10 86 225

Travis King

travisking

AI & ML interests

have you heard of generative AI?

Recent Activity

upvoted a paper about 15 hours ago

Franca: Nested Matryoshka Clustering for Scalable Visual Representation Learning

liked a model 1 day ago

Qwen/Qwen3-235B-A22B-Instruct-2507

upvoted a paper 5 days ago

A Survey of Context Engineering for Large Language Models

View all activity

Organizations

None yet

upvoted a paper about 15 hours ago

Franca: Nested Matryoshka Clustering for Scalable Visual Representation Learning

Paper • 2507.14137 • Published 5 days ago • 22

liked a model 1 day ago

Qwen/Qwen3-235B-A22B-Instruct-2507

Text Generation • 235B • Updated 1 day ago • 1.32k • • 390

upvoted a paper 5 days ago

A Survey of Context Engineering for Large Language Models

Paper • 2507.13334 • Published 6 days ago • 170

upvoted an article 14 days ago

Article

Three Mighty Alerts Supporting Hugging Face’s Production Infrastructure

•

15 days ago

• 8

New activity in google/gemma-3n-E2B-it 14 days ago

CPU support

#12 opened 14 days ago by

travisking

upvoted 2 papers 18 days ago

Energy-Based Transformers are Scalable Learners and Thinkers

Paper • 2507.02092 • Published 21 days ago • 55

Self-Correction Bench: Revealing and Addressing the Self-Correction Blind Spot in LLMs

Paper • 2507.02778 • Published 20 days ago • 9

reacted to arthurbresnu's post with 🚀 21 days ago

Post

2066

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

1️⃣ Sparse Encoder Models - New support for sparse embeddings (30k+ dims, <1% non-zero)

* Full SPLADE, Inference-free SPLADE, CSR support
* 4 new modules, 12 losses, 9 evaluators
* Integration with elastic, opensearch-project, Qdrant, ibm-granite
* Decode interpretable embeddings
* Hybrid search integration

2️⃣ Enhanced Encode Methods

* encode_query & encode_document with auto prompts
* Direct device list passing to encode()
* Cleaner multi-processing

3️⃣ Router Module & Training

* Different paths for queries vs documents
* Custom learning rates per parameter group
* Composite loss logging
* Perfect for two-tower architectures

4️⃣ Documentation & Training

* New Training/Loss Overview docs
* 6 training example pages
* Search engine integration examples

Read the comprehensive blogpost about training sparse embedding models: https://huggingface.co/blog/train-sparse-encoder

See the full release notes here: https://github.com/UKPLab/sentence-transformers/releases/v5.0.0

What's next? We would love to hear from the community! What sparse encoder models would you like to see? And what new capabilities should Sentence Transformers handle - multimodal embeddings, late interaction models, or something else? Your feedback shapes our roadmap!

I'm incredibly excited to see the community explore sparse embeddings and hybrid search! The interpretability alone makes this a game-changer for understanding what your models are actually doing.

🙏 Thanks to @tomaarsen for this incredible opportunity!