view post Post 2411 Updated the vikhyatk/lnqa dataset to include images, so you no longer need to separately download them from OpenImages!
view post Post 2970 Released a new version of vikhyatk/moondream2 today! Primarily focused on improving OCR and captioning (e.g. "Describe this image", "Describe this image in one sentence"), but also seeing general improvement across all benchmarks.