MobileMoE Collection a family of on-device MoE language models with sub-billion active parameters (0.3-0.9B active and 1.3-5.3B total) that establish a new Pareto frontier • 10 items • Updated about 4 hours ago • 5
An Empirical Study of Training Pixel-Space Text-to-Image Diffusion Models Paper • 2608.16887 • Published 8 days ago • 33
Unsloth Dynamic 3.0 Quants Collection Introducing Dynamic V3.0 quants, our new SOTA quantization methodology. • 1 item • Updated 5 days ago • 46
view post Post 3410 Open sourcing Coala Embeddings! It can compress 20 million documents which can take 80gb ram down to just 1gb RAM. Why is this important? Embeddings are used everywhere(RAG, semantic search, etc.) by many.Coala Embeddings massively cheapen cost to host them while being simply and easy to use.GitHub: https://github.com/ysharma3501/CoalaEmbeddingsNotebook Demo: https://colab.research.google.com/drive/1TXip-vZg72e_2AB185MINufVVav8Oo9T?usp=sharing See translation 🔥 7 7 🚀 2 2 ❤️ 1 1 + Reply