sentence-transformers
Embeddings, Retrieval, and Reranking
Description
<!--- BADGES: START ---> [](https://huggingface.co/models?library=sentence-transformers) [][#github-license] [][#pypi-package] [][#pypi-package] [][#docs-package] <!-- [][#pypi-package] --> <!--- BADGES: END ---> # Sentence Transformers: Embeddings, Retrieval, and Reranking This framework provides an easy method to compute embeddings for accessing, using, and training state-of-the-art embedding and reranker models. It can be used to compute embeddings using Sentence Transformer models ([quickstart](https://sbert.net/docs/quickstart.html#sentence-transformer)), to calculate similarity scores using Cross-Encoder (a.k.a. reranker) models ([quickstart](https://sbert.net/docs/quickstart.html#cross-encoder)) or to generate sparse embeddings using Sparse Encoder models ([quickstart](https://sbert.net/docs/quickstart.html#sparse-encoder)). This unlocks a wide range of applications, including [semantic search](https://sbert.net/examples/applications/semantic-search/README.html), [semantic textual similarity](https://sbert.net/docs/sentence_transformer/usage/semantic_textual_similarity.html), and [paraphrase mining](https://sbert.net/examples/applications/paraphrase-mining/README.html). A wide selection of over [15,000 pre-trained Sentence Transformers models](https://huggingface.co/models?library=sentence-transformers) are available for immediate use on 🤗 Hugging Face, including many of the state-of-the-art models from the [Massive Text Embeddings Benchmark (MTEB) leaderboard](https://huggingface.co/spaces/mteb/leaderboard). Additionally, it is easy to train or finetune your own [embedding models](https://sbert.net/docs/sentence_transformer/training_overview.html), [reranker models](https://sbert.net/docs/cross_encoder/training_overview.html) or [sparse encoder models](https://sbert.net/docs/sparse_encoder/training_overview.html) using Sentence Transformers, enabling you to create custom models for your specific use cases. For the **full documentation**, see **[www.SBERT.net](https://www.sbert.net)**. ## Installation We recommend **Python 3.10+**, **[PyTorch 1.11.0+](https://pytorch.org/get-started/locally/)**, and **[transformers v4.34.0+](https://github.com/huggingface/transformers)**. **Install with pip** ``` pip install -U sentence-transformers ``` **Install with conda** ``` conda install -c conda-forge sentence-transformers ``` **Install from sources** Alternatively, you can also clone the latest version from the [repository](https://github.com/huggingface/sentence-transformers) and install it directly from the source code: ``` pip install -e . ``` **PyTorch with CUDA** If you want to use a GPU / CUDA, you must install PyTorch with the matching CUDA Version. Follow [PyTorch - Get Started](https://pytorch.org/get-started/locally/) for further details how to install PyTorch. ## Getting Started See [Quickstart](https://www.sbert.net/docs/quickstart.html) in our documentation. ### Embedding Models First download a pretrained embedding a.k.a. Sentence Transformer model. ```python from sentence_transformers import SentenceTransformer model = SentenceTransformer("sentence-transformers/all-MiniLM-L6-v2") ``` Then provide some texts to the model. ```python sentences = [ "The weather is lovely today.", "It's so sunny outside!", "He drove to the stadium.", ] embeddings = model.encode(sentences) print(embeddings.shape) # => (3, 384) ``` And that's already it. We now have numpy arrays with the embeddings, one for each text. We can use these to compute similarities. ```python similarities = model.similarity(embeddings, embeddings) print(similarities) # tensor([[1.0000, 0.6660, 0.1046], # [0.6660, 1.0000, 0.1411], # [0.1046, 0.1411, 1.0000]]) ``` ### Reranker Models First download a pretrained reranker a.k.a. Cross Encoder model. ```python from sentence_transformers import CrossEncoder # 1. Load a pretrained CrossEncoder model model = CrossEncoder("cross-encoder/ms-marco-MiniLM-L6-v2") ``` Then provide some texts to the model. ```python # The texts for which to predict similarity scores query = "How many people live in Berlin?" passages = [ "Berlin had a population of 3,520,031 registered inhabitants in an area
