Post
2411
Updated the
vikhyatk/lnqa dataset to include images, so you no longer need to separately download them from OpenImages!
vik PRO
vikhyatk
AI & ML interests
None yet
Organizations
Posts
8
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.