🤗 Announcing the Ettin Reranker family: six new CrossEncoder rerankers from 17M to 1B parameters, state-of-the-art at their respective sizes. Built on the Ettin ModernBERT encoders, with the full training recipe and ~143M-triple training dataset as well. 🧵

Fastino Labs just released GLiGuard, an open-source safety moderation model that remembers encoders are king for these kinds of tasks. One model, Apache 2.0: gliguard-LLMGuardrails-300M: 300M params, evaluates multiple safety tasks at a time. 🧵

🤖 I've just released Sentence Transformers v5.5.0! It's headlined by a new `train-sentence-transformers` Agent Skill: let your AI coding agent train & finetune embedding, reranker & sparse encoder models for you. Plus more, here's a thread with highlights 🧵

The excellent zerank-2 reranker model by @zeroentropyai.bsky.social is now fully compatible with Sentence Transformers, no `trust_remote_code=True` needed. It's 4B and cc-by-nc-4.0, and performs very well. I'm quite fond of their training methodology, I'll explain in the 🧵

IBM just released the R2 generation of their Granite multilingual embedding models for retrieval, and the jump over R1 is very notable. Two models, both Apache 2.0: - granite-embedding-97m-multilingual-r2 (384-dim) - granite-embedding-311m-multilingual-r2 (768-dim) 🧵

Dun Zhang just released Prism-Reranker: a new open-source reranker family for improving (agentic) search on Qwen3.5, in four sizes from 0.8B to 9B. MIT licensed. Drop-in CrossEncoder for scores only. Trained on a realistic agent-style data mix. 🧵

BidirLM-Omni-2.5B-Embedding is live: a single bidirectional encoder that embeds text, images, and audio into the same space! Three modalities, all in one 2048-dim space. 🧵

The @flowercomputer.com team brought Static Embedding models to Rust and carried out optimizations to heavily speed up potential inference. They'll be open sourcing the deployment pipeline soon. This looks very nice at first glance! Definitely give the thread a read.

📈 New blog post: Training and Finetuning Multimodal Embedding & Reranker Models with Sentence Transformers. As a practical example, I finetuned Qwen3-VL-Embedding-2B for Visual Document Retrieval (matching text queries to document screenshots). Thread with highlights 🧵

This is what finetuning is all about: hyper-specific use cases tackled using a custom finetuned model to blow the generic baselines out of the water! Nice work to Aresh Tajvar on this San Diego Municipal Code retrieval model.

🔧 Sentence Transformers v5.4.1 is out, a small patch release patching support for numpy string arrays & improving the safety of activation function loading. Two fixes below 🧵

🧩 To celebrate yesterday's Sentence Transformers v5.4 release, I went back to update SpanMarker: my Named Entity Recognition project. It's still a solid, extremely efficient option for NER. Here's how it works and what's new 🧵

🌐 I've just released Sentence Transformers v5.4: we're going fully multimodal for embeddings & reranking! Also featuring a modular CrossEncoder, and automatic Flash Attention 2 input flattening. Highlights in 🧵

⬆️ I've just released Sentence Transformers v5.3.0! This release upgrades training with MultipleNegativesRankingLoss with alternative InfoNCE formulations and hardness weighting, adds two new losses, and more. Details in 🧵

🤗 Perplexity has released 4 open-weights state-of-the-art multilingual embedding models designed for retrieval tasks! pplx-embed-v1 and pplx-embed-context-v1 Specifically trained for int8 and binary embeddings, they'll be viable for massive search problems. Details in 🧵

🚀 LightOn is back with a SOTA late-interaction model for search: ColBERT-Zero! By performing contrastive pre-training directly in the multi-vector setting, it outperforms GTE-ModernColBERT etc. on BEIR, using only public data and reaching 55.43 nDCG@10. Details in 🧵

ggml / llama.cpp are joining @hf.co, ensuring it'll stay open, maintained, and up to date for a long long time! 🚀 huggingface.co/blog/ggml-jo...