Release History
| Version | Changes | Urgency | Date |
|---|---|---|---|
| 5.4.1 | Imported from PyPI (5.4.1) | Low | 4/21/2026 |
| v5.4.1 | This patch release allows `encode()` and `predict()` to accept 1D numpy string arrays as inputs. Install this version with ```bash # Training + Inference pip install sentence-transformers[train]==5.4.1 # Inference only, use one of: pip install sentence-transformers==5.4.1 pip install sentence-transformers[onnx-gpu]==5.4.1 pip install sentence-transformers[onnx]==5.4.1 pip install sentence-transformers[openvino]==5.4.1 # Multimodal dependencies (optional): pip install sentence-tr | Medium | 4/14/2026 |
| v5.4.0 | This large release introduces first-class multimodal support for both `SentenceTransformer` and `CrossEncoder`, making it easy to compute embeddings and rerank across text, images, audio, and video. The `CrossEncoder` class has been fully modularized, allowing for generative rerankers (CausalLM-based models) via a new `LogitScore` module. Flash Attention 2 now automatically skips padding for text-only inputs, providing significant speedups & memory reductions, especially when input lengths vary. | Medium | 4/9/2026 |
| v5.3.0 | This minor version brings several improvements to contrastive learning: `MultipleNegativesRankingLoss` now supports alternative InfoNCE formulations (symmetric, GTE-style) and optional hardness weighting for harder negatives. Two new losses are introduced, `GlobalOrthogonalRegularizationLoss` for embedding space regularization and `CachedSpladeLoss` for memory-efficient SPLADE training. The release also adds a faster hashed batch sampler, fixes `GroupByLabelBatchSampler` for triplet losses, and | Low | 3/12/2026 |
| v5.2.3 | This patch release introduces compatibility with Transformers v5.2. Install this version with ```bash # Training + Inference pip install sentence-transformers[train]==5.2.3 # Inference only, use one of: pip install sentence-transformers==5.2.3 pip install sentence-transformers[onnx-gpu]==5.2.3 pip install sentence-transformers[onnx]==5.2.3 pip install sentence-transformers[openvino]==5.2.3 ``` ## Transformers v5.2 Support [Transformers v5.2](https://github.com/huggingface/tra | Low | 2/17/2026 |
| v5.2.2 | This patch release replaces mandatory `requests` dependency with an optional `httpx` dependency. Install this version with ```bash # Training + Inference pip install sentence-transformers[train]==5.2.2 # Inference only, use one of: pip install sentence-transformers==5.2.2 pip install sentence-transformers[onnx-gpu]==5.2.2 pip install sentence-transformers[onnx]==5.2.2 pip install sentence-transformers[openvino]==5.2.2 ``` ## Transformers v5 Support [Transformers v5.0](https:/ | Low | 1/27/2026 |
| v5.2.1 | This patch release adds support for the full [Transformers v5 release](https://github.com/huggingface/transformers/releases/tag/v5.0.0). Install this version with ```bash # Training + Inference pip install sentence-transformers[train]==5.2.1 # Inference only, use one of: pip install sentence-transformers==5.2.1 pip install sentence-transformers[onnx-gpu]==5.2.1 pip install sentence-transformers[onnx]==5.2.1 pip install sentence-transformers[openvino]==5.2.1 ``` ## Transformer | Low | 1/26/2026 |
| v5.2.0 | This minor release introduces multi-processing for CrossEncoder (rerankers), multilingual NanoBEIR evaluators, similarity score outputs in `mine_hard_negatives`, Transformers v5 support, Python 3.9 deprecations, and more. Install this version with ```bash # Training + Inference pip install sentence-transformers[train]==5.2.0 # Inference only, use one of: pip install sentence-transformers==5.2.0 pip install sentence-transformers[onnx-gpu]==5.2.0 pip install sentence-transformers[onn | Low | 12/11/2025 |
| v5.1.2 | This patch celebrates the transition of Sentence Transformers to Hugging Face, and improves model saving, loading defaults, and loss compatibilities. Install this version with ```bash # Training + Inference pip install sentence-transformers[train]==5.1.2 # Inference only, use one of: pip install sentence-transformers==5.1.2 pip install sentence-transformers[onnx-gpu]==5.1.2 pip install sentence-transformers[onnx]==5.1.2 pip install sentence-transformers[openvino]==5.1.2 ``` # | Low | 10/22/2025 |
