LensVLM-9B by Apple

Apple has developed a new large language model called LensVLM-9B, which has achieved state-of-the-art performance on several natural language understanding tasks. The model is a variant of the Vision and Language Model transformer, and is based on a large-scale dataset of text. According to the paper, LensVLM-9B outperforms other models on tasks such as sentiment analysis, question answering, and text classification. The model's performance is attributed to its ability to leverage the relationships between images and text.