Merge branch 'master' into v5.1-release

Author: tomaarsen

.github/workflows/tests.yml

@@ -15,12 +15,11 @@ env:
   TRANSFORMERS_IS_CI: 1
 
 jobs:
-
   test_sampling:
     name: Run unit tests
     strategy:
       matrix:
-        python-version: ['3.9', '3.10', '3.11', '3.12']
+        python-version: ["3.9", "3.10", "3.11", "3.12", "3.13"]
         os: [ubuntu-latest, windows-latest]
       fail-fast: false
     runs-on: ${{ matrix.os }}
@@ -71,7 +70,7 @@ jobs:
 
       - name: Install model2vec
         run: python -m pip install model2vec
-        if: ${{ contains(fromJSON('["3.10", "3.11", "3.12"]'), matrix.python-version) }}
+        if: ${{ contains(fromJSON('["3.10", "3.11", "3.12", "3.13"]'), matrix.python-version) }}
 
       - name: Run unit tests
         run: |

NOTICE.txt

@@ -1,5 +1,10 @@
 -------------------------------------------------------------------------------
-Copyright 2019
+Sentence Transformers
+
+Copyright 2019-2025
 Ubiquitous Knowledge Processing (UKP) Lab
 Technische Universität Darmstadt
+
+Copyright 2025-present
+Hugging Face, Inc.
 -------------------------------------------------------------------------------

README.md

@@ -1,15 +1,13 @@
 <!--- BADGES: START --->
+
 [![HF Models](https://img.shields.io/badge/%F0%9F%A4%97-models-yellow)](https://huggingface.co/models?library=sentence-transformers)
 [![GitHub - License](https://img.shields.io/github/license/UKPLab/sentence-transformers?logo=github&style=flat&color=green)][#github-license]
 [![PyPI - Python Version](https://img.shields.io/pypi/pyversions/sentence-transformers?logo=pypi&style=flat&color=blue)][#pypi-package]
 [![PyPI - Package Version](https://img.shields.io/pypi/v/sentence-transformers?logo=pypi&style=flat&color=orange)][#pypi-package]
 [![Docs - GitHub.io](https://img.shields.io/static/v1?logo=github&style=flat&color=pink&label=docs&message=sentence-transformers)][#docs-package]
+
 <!-- [![PyPI - Downloads](https://img.shields.io/pypi/dm/sentence-transformers?logo=pypi&style=flat&color=green)][#pypi-package] -->
 
-[#github-license]: https://github.com/UKPLab/sentence-transformers/blob/master/LICENSE
-[#pypi-package]: https://pypi.org/project/sentence-transformers/
-[#conda-forge-package]: https://anaconda.org/conda-forge/sentence-transformers
-[#docs-package]: https://www.sbert.net/
 <!--- BADGES: END --->
 
 # Sentence Transformers: Embeddings, Retrieval, and Reranking
@@ -38,11 +36,11 @@ conda install -c conda-forge sentence-transformers
 
 **Install from sources**
 
-Alternatively, you can also clone the latest version from the [repository](https://github.com/UKPLab/sentence-transformers) and install it directly from the source code:
+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**
 
@@ -57,15 +55,15 @@ See [Quickstart](https://www.sbert.net/docs/quickstart.html) in our documentatio
 
 First download a pretrained embedding a.k.a. Sentence Transformer model.
 
-````python
+```python
 from sentence_transformers import SentenceTransformer
 
 model = SentenceTransformer("all-MiniLM-L6-v2")
-````
+```
 
 Then provide some texts to the model.
 