| v5.1.1 | This patch makes Sentence Transformers more explicit with incorrect arguments and introduces some fixes for multi-GPU processing, evaluators, and hard negatives mining. Install this version with ```bash # Training + Inference pip install sentence-transformers[train]==5.1.1 # Inference only, use one of: pip install sentence-transformers==5.1.1 pip install sentence-transformers[onnx-gpu]==5.1.1 pip install sentence-transformers[onnx]==5.1.1 pip install sentence-transformers[openvino | Low | 9/22/2025 |
| v5.1.0 | This release introduces 2 new efficient computing backends for SparseEncoder embedding models: [ONNX and OpenVINO + optimization & quantization, allowing for speedups up to 2x-3x](https://sbert.net/docs/sparse_encoder/usage/efficiency.html); a new "n-tuple-score" output format for hard negative mining for distillation; gathering across devices for free lunch on multi-gpu training; trackio support; MTEB documentation; any many small fixes and features. Install this version with ```bash # T | Low | 8/6/2025 |
| v5.0.0 | This release consists of significant updates including the introduction of Sparse Encoder models, new methods `encode_query` and `encode_document`, multi-processing support in `encode`, the `Router` module for asymmetric models, custom learning rates for parameter groups, composite loss logging, and various small improvements and bug fixes. Install this version with ```bash # Training + Inference pip install sentence-transformers[train]==5.0.0 # Inference only, use one of: pip instal | Low | 7/1/2025 |
| v4.1.0 | This release introduces 2 new efficient computing backends for CrossEncoder (reranker) models: [ONNX and OpenVINO + optimization & quantization, allowing for speedups up to 2x-3x](https://sbert.net/docs/cross_encoder/usage/efficiency.html); improved hard negatives mining strategies, and minor improvements. Install this version with ```bash # Training + Inference pip install sentence-transformers[train]==4.1.0 # Inference only, use one of: pip install sentence-transformers==4.1.0 pip i | Low | 4/15/2025 |
| v4.0.2 | This patch release updates some logic for maximum sequence lengths, typing issues, FSDP training, and distributed training device placement. Install this version with ```bash # Training + Inference pip install sentence-transformers[train]==4.0.2 # Inference only, use one of: pip install sentence-transformers==4.0.2 pip install sentence-transformers[onnx-gpu]==4.0.2 pip install sentence-transformers[onnx]==4.0.2 pip install sentence-transformers[openvino]==4.0.2 ``` ## Safer Cros | Low | 4/3/2025 |
| v4.0.1 | This release consists of a major refactor that overhauls the reranker a.k.a. Cross Encoder [training approach](https://huggingface.co/blog/train-reranker) (introducing multi-gpu training, bf16, loss logging, callbacks, and much more), including all new [Training Overview](https://sbert.net/docs/cross_encoder/training_overview.html), [Loss Overview](https://sbert.net/docs/cross_encoder/loss_overview.html), [API Reference](https://sbert.net/docs/package_reference/cross_encoder/index.html) docs, [t | Low | 3/26/2025 |
| v3.4.1 | This release introduces a convenient compatibility with [Model2Vec models](https://huggingface.co/models?library=model2vec), and fixes a bug that caused an outgoing request even when using a local model. Install this version with ```bash # Training + Inference pip install sentence-transformers[train]==3.4.1 # Inference only, use one of: pip install sentence-transformers==3.4.1 pip install sentence-transformers[onnx-gpu]==3.4.1 pip install sentence-transformers[onnx]==3.4.1 pip ins | Low | 1/29/2025 |
