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 3 days ago • 17
Running on Zero Agents Featured 226 Laya Demo 🎯 226 Fast System 1 decisions with calibrated probabilities
DeepMostInnovations/sales-conversion-model-reinf-learning Reinforcement Learning • Updated 11 days ago • 556 • 205
microsoft/VibeVoice-ASR-Streaming-7B Automatic Speech Recognition • 9B • Updated 25 days ago • 6.73k • 247