colpali-engine
AssessTools
A model stack for visual document retrieval that can be used through Sentence Transformers.
Why it's here
Placed in Assess: 2 article(s) of evidence from 1 source(s), led by framework updates, with 0 in the last 30 days. Confidence 32%.
Evidence (2)
- 7Hugging Face Blog·9/3/2026model_releaseNeoMME: an efficient multilingual multimodal encoder
Hugging Face introduced NeoMME, a family of 260M and 800M multimodal encoders built from scratch with a single bidirectional Transformer for text and image patches. The models target visual document retrieval, achieve strong results on ViDoRe v3, and are released in Hugging Face Transformers under Apache 2.0.
- 7Hugging Face Blog·8/18/2026framework_updateSentence Transformers Adds Multi-Vector Late-Interaction Models
Sentence Transformers v6.0 adds MultiVectorEncoder, a new model type for ColBERT-style late-interaction retrieval. The update supports PyLate, Stanford NLP ColBERT, and colpali-engine checkpoints through the same API used for dense, sparse, and reranker models.