mobiuslabsgmbh/Llama-3.1-8b-instruct_4bitgs64_hqq_calib Text Generation β’ Updated Feb 5 β’ 54 β’ 55
Running on Zero 486 486 Florence2 + SAM2 π₯ Segment objects in images and videos using text prompts
Running 543 543 Vision Arena (Testing VLMs side-by-side) πΌ Analyze images to detect and label objects