MCPcopy Create free account

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

Functions404 in github.com/huggingface/sentence-transformers

↓ 1 callersMethodget_embeddings
(self, sentences)
sentence_transformers/datasets/ParallelSentencesDataset.py:131
↓ 1 callersMethodget_examples
sentence_transformers/readers/TripletReader.py:21
↓ 1 callersMethodget_pooling_mode_str
Returns the pooling mode as string
sentence_transformers/models/Pooling.py:54
↓ 1 callersMethodget_sentence_features
(self, tokenized_texts: List[List[int]], pad_seq_length: int = 0)
sentence_transformers/models/BoW.py:59
↓ 1 callersMethodget_train_objective_info
(dataloader, loss)
sentence_transformers/model_card_templates.py:146
↓ 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/losses/BatchHardTripletLoss.py:146
↓ 1 callersMethodget_vocab
(self, vocab: Iterable[str])
sentence_transformers/models/tokenizer/WordTokenizer.py:13
↓ 1 callersFunctionhttp_get
Downloads a URL to a given path on disc
sentence_transformers/util.py:260
↓ 1 callersFunctionk
(t,r)
docs/_static/js/custom.js:23
↓ 1 callersMethodmap_label
(self, label)
sentence_transformers/readers/NLIDataReader.py:46
↓ 1 callersMethodmodel_card_get_pooling_function
(pooling_mode)
sentence_transformers/model_card_templates.py:120
↓ 1 callersMethodnext_entry
(self, data_idx)
sentence_transformers/datasets/ParallelSentencesDataset.py:121
↓ 1 callersFunctionnormalize_embeddings
Normalizes the embeddings matrix, so that each sentence embedding has unit length
sentence_transformers/util.py:93
↓ 1 callersMethodoutput_scores
(self, scores)
sentence_transformers/evaluation/InformationRetrievalEvaluator.py:274
↓ 1 callersFunctionpairwise_dot_score
Computes the pairwise dot-product dot_prod(a[i], b[i]) :return: Vector with res[i] = dot_prod(a[i], b[i])
sentence_transformers/util.py:65
↓ 1 callersFunctionparaphrase_mining
Given a list of sentences / texts, this function performs paraphrase mining. It compares all sentences against all other sentences and return
sentence_transformers/util.py:100
↓ 1 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.py:128
↓ 1 callersFunctionparseGithubButtons
* modified to run programmatically
docs/_static/js/custom.js:23
↓ 1 callersFunctionpytorch_cos_sim
Computes the cosine similarity cos_sim(a[i], b[j]) for all i and j. :return: Matrix with res[i][j] = cos_sim(a[i], b[j])
sentence_transformers/util.py:16
↓ 1 callersFunctionr
(n)
docs/_themes/sphinx_rtd_theme/static/js/badge_only.js:1
↓ 1 callersFunctionread_eval_dataset
(filepath)
examples/unsupervised_learning/SimCSE/train_askubuntu_simcse.py:46
↓ 1 callersFunctionread_eval_dataset
(filepath)
examples/unsupervised_learning/CT/train_askubuntu_ct.py:46
↓ 1 callersFunctionread_eval_dataset
(filepath)
examples/unsupervised_learning/TSDAE/train_askubuntu_tsdae.py:40
↓ 1 callersFunctionread_eval_dataset
(filepath)
examples/unsupervised_learning/TSDAE/eval_askubuntu.py:47
↓ 1 callersFunctionread_eval_dataset
(filepath)
examples/unsupervised_learning/CT_In-Batch_Negatives/train_askubuntu_ct-improved.py:47
↓ 1 callersMethodretokenize
(self, sentence_features)
sentence_transformers/losses/DenoisingAutoEncoderLoss.py:80
↓ 1 callersFunctionscore
(x, y, fwd_mean, bwd_mean, margin)
examples/applications/parallel-sentence-mining/bitext_mining_utils.py:16
↓ 1 callersFunctionsearch_papers
(title, abstract)
examples/applications/semantic-search/semantic_search_publications.py:37
↓ 1 callersFunctionsemantic_search
This function performs a cosine similarity search between a list of query embeddings and a list of corpus embeddings. It can be used for Inf
