kxxinDave/Qwen2.5-VL-instruct-3B-Geo
Image-Text-to-Text • 4B • Updated • 6 • 2
Kevin Dave
kxxinDave
AI & ML interests
Vision Models, distillation and quantisation.
Recent Activity
commentedon a paper 27 days ago
Generative Neural Video Compression via Video Diffusion Prior updated a dataset 7 months ago
kxxinDave/MedVQA published a dataset 7 months ago
kxxinDave/MedVQAOrganizations
None yet