| v3.4.0 | This release resolves a memory leak when deleting a model & trainer, adds compatibility between the Cached... losses and the Matryoshka loss modifier, resolves numerous bugs, and adds several small features. Install this version with ```bash # Training + Inference pip install sentence-transformers[train]==3.4.0 # Inference only, use one of: pip install sentence-transformers==3.4.0 pip install sentence-transformers[onnx-gpu]==3.4.0 pip install sentence-transformers[onnx]==3.4.0 pip i | Low | 1/23/2025 |
| v3.3.1 | This patch release fixes a small issue with loading private models from Hugging Face using the `token` argument. Install this version with ``` # Training + Inference pip install sentence-transformers[train]==3.3.1 # Inference only, use one of: pip install sentence-transformers==3.3.1 pip install sentence-transformers[onnx-gpu]==3.3.1 pip install sentence-transformers[onnx]==3.3.1 pip install sentence-transformers[openvino]==3.3.1 ``` ## Details If you're loading model under thi | Low | 11/18/2024 |
| v3.3.0 | 4x speedup for CPU with [OpenVINO int8 static quantization](https://sbert.net/docs/sentence_transformer/usage/efficiency.html#quantizing-openvino-models), [training with prompts for a free performance boost](https://sbert.net/examples/training/prompts/README.html), convenient evaluation on [NanoBEIR](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#nanobeirevaluator): a subset of a strong Information Retrieval benchmark, PEFT compatibility by easily adding/loading ad | Low | 11/11/2024 |
| v3.2.1 | This patch release fixes some small bugs, such as related to loading CLIP models, automatic model card generation issues, and ensuring compatibility with third party libraries. Install this version with ```bash # Training + Inference pip install sentence-transformers[train]==3.2.1 # Inference only, use one of: pip install sentence-transformers==3.2.1 pip install sentence-transformers[onnx-gpu]==3.2.1 pip install sentence-transformers[onnx]==3.2.1 pip install sentence-transformers[op | Low | 10/21/2024 |
| v3.2.0 | This release introduces 2 new efficient computing backends for SentenceTransformer models: [ONNX and OpenVINO + optimization & quantization, allowing for speedups up to 2x-3x](https://sbert.net/docs/sentence_transformer/usage/efficiency.html); static embeddings via [Model2Vec](https://github.com/MinishLab/model2vec) allowing for lightning-fast models (i.e., 50x-500x speedups) at a ~10%-20% performance cost; and various small improvements and fixes. Install this version with ```bash # Traini | Low | 10/10/2024 |
| v3.1.1 | This patch release fixes hard negatives mining for models that don't automatically normalize their embeddings and it lifts the `numpy<2` restriction that was previously required. Install this version with ```bash # Full installation: pip install sentence-transformers[train]==3.1.1 # Inference only: pip install sentence-transformers==3.1.1 ``` ## Hard Negatives Mining Patch (#2944) The [`mine_hard_negatives`](https://sbert.net/docs/package_reference/util.html#sentence_transformers. | Low | 9/19/2024 |
| v3.1.0 | This release introduces a [hard negatives mining utility](https://sbert.net/docs/package_reference/util.html#sentence_transformers.util.mine_hard_negatives) to get better models out of your data, a new strong [loss function](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#cachedmultiplenegativessymmetricrankingloss) for symmetric tasks, training with streaming datasets to avoid having to store datasets fully on disk, custom modules to allow for more creativity from mode | Low | 9/11/2024 |
| v3.0.1 | This patch release introduces some improvements for the SentenceTransformerTrainer, as well as some updates for the automatic model card generation. It also patches some minor evaluator bugs and a bug with `MatryoshkaLoss`. Lastly, every single Sentence Transformer model can now be saved and loaded with the safer `model.safetensors` files. Install this version with ```bash # Full installation: pip install sentence-transformers[train]==3.0.1 # Inference only: pip install sentence-transf | Low | 6/7/2024 |
