NanoBEIR
AI overview
Sign in and the AI will write an overview from our coverage.
Headlines · 1
- Pooling-Aware Training Cuts Multi-Vector Retrieval Storage
Tom Aarsen’s Hugging Face technical report introduces pooling-aware training for multi-vector embedding models, teaching encoders to retain useful information when similar token vectors are merged. The author reports that a factor-4 configuration reduced document vectors fourfold while retaining 97.8% of unpooled NanoBEIR nDCG@10, versus 94.6% for ordinary training, and provides reproducible Sentence Transformers code and checkpoints.
Hugging Face · 🔥 0
Experience and discussion from the community
Share my NanoBEIR experienceAsk about NanoBEIR
Nobody has shared their experience with NanoBEIR yet.