apple/LensVLM-9B — new model trending #30 on Hugging Face
Apple released LensVLM-9B, a vision-language model that selectively expands compressed document pages.
Apple published LensVLM-9B on Hugging Face, a 9-billion-parameter vision-language model for reading compressed images of text. It scans compressed pages and uses learned tools to expand only relevant pages, with 5x, 10x, and 15x compression options. Weights, including Apple's modifications to a Qwen model, are under the Apple Machine Learning Research Model License. A companion paper (arXiv:2605.07019) and inference code were released with the model.
- 9B VLM scans compressed document images then expands relevant pages
- Supports 5x, 10x, and 15x compression settings
- Weights modify a Qwen model under Apple's research license
- Paper arXiv:2605.07019 and inference code published with the weights
- Vendors
- Apple
- Organizations
- Apple
- AI models
- LensVLM-9BQwen
From the original article
1 min read at huggingface.coimage-text-to-text · 1,432 downloads · 223 likes · license apple-amlr
By apple · huggingface.co
A short excerpt; the article and its images belong to the publisher. Summary, key facts and assessment above are AI-written from the article and can be wrong.