Swift 1.5 27B Collection Swift 1.5 on Qwen3.8-27B: stronger than Swift 1.0 on agentic and coding tasks, with fewer thinking tokens. BF16 weights and every quant. • 11 items • Updated 7 days ago • 21
Running on Zero Agents Featured 257 Laya Demo 🎯 257 Fast System 1 decisions with calibrated probabilities
DeepMostInnovations/sales-conversion-model-reinf-learning Reinforcement Learning • Updated 14 days ago • 576 • 211
microsoft/VibeVoice-ASR-Streaming-7B Automatic Speech Recognition • 9B • Updated 28 days ago • 7k • 249