| v3.0.0 | This release consists of a major refactor that overhauls the [training approach](https://huggingface.co/blog/train-sentence-transformers) (introducing multi-gpu training, bf16, loss logging, callbacks, and much more), adds convenient [`similarity`](https://sbert.net/docs/package_reference/sentence_transformer/SentenceTransformer.html#sentence_transformers.SentenceTransformer.similarity) and [`similarity_pairwise`](https://sbert.net/docs/package_reference/sentence_transformer/SentenceTransformer. | Low | 5/28/2024 |
| v2.7.0 | This release introduces a [new promising loss function](https://sbert.net/docs/package_reference/losses.html#cachedgistembedloss), easier inference for [Matryoshka models](https://sbert.net/examples/training/matryoshka/README.html), new functionality for CrossEncoders and Inference on Intel Gaudi2, along much more. Install this version with ``` pip install sentence-transformers==2.7.0 ``` ## New loss function: CachedGISTEmbedLoss (#2592) For a number of years, [`MultipleNegativesRankin | Low | 4/17/2024 |
| v2.6.1 | This is a patch release to fix a bug in [`semantic_search_faiss`](https://sbert.net/docs/package_reference/quantization.html#sentence_transformers.quantization.semantic_search_faiss) and [`semantic_search_usearch`](https://sbert.net/docs/package_reference/quantization.html#sentence_transformers.quantization.semantic_search_usearch) that caused the scores to not correspond to the returned corpus indices. Additionally, you can now evaluate embedding models after quantizing their embeddings. ## | Low | 3/26/2024 |
| v2.6.0 | This release brings embedding quantization: a way to heavily speed up retrieval & other tasks, and a new powerful loss function: GISTEmbedLoss. Install this version with ``` pip install sentence-transformers==2.6.0 ``` ## Embedding Quantization Embeddings may be challenging to scale up, which leads to expensive solutions and high latencies. However, there is a new approach to counter this problem; it entails reducing the size of each of the individual values in the embedding: **Quantiz | Low | 3/22/2024 |
| v2.5.1 | This is a patch release to fix a bug in `CrossEncoder.rank` that caused the last value to be discarded when using the default `top_k=-1`. ## `CrossEncoder.rank` patch: ```python from sentence_transformers.cross_encoder import CrossEncoder # Pre-trained cross encoder model = CrossEncoder("cross-encoder/stsb-distilroberta-base") # We want to compute the similarity between the query sentence query = "A man is eating pasta." # With all sentences in the corpus corpus = [ "A ma | Low | 3/1/2024 |
| v2.5.0 | This release brings two new loss functions, a new way to (re)rank with CrossEncoder models, and more fixes Install this version with ``` pip install sentence-transformers==2.5.0 ``` ## 2D Matryoshka & Adaptive Layer models (#2506) Embedding models are often encoder models with numerous layers, such as 12 (e.g. [all-mpnet-base-v2](https://huggingface.co/sentence-transformers/all-mpnet-base-v2)) or 6 (e.g. [all-MiniLM-L6-v2](https://huggingface.co/sentence-transformers/all-MiniLM-L6-v2)) | Low | 2/29/2024 |
| v2.4.0 | This release introduces numerous notable features that are well worth learning about! Install this version with ``` pip install sentence-transformers==2.4.0 ``` ## MatryoshkaLoss (#2485) Dense embedding models typically produce embeddings with a fixed size, such as 768 or 1024. All further computations (clustering, classification, semantic search, retrieval, reranking, etc.) must then be done on these full embeddings. [Matryoshka Representation Learning](https://arxiv.org/abs/2205.1314 | Low | 2/23/2024 |
| v2.3.1 | This releases patches a niche bug when loading a Sentence Transformer model which: 1. is local 2. uses a `Normalize` module as specified in `modules.json` 3. does not contain the directory specified in the model configuration This only occurs when a model with `Normalize` is downloaded from the Hugging Face hub and then later used locally. See #2458 and #2459 for more details. ## Release highlights * Don't require loading files for Normalize by @tomaarsen (#2460) **Full Changelog** | Low | 1/30/2024 |
