MCPcopy Create free account

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

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

↓ 12 callersFunction_disable_dropout
(model: CrossEncoder)
tests/cross_encoder/losses/test_cached_multiple_negatives_ranking.py:27
↓ 12 callersMethod_format_example_value
Format a dataset example value for the model card examples table.
sentence_transformers/base/model_card.py:1849
↓ 12 callersFunction_make_data
(**kwargs)
tests/multi_vector_encoder/test_model_card.py:39
↓ 12 callersFunction_make_feature
(t_tokens: int, batch: int, dim: int, seed: int)
tests/multi_vector_encoder/losses/test_misc.py:44
↓ 12 callersMethodevaluate
Evaluate the model based on an evaluator Args: evaluator (BaseEvaluator): The evaluator used to evaluate the model.
sentence_transformers/base/model.py:1652
↓ 12 callersMethodis_text_only_messages
Check whether all messages in a batch contain only text content. Works with both flat format (``{"content": "hello"}``) and structured format
sentence_transformers/base/modality.py:617
↓ 12 callersMethodlog
(self, logs: dict[str, float], start_time: float | None = None)
sentence_transformers/base/trainer.py:547
↓ 12 callersMethodpair_to_messages
Convert a pair of inputs to query/document message format. Each element of the pair is wrapped in a message with role ``"query"`` (first elem
sentence_transformers/base/modality.py:515
↓ 12 callersFunctionscorer_config
()
tests/test_kernels.py:113
↓ 11 callersMethod_resolve_inference_device
Resolve the input device and skip redundant or delegated model moves. Delegated models align auxiliary modules during construction and again
sentence_transformers/base/model.py:1738
↓ 11 callersFunction_to_list
Convert an iterable to a list, materializing dataset columns in one batch.
sentence_transformers/util/misc.py:22
↓ 11 callersMethodadd_adapter
Adds a fresh new adapter to the current model for training purposes. If no adapter name is passed, a default name is assigned to the
sentence_transformers/base/peft_mixin.py:65
↓ 11 callersFunctioncos_sim
Computes the cosine similarity between two tensors. Args: a (Union[list, np.ndarray, Tensor]): The first tensor. b (Union[li
sentence_transformers/util/similarity.py:59
↓ 11 callersMethodget_embedding_dimension
The dimensionality of each token vector returned by :meth:`encode`.
sentence_transformers/multi_vector_encoder/model.py:1689
↓ 11 callersFunctioninfer_batch_modality
Infer the modality of a batch of input samples. If all samples share the same modality, that modality is returned. If the batch contains mixe
sentence_transformers/base/modality.py:835
↓ 11 callersFunctionis_video_url_or_path
Check if a string is a video URL or file path.
sentence_transformers/base/modality.py:84
↓ 11 callersFunctionsemantic_search_usearch
Performs semantic search using the usearch library. Rescoring will be performed if: 1. `rescore` is True 2. The query embeddings are
sentence_transformers/util/quantization.py:215
↓ 11 callersMethodstore_metrics_in_model_card_data
(self, *args, **kwargs)
sentence_transformers/sentence_transformer/evaluation/nano_beir.py:536
↓ 10 callersFunction_columns
( model: SentenceTransformer, columns: Sequence[Sequence[str]], prompt: str | None = None )
tests/sentence_transformer/losses/test_merged_forward.py:42
↓ 10 callersMethod_multi_process
Run inference in a provided pool or a temporary pool created from a list of devices.
sentence_transformers/base/model.py:2009
↓ 10 callersFunctionassert_runs
A model is only usable if the files holding its weights came along, so load it and run it.
