Value-and-Structure Alignment for Routing-Consistent Quantization of Mixture-of-Experts Models Paper • 2606.05688 • Published 6 days ago
Efficient MoE-based LLM Collection Mixture-of-Experts Large Language Models with Advanced Quantization • 5 items • Updated Mar 11 • 23
Efficient Large Vision-Language Model Collection ERGO: LVLM trained with RL on efficiency objectives; https://github.com/nota-github/ERGO • 3 items • Updated Feb 22 • 25
Efficient MoE-based LLM Collection Mixture-of-Experts Large Language Models with Advanced Quantization • 5 items • Updated Mar 11 • 23
Running Agents 82 Compressed Wav2Lip 🌟 82 Generate lip-sync videos from uploaded videos and audio files
Running Agents Featured 117 Compressed Stable Diffusion 🌟 117 Compare image generation results from original and compressed AI models
Running Agents Featured 117 Compressed Stable Diffusion 🌟 117 Compare image generation results from original and compressed AI models