-````python
+```python
 sentences = [
     "The weather is lovely today.",
     "It's so sunny outside!",
@@ -74,17 +72,17 @@ sentences = [
 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
+```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
 
@@ -130,6 +128,7 @@ Query: How many people live in Berlin?
 - #1 (5.51): Berlin has a yearly total of about 135 million day visitors, making it one of the most-visited cities in the European Union.
 """
 ```
+
 ### Sparse Encoder Models
 
 First download a pretrained sparse embedding a.k.a. Sparse Encoder model.
@@ -168,27 +167,28 @@ print(f"Sparsity: {stats['sparsity_ratio']:.2%}")
 
 ## Pre-Trained Models
 
-We provide a large list of pretrained models for more than 100 languages. Some models are general purpose models, while others produce embeddings for specific use cases. 
+We provide a large list of pretrained models for more than 100 languages. Some models are general purpose models, while others produce embeddings for specific use cases.
 
-* [Pretrained Sentence Transformer (Embedding) Models](https://sbert.net/docs/sentence_transformer/pretrained_models.html)
-* [Pretrained Cross Encoder (Reranker) Models](https://sbert.net/docs/cross_encoder/pretrained_models.html)
-* [Pretrained Sparse Encoder (Sparse Embeddings) Models](https://sbert.net/docs/sparse_encoder/pretrained_models.html)
+- [Pretrained Sentence Transformer (Embedding) Models](https://sbert.net/docs/sentence_transformer/pretrained_models.html)
+- [Pretrained Cross Encoder (Reranker) Models](https://sbert.net/docs/cross_encoder/pretrained_models.html)
+- [Pretrained Sparse Encoder (Sparse Embeddings) Models](https://sbert.net/docs/sparse_encoder/pretrained_models.html)
 
 ## Training
 
-This framework allows you to fine-tune your own sentence embedding methods, so that you get task-specific sentence embeddings. You have various options to choose from in order to get perfect sentence embeddings for your specific task. 
+This framework allows you to fine-tune your own sentence embedding methods, so that you get task-specific sentence embeddings. You have various options to choose from in order to get perfect sentence embeddings for your specific task.
 
-* Embedding Models
-    * [Sentence Transformer > Training Overview](https://www.sbert.net/docs/sentence_transformer/training_overview.html)
-    * [Sentence Transformer > Training Examples](https://www.sbert.net/docs/sentence_transformer/training/examples.html) or [training examples on GitHub](https://github.com/UKPLab/sentence-transformers/tree/master/examples/sentence_transformer/training).
-* Reranker Models
-    * [Cross Encoder > Training Overview](https://www.sbert.net/docs/cross_encoder/training_overview.html)
-    * [Cross Encoder > Training Examples](https://www.sbert.net/docs/cross_encoder/training/examples.html) or [training examples on GitHub](https://github.com/UKPLab/sentence-transformers/tree/master/examples/cross_encoder/training).
-* Sparse Embedding Models
-    * [Sparse Encoder > Training Overview](https://www.sbert.net/docs/sparse_encoder/training_overview.html)
-    * [Sparse Encoder > Training Examples](https://www.sbert.net/docs/sparse_encoder/training/examples.html) or [training examples on GitHub](https://github.com/UKPLab/sentence-transformers/tree/master/examples/sparse_encoder/training).
+- Embedding Models
+  - [Sentence Transformer > Training Overview](https://www.sbert.net/docs/sentence_transformer/training_overview.html)
+  - [Sentence Transformer > Training Examples](https://www.sbert.net/docs/sentence_transformer/training/examples.html) or [training examples on GitHub](https://github.com/huggingface/sentence-transformers/tree/master/examples/sentence_transformer/training).
+- Reranker Models
+  - [Cross Encoder > Training Overview](https://www.sbert.net/docs/cross_encoder/training_overview.html)
+  - [Cross Encoder > Training Examples](https://www.sbert.net/docs/cross_encoder/training/examples.html) or [training examples on GitHub](https://github.com/huggingface/sentence-transformers/tree/master/examples/cross_encoder/training).
+- Sparse Embedding Models
+  - [Sparse Encoder > Training Overview](https://www.sbert.net/docs/sparse_encoder/training_overview.html)