👏 Jina AI is back with new state-of-the-art multilingual embedding models for retrieval & more: jina-embedding-v5-text! 2 efficient sizes, 239M & 677M, they outperform Qwen3-embedding, EmbeddingGemma-300m, multilingual-e5-large, etc. Details in 🧵

More embedding models and an even more reliable inference engine is what you get with @hf.co Text Embeddings Inference v1.9.0 💥 More in the thread 🧵

I've just pushed a v5.2.3 update for Sentence Transformers that introduces support training with Transformers v5.2 (apologies for the confusion around the project versions, they just happen to be close now 😆). Updating is only useful if you're training. Details in 🧵

The folks from @lightonai.bsky.social have released extremely strong & efficient Late Interaction models for code search: LateOn-Code(-edge) Alongside a new tool: ColGrep, to use it with your coding agents straight away, locally & cheap Models, dataset, and training code released 🧵

A few days back, following a long line of excellent proprietary models, VoyageAI by @mongodb.bsky.social released their 🚨 first ever open-weights embedding model for retrieval 🚨! It's called voyage-4-nano, it's multilingual, and very efficient. Details in 🧵

🤝 I just released Sentence Transformers v5.2.1, introducing official support for the brand-new Transformers v5.x alongside v4.x. Both versions will be supported for the foreseeable future! Details in 🧵

There were very few search rerankers specifically for e-commerce queries. Until now, that is. RexRerankers by Walmart Tech MLEs is a suite of 5 SOTA rerankers ranging from 17M to 0.6B parameters. Details in 🧵:

Sentence Transformers 🤝 @unsloth.ai We've collaborated with the fine folks at Unsloth to make your embedding model finetuning ~2x faster and require ~20% less VRAM! The Unsloth team prepared 6 notebooks showing how you can take advantage of it! 🧵

🏎️ You can perform 200ms search over 40 million texts using just a CPU server, 8GB of RAM, and 45GB of disk space. The trick: Binary search with int8 rescoring. I'll show you a demo & how it works in the 🧵:

🔥I've just published Sentence Transformers v5.2.0! It introduces multi-processing for CrossEncoder (rerankers), multilingual NanoBEIR evaluators, similarity score outputs in mine_hard_negatives, Transformers v5 support and more. Details in 🧵

🤝 𝗦𝗲𝗻𝘁𝗲𝗻𝗰𝗲 𝗧𝗿𝗮𝗻𝘀𝗳𝗼𝗿𝗺𝗲𝗿𝘀 𝗷𝗼𝗶𝗻𝘀 𝗛𝘂𝗴𝗴𝗶𝗻𝗴 𝗙𝗮𝗰𝗲 Originally developed at the UKP Lab at @tuda.bsky.social, Sentence Transformers has become one of the world’s most widely used open-source libraries for semantic embeddings in natural language processing. (1/🧵)

🤗 Sentence Transformers is joining @hf.co! 🤗 This formalizes the existing maintenance structure, as I've personally led the project for the past two years on behalf of Hugging Face. I'm super excited about the transfer! Details in 🧵

The MTEB team has just released MTEB v2, an upgrade to their evaluation suite for embedding models! Their blogpost covers all changes, including easier evaluation, multimodal support, rerankers, new interfaces, documentation, dataset statistics, a migration guide, etc. 🧵

We're announcing a new update to MTEB: RTEB It's a new multilingual text embedding retrieval benchmark with private (!) datasets, to ensure that we measure true generalization and avoid (accidental) overfitting. Details in our blogpost below 🧵

🐛 I've just released Sentence Transformers v5.1.1! It's a small patch release that makes the project more explicit with incorrect arguments and introduces some fixes for multi-GPU processing, evaluators, and hard negatives mining. Details in 🧵

