Hugging Face· PlatformNew model

Train 400x faster Static Embedding Models with Sentence Transformers

Hugging Face introduces a training method for static embedding models that are 100x to 400x faster on CPU than state-of-the-art models while retaining about 85% of performance. They release two models (for English retrieval and multilingual similarity), training scripts, and datasets.

From the source

This blog post introduces a method to train static embedding models that run 100x to 400x faster on CPU than state-of-the-art embedding models, while retaining most of the quality.

huggingface.co

Announced

15 Jan 2025 00:00 UTC

Detected

03 Aug 2026 21:12 UTC (+565d after)