tests/backend/test_utils.py:146
↓ 10 callersMethodforward
(self, task=None, modality=None, **kwargs)
tests/base/modules/test_transformer.py:1071
↓ 10 callersMethodforward
(self, features)
tests/base/modules/test_router.py:35
↓ 10 callersFunctionget_n_patches
Infer the ``(n_patches_x, n_patches_y)`` = ``(n_cols, n_rows)`` image-patch grid that ``model``'s processor produces for an image of ``image_size`
sentence_transformers/multi_vector_encoder/interpretability.py:91
↓ 10 callersFunctionhttp_get
Download a URL to a local file with a progress bar. The content is streamed in chunks and first written to a temporary ``"<path>_part"`` file
sentence_transformers/util/file_io.py:316
↓ 10 callersFunctionimport_module_class
Resolve a module class reference to a class object. For class refs in the ``sentence_transformers.*`` namespace, this imports directly via
sentence_transformers/util/misc.py:171
↓ 10 callersMethodload
(cls, path)
tests/sentence_transformer/modules/test_word_embeddings.py:28
↓ 10 callersMethodload_torch_weights
A utility function to load the PyTorch weights of a model from a checkpoint. The checkpoint can be either a local directory or a mode
sentence_transformers/base/modules/module.py:311
↓ 10 callersFunctionnormalize_embeddings
Normalizes the embeddings matrix, so that each sentence embedding has unit length. Args: embeddings (Tensor): A dense or sparse embe
sentence_transformers/util/tensor.py:120
↓ 10 callersFunctionscorer
()
tests/test_kernels.py:109
↓ 10 callersMethodsparsity
Calculate sparsity statistics for the given embeddings, including the mean number of active (non-zero) dimensions and the mean sparsi
sentence_transformers/sparse_encoder/model.py:1174
↓ 10 callersMethodtokenizer
Property to get the tokenizer that is used by this model
sentence_transformers/base/model.py:2113
↓ 9 callersFunction_corpus
(n_docs: int, precision: str, seed: int = 0)
tests/util/test_quantization.py:245
↓ 9 callersFunction_model_stub
Duck-typed stand-in for ``MultiVectorEncoder``: ``get_n_patches`` only reads ``model.processor``.
tests/multi_vector_encoder/test_interpretability.py:186
↓ 9 callersFunction_reset_for_snippet
Reset model_card_data fields to ensure a clean snippet test.
tests/sentence_transformer/test_model_card.py:183
↓ 9 callersFunction_setup_hub_mocks
Set up common mocks for push_to_hub tests. Returns a dict with: - "upload_folder": dict capturing the most recent upload_folder kwargs
tests/base/test_model.py:751
↓ 9 callersFunctionappend_to_last_row
(csv_path, additional_data)
sentence_transformers/util/misc.py:300
↓ 9 callersMethodencode_document
( self, inputs: Sequence[SingleInput] | SingleInput, prompt_name: str | None = ...,
sentence_transformers/sentence_transformer/model.py:406
↓ 9 callersMethodencode_query
( self, inputs: Sequence[SingleInput] | SingleInput, prompt_name: str | None = ...,
sentence_transformers/sentence_transformer/model.py:243
↓ 9 callersMethodload
( cls, model_name_or_path: str, subfolder: str = "", token: bool | str | None
sentence_transformers/base/modules/dense.py:122
↓ 9 callersMethodpool_one
(self, embedding: Tensor, **kwargs)
sentence_transformers/multi_vector_encoder/modules/token_pooling.py:468
↓ 9 callersMethodpreprocess
(self, pairs, **kwargs)
tests/cross_encoder/losses/test_misc.py:112
↓ 9 callersMethodsave_torch_weights
Save the PyTorch weights of the module to disk. Args: output_path (str): The path to the directory where the weights sho
sentence_transformers/base/modules/module.py:435
↓ 9 callersFunctionscore
(x, y, fwd_mean, bwd_mean, margin)
examples/sentence_transformer/applications/parallel-sentence-mining/bitext_mining_utils.py:18
↓ 9 callersMethodset_evaluation_metrics
( self, evaluator: BaseEvaluator, metrics: dict[str, Any], epoch: int = 0, step: int = 0 )
sentence_transformers/base/model_card.py:934
↓ 9 callersMethodsimilarity_pairwise
(self, queries, positives)
tests/util/test_hard_negatives.py:1918
↓ 9 callersFunctionsuggest_extra_on_exception
Re-raise ImportError/AttributeError with an install hint when a multimodal dependency is missing.
sentence_transformers/util/environment.py:33
↓ 9 callersMethodto_message
Convert a typed input dictionary to message format. Produces a single message with the given ``role``. For query/document pairs, use
sentence_transformers/base/modality.py:542
↓ 8 callersMethod_chat_template_suffix_ids
Derive one conversation's trailing chat-template suffix (cached). The conversation is rendered twice with different fillers: the longest comm
sentence_transformers/base/modules/transformer.py:2118
↓ 8 callersMethod_hash_asset
Compute an identity hash for an asset value, or None if the type is not supported.
sentence_transformers/base/model_card.py:804
↓ 8 callersFunction_make_mock_video_decoder
Create a ``_MockVideoDecoder`` with custom metadata overrides.
