Unlocking Lossless Speedups in LLMs via Discrete Diffusion Paper • 2609.04010 • Published Sep 3 • 114
French audio datasets (pretraining) Collection Around 117K hours of audio in French for research purpose • 51 items • Updated Mar 2 • 2
Muse Glimmer Collection Muse Glimmer 30B: multimodal agentic model for local deployment. BF16 weights, GGUF k-quants, ExecuTorch builds, DFlash drafter. • 4 items • Updated Aug 10 • 112
Orthrus: Memory-Efficient Parallel Token Generation via Dual-View Diffusion Paper • 2605.12825 • Published May 12 • 13
Ministral 3 Collection A collection of edge models, with Base, Instruct and Reasoning variants, in 3 different sizes: 3B, 8B and 14B. All with vision capabilities. • 9 items • Updated 1 day ago • 178