| v2.3.0 | This release focuses on various bug fixes & improvements to keep up with adjacent works like `transformers` and `huggingface_hub`. These are the key changes in the release: # Pushing models to the Hugging Face Hub (#2376) Prior to Sentence Transformers v2.3.0, saving models to the Hugging Face Hub may have resulted in various errors depending on the versions of the dependencies. Sentence Transformers v2.3.0 introduces a refactor to [`save_to_hub`](https://sbert.net/docs/package_reference/S | Low | 1/29/2024 |
| v2.2.2 | `huggingface_hub` dropped support in version 0.5.0 for Python 3.6 This release fixes the issue so that `huggingface_hub` with version 0.4.0 and Python 3.6 can still be used. | Low | 6/26/2022 |
| v2.2.1 | Version `0.8.1` of `huggingface_hub` introduces several changes that resulted in errors and warnings. This version of `sentence-transformers` fixes these issues. Further, several improvements have been added / merged: - `util.community_detection` was improved: 1) It works in a batched mode to save memory, 2) Overlapping clusters are no longer dropped but removed by overlapping items, 3) The parameter `init_max_size` was removed and replaced by a heuristic to estimate the max size of cluster | Low | 6/23/2022 |
| v2.2.0 | # T5 You can now use the encoder from T5 to learn text embeddings. You can use it like any other transformer model: ```python from sentence_transformers import SentenceTransformer, models word_embedding_model = models.Transformer('t5-base', max_seq_length=256) pooling_model = models.Pooling(word_embedding_model.get_word_embedding_dimension()) model = SentenceTransformer(modules=[word_embedding_model, pooling_model]) ``` See [T5-Benchmark results](https://www.sbert.net/docs/training/ove | Low | 2/10/2022 |
| v2.1.0 | This is a smaller release with some new features ### MarginMSELoss [MarginMSELoss](https://github.com/UKPLab/sentence-transformers/blob/master/sentence_transformers/losses/MarginMSELoss.py) is a great method to train embeddings model with the help of a cross-encoder model. The details are explained here: [MSMARCO - MarginMSE Training](https://www.sbert.net/examples/training/ms_marco/README.html#marginmse) You pass your training data in the format: ```python InputExample(texts=[query, p | Low | 10/1/2021 |
| v2.0.0 | ## Models hosted on the hub All pre-trained models are now hosted on the [Huggingface Models hub](https://huggingface.co/models). Our pre-trained models can be found here: [https://huggingface.co/sentence-transformers](https://huggingface.co/sentence-transformers) But you can easily share your own sentence-transformer model on the hub and have other people easily access it. Simple upload the folder and have people load it via: ``` model = SentenceTransformer('[your_username]/[model_na | Low | 6/24/2021 |
| v1.2.1 | Final release of version 1: Makes v1 of sentence-transformers forward compatible with models from version 2 of sentence-transformers. | Low | 6/24/2021 |
| v1.2.0 | # Unsupervised Sentence Embedding Learning New methods integrated to train sentence embedding models without labeled data. See [Unsupervised Learning](https://github.com/UKPLab/sentence-transformers/tree/master/examples/unsupervised_learning) for an overview of all existent methods. New methods: - **[CT](https://github.com/UKPLab/sentence-transformers/tree/master/examples/unsupervised_learning/CT)**: Integration of [Semantic Re-Tuning With Contrastive Tension (CT)](https://openreview.n | Low | 5/12/2021 |
| v1.1.0 | ## Unsupervised Sentence Embedding Learning This release integrates methods that allows to learn sentence embeddings without having labeled data: - **[TSDAE](https://github.com/UKPLab/sentence-transformers/tree/master/examples/unsupervised_learning/TSDAE)**: TSDAE is using a denoising auto-encoder to learn sentence embeddings. The method has been presented in our [recent paper](https://arxiv.org/abs/2104.06979) and achieves state-of-the-art performance for several tasks. - **[GenQ](https://gi | Low | 4/21/2021 |
| v1.0.4 | It was not possible to fine-tune and save the CLIPModel. This release fixes it. CLIPModel can now be saved like any other model by calling `model.save(path)` | Low | 4/1/2021 |
| v1.0.3 | v1.0.3 - Patch for util.paraphrase_mining method | Low | 3/22/2021 |