sentence_transformers/util.py:196
↓ 1 callersMethodset_vocab
(self, vocab: Iterable[str])
sentence_transformers/models/tokenizer/WhitespaceTokenizer.py:21
↓ 1 callersMethodset_vocab
(self, vocab: Iterable[str])
sentence_transformers/models/tokenizer/PhraseTokenizer.py:29
↓ 1 callersMethodset_vocab
(self, vocab: Iterable[str])
sentence_transformers/models/tokenizer/WordTokenizer.py:9
↓ 1 callersFunctionsetup
(app)
docs/conf.py:108
↓ 1 callersFunctionsnapshot_download
Method derived from huggingface_hub. Adds a new parameters 'ignore_files', which allows to ignore certain files / file-patterns
sentence_transformers/util.py:410
↓ 1 callersFunctionstationary_distribution
( transition_matrix, increase_power=True, normalized=True, )
examples/applications/text-summarization/LexRank.py:106
↓ 1 callersMethodstop_multi_process_pool
Stops all processes started with start_multi_process_pool
sentence_transformers/SentenceTransformer.py:237
↓ 1 callersFunctiont
(i)
docs/_themes/sphinx_rtd_theme/static/js/theme.js:1
↓ 1 callersMethodtokenize
(self, texts: List[str])
sentence_transformers/models/BoW.py:52
↓ 1 callersFunctiontrec_dataset
( directory="datasets/trec/", train_filename="train_5500.label", test_filename="TREC_10.label",
examples/training/other/training_batch_hard_trec.py:40
↓ 1 callersFunctiontriplets_from_labeled_dataset
(input_examples)
examples/training/other/training_batch_hard_trec.py:89
↓ 1 callersFunctionwrite_mining_files
(name, ids, dups)
examples/training/quora_duplicate_questions/create_splits.py:283
↓ 1 callersFunctionwrite_qids
(name, ids_list)
examples/training/quora_duplicate_questions/create_splits.py:272
Method__call__
(self, model, output_path: str = None, epoch: int = -1, steps: int = -1)
sentence_transformers/cross_encoder/evaluation/CEBinaryAccuracyEvaluator.py:40
Method__call__
(self, model, output_path: str = None, epoch: int = -1, steps: int = -1)
sentence_transformers/cross_encoder/evaluation/CERerankingEvaluator.py:30
Method__call__
(self, model, output_path: str = None, epoch: int = -1, steps: int = -1)
sentence_transformers/cross_encoder/evaluation/CECorrelationEvaluator.py:36
Method__call__
(self, model, output_path: str = None, epoch: int = -1, steps: int = -1)
sentence_transformers/cross_encoder/evaluation/CEBinaryClassificationEvaluator.py:42
Method__call__
(self, model, output_path: str = None, epoch: int = -1, steps: int = -1)
sentence_transformers/cross_encoder/evaluation/CESoftmaxAccuracyEvaluator.py:37
Method__call__
(self, model, output_path: str = None, epoch: int = -1, steps: int = -1)
sentence_transformers/evaluation/EmbeddingSimilarityEvaluator.py:66
Method__call__
(self, model, output_path: str = None, epoch: int = -1, steps: int = -1)
sentence_transformers/evaluation/MSEEvaluatorFromDataFrame.py:62
Method__call__
(self, model, output_path: str = None, epoch: int = -1, steps: int = -1)
sentence_transformers/evaluation/RerankingEvaluator.py:43
Method__call__
(self, model, output_path: str = None, epoch: int = -1, steps: int = -1, *args, **kwargs)
sentence_transformers/evaluation/InformationRetrievalEvaluator.py:90
Method__call__
(self, model, output_path: str = None, epoch: int = -1, steps: int = -1)
sentence_transformers/evaluation/SequentialEvaluator.py:15
Method__call__
(self, model, output_path: str = None, epoch: int = -1, steps: int = -1)
sentence_transformers/evaluation/TripletEvaluator.py:73
Method__call__
(self, model, output_path: str = None, epoch: int = -1, steps: int = -1)