+  - [Sparse Encoder > Training Examples](https://www.sbert.net/docs/sparse_encoder/training/examples.html) or [training examples on GitHub](https://github.com/huggingface/sentence-transformers/tree/master/examples/sparse_encoder/training).
 
 Some highlights across the different types of training are:
+
 - Support of various transformer networks including BERT, RoBERTa, XLM-R, DistilBERT, Electra, BART, ...
 - Multi-Lingual and multi-task learning
 - Evaluation during training to find optimal model
@@ -199,29 +199,36 @@ Some highlights across the different types of training are:
 You can use this framework for:
 
 - **Computing Sentence Embeddings**
+
   - [Dense Embeddings](https://www.sbert.net/examples/sentence_transformer/applications/computing-embeddings/README.html)
   - [Sparse Embeddings](https://www.sbert.net/examples/sparse_encoder/applications/computing_embeddings/README.html)
 
-- **Semantic Textual Similarity** 
+- **Semantic Textual Similarity**
+
   - [Dense STS](https://www.sbert.net/docs/sentence_transformer/usage/semantic_textual_similarity.html)
   - [Sparse STS](https://www.sbert.net/examples/sparse_encoder/applications/semantic_textual_similarity/README.html)
 
 - **Semantic Search**
-  - [Dense Search](https://www.sbert.net/examples/sentence_transformer/applications/semantic-search/README.html)  
+
+  - [Dense Search](https://www.sbert.net/examples/sentence_transformer/applications/semantic-search/README.html)
   - [Sparse Search](https://www.sbert.net/examples/sparse_encoder/applications/semantic_search/README.html)
 
 - **Retrieve & Re-Rank**
+
   - [Dense only Retrieval](https://www.sbert.net/examples/sentence_transformer/applications/retrieve_rerank/README.html)
   - [Sparse/Dense/Hybrid Retrieval](https://www.sbert.net/examples/sentence_transformer/applications/retrieve_rerank/README.html)
 
 - [Clustering](https://www.sbert.net/examples/sentence_transformer/applications/clustering/README.html)
+
 - [Paraphrase Mining](https://www.sbert.net/examples/sentence_transformer/applications/paraphrase-mining/README.html)
+
 - [Translated Sentence Mining](https://www.sbert.net/examples/sentence_transformer/applications/parallel-sentence-mining/README.html)
+
 - [Multilingual Image Search, Clustering & Duplicate Detection](https://www.sbert.net/examples/sentence_transformer/applications/image-search/README.html)
 
 and many more use-cases.
 
-For all examples, see [examples/sentence_transformer/applications](https://github.com/UKPLab/sentence-transformers/tree/master/examples/sentence_transformer/applications).
+For all examples, see [examples/sentence_transformer/applications](https://github.com/huggingface/sentence-transformers/tree/master/examples/sentence_transformer/applications).
 
 ## Development setup
 
@@ -243,7 +250,7 @@ pytest
 
 If you find this repository helpful, feel free to cite our publication [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://arxiv.org/abs/1908.10084):
 
-```bibtex 
+```bibtex
 @inproceedings{reimers-2019-sentence-bert,
     title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks",
     author = "Reimers, Nils and Gurevych, Iryna",
@@ -271,10 +278,18 @@ If you use one of the multilingual models, feel free to cite our publication [Ma
 
 Please have a look at [Publications](https://www.sbert.net/docs/publications.html) for our different publications that are integrated into SentenceTransformers.
 
-Maintainer: [Tom Aarsen](https://github.com/tomaarsen), 🤗 Hugging Face
+### Maintainers
 
-https://www.ukp.tu-darmstadt.de/
+Maintainer: [Tom Aarsen](https://github.com/tomaarsen), 🤗 Hugging Face
 
 Don't hesitate to open an issue if something is broken (and it shouldn't be) or if you have further questions.
 
+---
+
+This project was originally developed by the [Ubiquitous Knowledge Processing (UKP) Lab](https://www.ukp.tu-darmstadt.de/) at TU Darmstadt. We're grateful for their foundational work and continued contributions to the field.
+
 > This repository contains experimental software and is published for the sole purpose of giving additional background details on the respective publication.
+
+[#docs-package]: https://www.sbert.net/
+[#github-license]: https://github.com/huggingface/sentence-transformers/blob/master/LICENSE
+[#pypi-package]: https://pypi.org/project/sentence-transformers/