tests/base/test_model_card.py:1119
↓ 8 callersFunction_mnrl
(model: nn.Module, **kwargs)
tests/multi_vector_encoder/losses/test_token_pooling.py:53
↓ 8 callersFunction_mnrl
(model: nn.Module, **kwargs)
tests/multi_vector_encoder/losses/test_matryoshka.py:46
↓ 8 callersMethod_prepare_for_inference
Convert a value to a format suitable for model inference. ``VideoDecoder`` objects are converted to a ``VideoDict`` via :meth:`_video_decoder
sentence_transformers/base/model_card.py:1649
↓ 8 callersMethod_process_chat_messages
Process chat messages using the processor's chat template. ``chat_template_kwargs`` is forwarded to ``apply_chat_template``, except the Sente
sentence_transformers/base/modules/transformer.py:1910
↓ 8 callersMethod_restore_chat_template_suffix
Restore the trailing chat-template suffix that truncation may have removed (in place). Chat templates append fixed tokens after the content (
sentence_transformers/base/modules/transformer.py:2050
↓ 8 callersMethodcompile
Compile the model's forward pass with :func:`torch.compile` to speed up inference. All arguments are forwarded to :func:`torch.compi
sentence_transformers/base/model.py:645
↓ 8 callersMethodencode_document
(self, sentences, **kwargs)
tests/sentence_transformer/evaluation/test_information_retrieval_evaluator.py:55
↓ 8 callersFunctionexport_to
Run save_or_push_to_hub_model against a local directory and return the files it wrote.
tests/backend/test_utils.py:107
↓ 8 callersFunctionget_rank
The rank of the current process in the distributed group, or ``0`` when not distributed.
sentence_transformers/util/distributed.py:24
↓ 8 callersMethodget_vocab
(self, vocab: Iterable[str])
sentence_transformers/sentence_transformer/modules/tokenizer/word.py:404
↓ 8 callersFunctionis_audio_url_or_path
Check if a string is an audio URL or file path.
sentence_transformers/base/modality.py:102
↓ 8 callersMethodload_config
Load the configuration of the module 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:176
↓ 8 callersMethodnormalize_messages
Normalize messages to the target format (``self.message_format``). Extra keys beyond ``"role"`` and ``"content"`` are preserved during conver
sentence_transformers/base/modality.py:641
↓ 8 callersFunctionpairwise_cos_sim
Computes the pairwise cosine similarity cos_sim(a[i], b[i]). Args: a (Union[list, np.ndarray, Tensor]): The first tensor. b
sentence_transformers/util/similarity.py:78
↓ 8 callersFunctionpairwise_euclidean_sim
Computes the euclidean similarity (i.e., negative distance) between pairs of tensors. Args: a (Union[list, np.ndarray, Tensor]): The
sentence_transformers/util/similarity.py:213
↓ 8 callersMethodpredict
(self, inputs, device=None, **kwargs)
tests/utils.py:66
↓ 8 callersMethodrank
Performs ranking with the CrossEncoder on the given query and documents. Returns a sorted list with the document indices and scores.
sentence_transformers/cross_encoder/model.py:723
↓ 8 callersMethodresolve_with_tokenizer
Convert ``skiplist_words`` to token IDs using ``tokenizer``. Called by :class:`MultiVectorEncoder` after the tokenizer is fully initialised.
sentence_transformers/multi_vector_encoder/modules/multi_vector_mask.py:92
↓ 8 callersFunctionsemantic_search_faiss
Performs semantic search using the FAISS library. Rescoring will be performed if: 1. `rescore` is True 2. The query embeddings are n
sentence_transformers/util/quantization.py:20
↓ 8 callersMethodset_base_model
(self, model_id: str, revision: str | None = None)
sentence_transformers/base/model_card.py:1360
↓ 8 callersMethodset_pooling_include_prompt
Sets the ``include_prompt`` attribute in the pooling layer in the model, if there is one. This is useful for models where the prompt
sentence_transformers/sparse_encoder/model.py:877
↓ 8 callersMethodsimilarity
(self, queries, corpus)
tests/util/test_hard_negatives.py:1915
↓ 7 callersFunction_build_flattened_features
Convert padded inputs to flattened format using DataCollatorWithFlattening.
tests/sentence_transformer/modules/test_pooling.py:489
↓ 7 callersFunction_count_media_per_sample
Count images and videos per sample from the message structure. Some VLM processors flatten per-sample visual tokens into single tensors (e.g.
