HiRED: Attention-Guided Token Dropping for Efficient Inference of High-Resolution Vision-Language Models in Resource-Constrained Environments Paper โข 2408.10945 โข Published Aug 20 โข 9
A Model Generalization Study in Localizing Indoor Cows with COw LOcalization (COLO) dataset Paper โข 2407.20372 โข Published Jul 29
Performance Scaling via Optimal Transport: Enabling Data Selection from Partially Revealed Sources Paper โข 2307.02460 โข Published Jul 5, 2023
Stylebreeder: Exploring and Democratizing Artistic Styles through Text-to-Image Models Paper โข 2406.14599 โข Published Jun 20 โข 16
view post Post 1675 ๐ Big reveal: 01.AI Yi-1.5 models are in town! ๐ 1st Apache 2.0 release๐ก Capabilities: Enhanced coding, math, reasoning, & instruction-following๐ค Models: 34B/9B/6B, Base & Chat ๐ Performance: Yi-1.5-34B matches or exceeds Llama 3 70B in benchmarks๐ฅ Discover the power now! 01-ai/yi-15-2024-05-663f3ecab5f815a3eaca7ca8 4 replies ยท ๐ฅ 3 3 + Reply