docs/_static/js/custom.js

@@ -153,11 +153,11 @@ def linkcode_resolve(domain, info):
         return None
     start, end = lines[1], lines[1] + len(lines[0]) - 1
 
-    return f"https://github.com/UKPLab/sentence-transformers/blob/master/{file}#L{start}-L{end}"
+    return f"https://github.com/huggingface/sentence-transformers/blob/master/{file}#L{start}-L{end}"
 
 
 def visit_download_reference(self, node):
-    root = "https://github.com/UKPLab/sentence-transformers/tree/master"
+    root = "https://github.com/huggingface/sentence-transformers/tree/master"
     atts = {"class": "reference download", "download": ""}
 
     if not self.builder.download_support:

docs/conf.py

@@ -28,6 +28,7 @@ Loss functions play a critical role in the performance of your fine-tuned Cross
 | `(query, [doc1, doc2, ..., docN])`                | `[score1, score2, ..., scoreN]`          | `1`                           | <ol style="margin-bottom: 0;line-height: inherit;"><li><a href="../package_reference/cross_encoder/losses.html#lambdaloss">`LambdaLoss`</a></li><li><a href="../package_reference/cross_encoder/losses.html#plistmleloss">`PListMLELoss`</a></li><li><a href="../package_reference/cross_encoder/losses.html#listnetloss">`ListNetLoss`</a></li><li><a href="../package_reference/cross_encoder/losses.html#ranknetloss">`RankNetLoss`</a></li><li><a href="../package_reference/cross_encoder/losses.html#listmleloss">`ListMLELoss`</a></li></ol> |
 
 ## Distillation
+
 These loss functions are specifically designed to be used when distilling the knowledge from one model into another.
 For example, when finetuning a small model to behave more like a larger & stronger one, or when finetuning a model to become multi-lingual.
 
@@ -40,12 +41,13 @@ For example, when finetuning a small model to behave more like a larger & strong
 | `(query, positive, negative_1, ..., negative_n) ` | `[gold_sim(query, positive), gold_sim(query, negative_i)...] `            | <a href="../package_reference/cross_encoder/losses.html#marginmseloss">`MarginMSELoss`</a> |
 
 ## Commonly used Loss Functions
+
 In practice, not all loss functions get used equally often. The most common scenarios are:
 
-* `(sentence_A, sentence_B) pairs` with `float similarity score` or `1 if positive, 0 if negative`: <a href="../package_reference/cross_encoder/losses.html#binarycrossentropyloss"><code>BinaryCrossEntropyLoss</code></a> is a traditional option that remains very challenging to outperform. 
-* `(anchor, positive) pairs` without any labels: combined with <a href="../package_reference/util.html#sentence_transformers.util.mine_hard_negatives"><code>mine_hard_negatives</code></a>
-    * with <code>output_format="labeled-list"</code>, then <a href="../package_reference/cross_encoder/losses.html#lambdaloss"><code>LambdaLoss</code></a> is frequently used for learning-to-rank tasks.
-    * with <code>output_format="labeled-pair"</code>, then <a href="../package_reference/cross_encoder/losses.html#binarycrossentropyloss"><code>BinaryCrossEntropyLoss</code></a> remains a strong option.
+- `(sentence_A, sentence_B) pairs` with `float similarity score` or `1 if positive, 0 if negative`: <a href="../package_reference/cross_encoder/losses.html#binarycrossentropyloss"><code>BinaryCrossEntropyLoss</code></a> is a traditional option that remains very challenging to outperform.
+- `(anchor, positive) pairs` without any labels: combined with <a href="../package_reference/util.html#sentence_transformers.util.mine_hard_negatives"><code>mine_hard_negatives</code></a>
+  - with <code>output_format="labeled-list"</code>, then <a href="../package_reference/cross_encoder/losses.html#lambdaloss"><code>LambdaLoss</code></a> is frequently used for learning-to-rank tasks.
+  - with <code>output_format="labeled-pair"</code>, then <a href="../package_reference/cross_encoder/losses.html#binarycrossentropyloss"><code>BinaryCrossEntropyLoss</code></a> remains a strong option.
 
 ## Custom Loss Functions
 
@@ -62,4 +64,4 @@ To get full support with the automatic model card generation, you may also wish
 - a ``citation`` property so your work gets cited in all models that train with the loss.
 
 Consider inspecting existing loss functions to get a feel for how loss functions are commonly implemented.
-```
+```