sentence_transformers/evaluation/BinaryClassificationEvaluator.py:71
Method__call__
(self, model, output_path: str = None, epoch: int = -1, steps: int = -1)
sentence_transformers/evaluation/ParaphraseMiningEvaluator.py:80
Method__call__
This is called during training to evaluate the model. It returns a score for the evaluation with a higher score indicating a better r
sentence_transformers/evaluation/SentenceEvaluator.py:8
Method__call__
(self, model, output_path, epoch = -1, steps = -1)
sentence_transformers/evaluation/MSEEvaluator.py:40
Method__call__
(self, model, output_path: str = None, epoch: int = -1, steps: int = -1)
sentence_transformers/evaluation/TranslationEvaluator.py:51
Method__call__
(self, model, output_path: str = None, epoch: int = -1, steps: int = -1)
sentence_transformers/evaluation/LabelAccuracyEvaluator.py:39
Method__getitem__
(self, item)
sentence_transformers/datasets/SentencesDataset.py:19
Method__getitem__
(self, item)
sentence_transformers/datasets/DenoisingAutoEncoderDataset.py:22
Method__getitem__
(self, idx)
sentence_transformers/datasets/ParallelSentencesDataset.py:151
Method__getitem__
(self, item)
examples/unsupervised_learning/MLM/train_mlm.py:72
Method__getitem__
(self, item)
examples/training/ms_marco/train_bi-encoder_mnrl.py:207
Method__getitem__
(self, item)
examples/training/ms_marco/train_bi-encoder_margin-mse.py:190
Method__init__
(self, model_name_or_path: Optional[str] = None, modules: Optional[Iterable[nn.Module]] = Non
sentence_transformers/SentenceTransformer.py:43
Method__init__
(self, level=logging.NOTSET)
sentence_transformers/LoggingHandler.py:5
Method__init__
A CrossEncoder takes exactly two sentences / texts as input and either predicts a score or label for this sentence pair. It can for e
sentence_transformers/cross_encoder/CrossEncoder.py:21
Method__init__
(self, sentence_pairs: List[List[str]], labels: List[int], name: str='', threshold: float = 0.5, write_csv: bo
sentence_transformers/cross_encoder/evaluation/CEBinaryAccuracyEvaluator.py:20
Method__init__
(self, samples, mrr_at_k: int = 10, name: str = '', write_csv: bool = True)
sentence_transformers/cross_encoder/evaluation/CERerankingEvaluator.py:18
Method__init__
(self, sentence_pairs: List[List[str]], scores: List[float], name: str='', write_csv: bool = True)
sentence_transformers/cross_encoder/evaluation/CECorrelationEvaluator.py:17
Method__init__
(self, sentence_pairs: List[List[str]], labels: List[int], name: str='', write_csv: bool = True)
sentence_transformers/cross_encoder/evaluation/CEBinaryClassificationEvaluator.py:19
Method__init__
(self, sentence_pairs: List[List[str]], labels: List[int], name: str='', write_csv: bool = True)
sentence_transformers/cross_encoder/evaluation/CESoftmaxAccuracyEvaluator.py:18
Method__init__
Creates a LabelSampler for a SentenceLabelDataset. :param examples: a list with InputExamples :param samples_per
sentence_transformers/datasets/SentenceLabelDataset.py:25
Method__init__
(self, examples: List[InputExample], model: SentenceTransformer
sentence_transformers/datasets/SentencesDataset.py:12
Method__init__
A special data loader to be used with MultipleNegativesRankingLoss. The data loader ensures that there are no duplicate sentences wit
sentence_transformers/datasets/NoDuplicatesDataLoader.py:6
Method__init__
(self, sentences: List[str], noise_fn=lambda s: DenoisingAutoEncoderDataset.delete(s))
sentence_transformers/datasets/DenoisingAutoEncoderDataset.py:17
Method__init__