| v1.0.2 | v1.0.2 - Patch for CLIPModel, new Image Examples - Bugfix in CLIPModel: Too long inputs raised a RuntimeError. Now they are truncated. - New util function: util.paraphrase_mining_embeddings, to find most similar embeddings in a matrix - **Image Clustering** and **Duplicate Image Detection** examples added: [more info](https://www.sbert.net/examples/applications/image-search/README.html#examples) | Low | 3/19/2021 |
| v1.0.0 | This release brings many new improvements and new features. Also, the version number scheme is updated. Now we use the format x.y.z with x: for major releases, y: smaller releases with new features, z: bugfixes ## Text-Image-Model CLIP You can now encode text and images in the same vector space using the OpenAI CLIP Model. You can use the model like this: ```python from sentence_transformers import SentenceTransformer, util from PIL import Image #Load CLIP model model = SentenceTransf | Low | 3/18/2021 |
| v0.4.1 | **Refactored Tokenization** - Faster tokenization speed: Using batched tokenization for training & inference - Now, all sentences in a batch are tokenized simoultanously. - Usage of the `SentencesDataset` no longer needed for training. You can pass your train examples directly to the DataLoader: ```python train_examples = [InputExample(texts=['My first sentence', 'My second sentence'], label=0.8), InputExample(texts=['Another pair', 'Unrelated sentence'], label=0.3)] train_dataloader = | Low | 1/4/2021 |
| v0.4.0 | - Updated the dependencies so that it works with Huggingface Transformers version 4. Sentence-Transformers still works with huggingface transformers version 3, but an update to version 4 of transformers is recommended. Future changes might break with transformers version 3. - New naming of pre-trained models. Models will be named: {task}-{transformer_model}. So 'bert-base-nli-stsb-mean-tokens' becomes 'stsb-bert-base'. Models will still be available under their old names, but newer models will | Low | 12/22/2020 |
| v0.3.9 | This release only include some smaller updates: - Code was tested with transformers 3.5.1, requirement was updated so that it works with transformers 3.5.1 - As some parts and models require Pytorch >= 1.6.0, requirement was updated to require at least pytorch 1.6.0. Most of the code and models will work with older pytorch versions. - model.encode() stored the embeddings on the GPU, which required quite a lot of GPU memory when encoding millions of sentences. The embeddings are now moved to | Low | 11/18/2020 |
| v0.3.8 | - Add support training and using [CrossEncoder](https://www.sbert.net/docs/usage/cross-encoder.html) - Data Augmentation method [AugSBERT](https://www.sbert.net/examples/training/data_augmentation/README.html) added - New model trained on large scale paraphrase data. Models works on internal benchmark much better than previous models: **distilroberta-base-paraphrase-v1** and **xlm-r-distilroberta-base-paraphrase-v1** - New model for Information Retrieval trained on MS Marco: **distilroberta-b | Low | 10/19/2020 |
| v0.3.7 | - Upgrade transformers dependency, transformers 3.1.0, 3.2.0 and 3.3.1 are working - Added example code for model distillation: Sentence Embeddings models can be drastically reduced to e.g. only 2-4 layers while keeping 98+% of their performance. Code can be found in examples/training/distillation - Transformer models can now accepts two inputs ['sentence 1', 'context for sent1'], which are encoded as the two inputs for BERT. Minor changes: - Tokenization in the multi-processes encoding | Low | 9/29/2020 |
| v0.3.6 | Hugginface Transformers version 3.1.0 had a breaking change with previous version 3.0.2 This release fixes the issue so that Sentence-Transformers is compatible with Huggingface Transformers 3.1.0. Note, that this and future version will not be compatible with transformers < 3.1.0. | Low | 9/11/2020 |
Dependencies & License Audit
Loading dependencies...
Similar Packages
transformersTransformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.5.5.4
azure-storage-blobMicrosoft Azure Blob Storage Client Library for Pythonazure-template_0.1.0b6187637