facebook/vjepa2-vitl-fpc64-256 Video Classification โข 0.3B โข Updated 16 days ago โข 21.5k โข 131
Running on Zero 510 510 Florence2 + SAM2 ๐ฅ Segment objects in images and videos using text prompts
Running on Zero 773 773 Florence 2 ๐ Analyze images to generate captions, detect objects, or perform OCR
mlx-community/Meta-Llama-3-8B-Instruct-4bit Text Generation โข 2B โข Updated Apr 19, 2024 โข 9.77k โข 78
Running 108 108 Llmlingua 2 ๐ป Compress lengthy prompts into shorter versions while preserving key information
The Era of 1-bit LLMs: All Large Language Models are in 1.58 Bits Paper โข 2402.17764 โข Published Feb 27, 2024 โข 619