view article Article Shrinking Full-Duplex Speech: Training a 600M Moshi-Style Model on a Weekend Budget edwixx • Sep 22 • 6
DavidAU/Qwen3-30B-A1.5B-64K-High-Speed-NEO-Imatrix-MAX-gguf Text Generation • 31B • Updated 1 day ago • 2.61k • 31
Runtime error 15 Fairly Multilingual ModernBERT Token Alignment 🔀 15 Aligns the tokens of two sentences