Parallel sentences dataset reader to train student model given a teacher model :param student_model: Student sentence embedding model
sentence_transformers/datasets/ParallelSentencesDataset.py:29
Method__init__
(self, model_name_or_path: str, max_seq_length: Optional[int] = None, model_args: Dict = {},
sentence_transformers/models/Transformer.py:20
Method__init__
(self, vocab: List[str], word_weights: Dict[str, float] = {}, unknown_word_weight: float = 1, cumulative_term_
sentence_transformers/models/BoW.py:20
Method__init__
(self, tokenizer: WordTokenizer, embedding_weights, update_embeddings: bool = False, max_seq_length: int = 100
sentence_transformers/models/WordEmbeddings.py:17
Method__init__
(self, dimension: int)
sentence_transformers/models/LayerNorm.py:10
Method__init__
(self, in_features: int, out_features: int, bias: bool = True, activation_function=nn.Tanh(), init_weight: Ten
sentence_transformers/models/Dense.py:23
Method__init__
(self, dropout: float = 0.2)
sentence_transformers/models/Dropout.py:14
Method__init__
:param vocab: Vocabulary of the tokenizer :param word_weights: Mapping of tokens to a float weight value. Wo
sentence_transformers/models/WordWeights.py:15
Method__init__
(self, model_name: str = "openai/clip-vit-base-patch32", processor_name = None)
sentence_transformers/models/CLIPModel.py:8
Method__init__
(self, in_word_embedding_dimension: int, out_channels: int = 256, kernel_sizes: List[int] = [1, 3, 5], stride_
sentence_transformers/models/CNN.py:17
Method__init__
This model allows to create asymmetric SentenceTransformer models, that apply different models depending on the specified input key.
sentence_transformers/models/Asym.py:11
Method__init__
(self)
sentence_transformers/models/Normalize.py:10
Method__init__
(self, word_embedding_dimension, num_hidden_layers: int = 12, layer_start: int = 4, layer_weights = None)
sentence_transformers/models/WeightedLayerPooling.py:13
Method__init__
(self, word_embedding_dimension: int, pooling_mode: str = None,
sentence_transformers/models/Pooling.py:22
Method__init__
(self, word_embedding_dimension: int, hidden_dim: int, num_layers: int = 1, dropout: float = 0, bidirectional:
sentence_transformers/models/LSTM.py:13
Method__init__
(self, vocab: Iterable[str] = [], stop_words: Iterable[str] = ENGLISH_STOP_WORDS, do_lower_case: bool = False)
sentence_transformers/models/tokenizer/WhitespaceTokenizer.py:13
Method__init__
(self, vocab: Iterable[str] = [], stop_words: Iterable[str] = ENGLISH_STOP_WORDS, do_lower_case: bool = False,
sentence_transformers/models/tokenizer/PhraseTokenizer.py:19
Method__init__
:param model: SentenceTransformer model
sentence_transformers/losses/ContrastiveTensionLoss.py:45
Method__init__
(self, sentences, batch_size, pos_neg_ratio=8)
sentence_transformers/losses/ContrastiveTensionLoss.py:72
Method__init__
(self, model: SentenceTransformer, loss_fct = nn.MSELoss(), cos_score_transformation=nn.Identity())
sentence_transformers/losses/CosineSimilarityLoss.py:31
Method__init__
(self, model: SentenceTransformer, distance_metric=SiameseDistanceMetric.COSINE_DISTANCE, margin: float = 0.5,
sentence_transformers/losses/ContrastiveLoss.py:46
Method__init__
:param model: SentenceTransformer model :param scale: Output of similarity function is multiplied by scale value :param simil
sentence_transformers/losses/MultipleNegativesSymmetricRankingLoss.py:32
Method__init__
(self, model: SentenceTransformer, sentence_embedding_dimension: int,
sentence_transformers/losses/SoftmaxLoss.py:35
← previousnext →101–200 of 404, ranked by callers