NeoMME: an efficient Multimodal-native and Multilingual Encoder
New multimodal encoder achieves 2× faster document encoding and 255× smaller index storage.
Open-weight release
Hugging Face introduces NeoMME, a family of 260M and 800M multilingual multimodal encoders trained from scratch with a masked discrete-diffusion objective.
- The model is fine-tuned for visual document retrieval and achieves high throughput.
- All model checkpoints are released under the Apache 2.0 license.
