(self, repo_id, **kwargs)
tests/sentence_transformer/test_model.py:124
Function
mock_create_repo
(self, repo_id, **kwargs)
tests/cross_encoder/test_model.py:459
Function
mock_create_repo
(self, repo_id, **kwargs)
tests/base/test_model.py:694
Method
mock_forward
(**kwargs)
tests/base/modules/test_transformer.py:613
Function
mock_from_pretrained
(*args, **kwargs)
tests/util/test_environment.py:88
Function
mock_get_class
(class_ref, model_name_or_path, **kwargs)
tests/base/test_model.py:591
Function
mock_hub_info
Mock the Hub requests checking whether base models and datasets exist, e.g. to dodge rate limits in CI.
tests/conftest.py:55
Function
mock_init
(self, *args, **kwargs)
tests/cross_encoder/test_model.py:602
Function
mock_loss
Create a mock base loss for testing.
tests/sentence_transformer/losses/test_matryoshka.py:12
Function
mock_model
()
tests/sentence_transformer/evaluation/test_information_retrieval_evaluator.py:14
Function
mock_predict
(self, *args, **kwargs)
tests/cross_encoder/test_model.py:644
Function
mock_preprocess
(texts, **kwargs)
tests/util/test_hard_negatives.py:1505
Function
mock_upload_folder
(self, **kwargs)
tests/sentence_transformer/test_model.py:129
Function
mock_upload_folder
(self, **kwargs)
tests/cross_encoder/test_model.py:464
Function
mock_upload_folder
(self, **kwargs)
tests/base/test_model.py:697
Method
modalities
Return the list of modalities supported by this model, e.g. ``["text"]`` or ``["text", "image", "message"]``.
sentence_transformers/base/model.py:380
Method
modalities
The list of supported input modalities. Defaults to ``["text"]``.
sentence_transformers/base/modules/input_module.py:71
Method
modalities
The list of supported input modalities (e.g. ``"text"``, ``"image"``, ``("image", "text")``).
sentence_transformers/base/modules/transformer.py:1171
Method
modalities
The union of modalities supported by all sub-module input modules.
sentence_transformers/base/modules/router.py:327
Method
modalities
(self)
tests/base/modules/test_router.py:66
Function
model
()
tests/multi_vector_encoder/test_multi_process.py:17
Function
model
()
tests/multi_vector_encoder/test_trainer.py:29
Function
model
()
tests/multi_vector_encoder/test_evaluators.py:17
Method
model_card_get_pooling_function
(pooling_mode)
sentence_transformers/sentence_transformer/deprecated_model_card_templates.py:125
Function
model_dir
(tmp_path_factory)
tests/multi_vector_encoder/test_backends.py:31
Function
model_init
()
tests/sentence_transformer/test_trainer.py:1033
Function
multiple_positive_dataset
Return a sample dataset with multiple matching passages for each query.
tests/util/test_hard_negatives.py:103
Function
multiple_positive_passages_dataset
Return a sample dataset with multiple matching passages for each query.
tests/util/test_hard_negatives.py:92
Function
multiple_positive_queries_dataset
Return a sample dataset with multiple matching passages for each query.
tests/util/test_hard_negatives.py:81
Method
naive_feature
(value: Any)
sentence_transformers/base/trainer.py:239
Function
nli_minilm_model
(_nli_minilm_model)
tests/cross_encoder/conftest.py:31
Function
nli_resource
()
tests/sentence_transformer/test_train_stsb.py:28
Function
notice
(self, message, *args, **kws)
sentence_transformers/util/logging.py:34
Function
null_batch_sampler
(*args, **kwargs)
tests/sentence_transformer/test_trainer.py:864
Function
null_multi_dataset_batch_sampler
(*args, **kwargs)
tests/sentence_transformer/test_trainer.py:990
Method
num_labels
(self)
sentence_transformers/cross_encoder/model.py:434
Method
old_fit
Deprecated training method from before Sentence Transformers v3.0, it is recommended to use :class:`sentence_transformers.sentence_tr
sentence_transformers/sentence_transformer/fit_mixin.py:456
← previous
next →
1,701–1,800 of 3,759, ranked by callers