ModernBERT goes MULTILINGUAL! One of the most requested models I've seen, @jhuclsp.bsky.social has trained state-of-the-art massively multilingual encoders using the ModernBERT architecture: mmBERT. Stronger than an existing models at their sizes, while also much faster! Details in 🧵

Google just launched EmbeddingGemma: an efficient, multilingual 308M embedding model that's ready for semantic search & more on just about any hardware, CPU included. Details in 🧵:

One of the most underrated players in AI models, IBM, released 2 new extremely efficient embedding models: granite-embedding-english-r2 & granite-embedding-small-english-r2, commercially viable. Details in 🧵:

😎 I just published Sentence Transformers v5.1.0, and it's a big one. 2x-3x speedups of SparseEncoder models via ONNX and/or OpenVINO backends, easier distillation data preparation with hard negatives mining, and more! See 🧵for the deets:

OpenAI is back with open source releases on @hf.co. This is the biggest release I've seen in a long time! See more in huggingface.co/openai

I've just updated SetFit to v1.1.3, bringing compatibility with the recent datasets v4.0+ and Sentence Transformers v5.0+. You'll again be able to train tiny classifiers using very little training data! 🧵

Some of the ModernBERT team is back with new encoder models: Ettin, ranging from tiny to small: 17M, 32M, 68M, 150M, 400M & 1B parameters. They also trained decoder models & checked if decoders could classify & if encoders could generate. Details in 🧵:

‼️Sentence Transformers v5.0 is out! The biggest update yet introduces Sparse Embedding models, encode methods improvements, Router module for asymmetric models & much more. Sparse + Dense = 🔥 hybrid search performance! Details in 🧵

ColBERT (a.k.a. multi-vector, late-interaction) models are extremely strong search models, often outperforming dense embedding models. And @lightonai.bsky.social just released a new state-of-the-art one: GTE-ModernColBERT-v1! Details in 🧵

I just released Sentence Transformers v4.1; featuring ONNX and OpenVINO backends for rerankers offering 2-3x speedups and improved hard negatives mining which helps prepare stronger training datasets. Details in 🧵

I just published the SetFit v1.1.2 release, allowing you to finetune efficient classification models with very little training data. The new patch introduces compatibility with the latest transformers and sentence-transformers versions.

I just released Sentence Transformers v4.0.2. This patch release brings a slight improvement for maximum sequence lengths, typing issues, and distributed training device placement. Details in 🧵

I've just ported the excellent monoELECTRA-{base, large} reranker models from @fschlatt.bsky.social & the research network Webis Group to Sentence Transformers! These models were introduced in the Rank-DistiLLM paper, and distilled from LLMs like RankZephyr and RankGPT4. Details in 🧵

Ever thought that finetuning rerankers for your search system wasn't worth it? Think again. I finetuned ModernBERT on my dataset, TriviaQA, just on my normal PC in a few hours. It outperforms all open models on the market on my eval set. Finetuning is so worth it. Blog in 🧵

‼️Sentence Transformers v4.0 is out! You can now train and finetune reranker (aka cross-encoder) models with multi-GPU training, bf16 support, loss logging, callbacks & much more. I also prove that finetuning on your domain helps much more than you might think. Details in 🧵

Let's goo, Mixedbread is back with more open weight Apache 2.0 rerankers. Their new mxbai-rerank-...-v2 line is quite novel, using GRPO (akin to DeepSeek-R1), contrastive learning, and ranking objectives. Details in 🧵

I just tried to find a paper from a few months ago for some docs that I'm writing. I tried on Google with like 5 separate queries, but just couldn't find it. Tried it again via hf.co/papers, same prompt, and the paper I wanted is literally the first result. 🩷🤗🩷

An assembly of 18 European companies, labs, and universities have banded together to launch 🇪🇺 EuroBERT! It's a state-of-the-art multilingual encoder for 15 European languages, designed to be finetuned for retrieval, classification, etc. Details in 🧵