sentence_transformers/base/modules/transformer.py:641
↓ 7 callersFunction_features_and_labels
(model: SentenceTransformer)
tests/sentence_transformer/losses/test_adaptive_layer.py:52
↓ 7 callersMethod_format_snippet_value
Format a value for inclusion in a code snippet. Strings are shown as repr (quoted), and asset paths are converted to Hub URLs when mo
sentence_transformers/base/model_card.py:1871
↓ 7 callersMethod_infer_format
Infer the message format expected by the processor. Checks known model types first, then inspects the processor's chat template for p
sentence_transformers/base/modality.py:308
↓ 7 callersFunction_resolve_model_revision
Resolve a Hub revision once when supported. Falls back to the requested revision on older Hub versions, and when resolution fails for any reason
sentence_transformers/util/file_io.py:65
↓ 7 callersMethod_resolve_prompts
Resolve the prompts for this batch, handling nested (per-dataset) mappings.
sentence_transformers/base/data_collator.py:52
↓ 7 callersFunction_sample_value_str
(value: Any)
sentence_transformers/base/sampler.py:359
↓ 7 callersMethod_video_decoder_to_dict
Convert a ``VideoDecoder`` to a ``VideoDict`` by extracting all frames. Tries multiple strategies to extract frames: 1. ``get_frames_
sentence_transformers/base/model_card.py:1585
↓ 7 callersMethodcalibrate_distance_threshold
Choose a Ward distance threshold for an average document token budget. The calibration average is at most ``target_tokens``. Individual docum
sentence_transformers/multi_vector_encoder/modules/token_pooling.py:540
↓ 7 callersMethodcompute_loss_from_embeddings
(self, embeddings: list[Tensor], labels: Tensor)
sentence_transformers/sentence_transformer/losses/distill_kl_div.py:174
↓ 7 callersMethodcuda
Move the model to a CUDA device and override its saved device map.
sentence_transformers/base/model.py:1792
↓ 7 callersMethoddevice
Return the execution device, falling back to model tensors and then CPU.
sentence_transformers/base/model.py:1848
↓ 7 callersFunctionformat_modality
Format a modality for display, e.g. ``("text", "image")`` becomes ``"text+image"``.
sentence_transformers/base/modality.py:859
↓ 7 callersMethodload_config
(cls, *args, **kwargs)
sentence_transformers/sentence_transformer/modules/pooling.py:118
↓ 7 callersFunctionmake_char_chat_template_mock
Chat-template mock: one token per content character plus ``suffix``, honoring truncation/max_length and return_tensors ("pt", "np", or ragged list
tests/base/modules/test_transformer.py:1230
↓ 7 callersFunctionmake_modality_kwargs
Modality kwargs for _process_chat_messages with only the text bucket populated.
tests/base/modules/test_transformer.py:1251
↓ 7 callersFunctionmaxsim_similarity_map
Per-query-token similarity over a 2D image-patch grid. Args: query_embedding: ``(Qt, D)`` per-token query embeddings. image_embed
sentence_transformers/multi_vector_encoder/interpretability.py:136
↓ 7 callersFunctionparaphrase_mining_embeddings
Given a list of sentences / texts, this function performs paraphrase mining. It compares all sentences against all other sentences and return
sentence_transformers/util/retrieval.py:91
↓ 7 callersMethodset_widget_examples
(self, dataset: Dataset | DatasetDict)
sentence_transformers/base/model_card.py:520
↓ 6 callersMethod__init__
(self)
tests/base/modules/test_router.py:32
↓ 6 callersMethod_can_flatten_inputs
Check if the first module (Transformer or Router containing Transformers) supports flattened text-only inputs. For Router models, this return
sentence_transformers/base/model.py:542
↓ 6 callersFunction_convert_to_float_tensor
Converts like :func:`_convert_to_tensor`, then upcasts sub-float32 floats (fp8, float16, bfloat16) to float32: matmul rounds its output to th
sentence_transformers/util/tensor.py:61
↓ 6 callersFunction_features
(model: SentenceTransformer, texts: list[str])
tests/sentence_transformer/losses/test_embed_distill.py:13
↓ 6 callersMethod_is_typed_media_dict
Check if a dict is an AudioDict or VideoDict (vs a multimodal input dict).
sentence_transformers/base/model_card.py:799
↓ 6 callersFunction_make_loss
(model: SentenceTransformer)
tests/sentence_transformer/losses/test_adaptive_layer.py:47
↓ 6 callersMethod_padded
(self, lengths: list[int])
tests/sentence_transformer/losses/test_gradcache.py:266
← previousnext →101–200 of 4,575, ranked by callers