Running on Zero Featured 1.32k Qwen3-TTS Demo 🎙 1.32k Generate custom speech from text with selectable voices
high-quality Chinese training datasets Collection a suite of high-quality Chinese datasets, used for pretraining, fine-tuning or preference alignment. And the models trained on these datasets. • 13 items • Updated May 22, 2025 • 24
Running on CPU Upgrade Featured 2.97k The Smol Training Playbook 📚 2.97k The secrets to building world-class LLMs
view article Article mem-agent: Persistent, Human Readable Memory Agent Trained with Online RL Sep 11, 2025 • 26
SmolLM2 Collection State-of-the-art compact LLMs for on-device applications: 1.7B, 360M, 135M • 16 items • Updated May 5, 2025 • 301
Decoupling the "What" and "Where" With Polar Coordinate Positional Embeddings Paper • 2509.10534 • Published Sep 5, 2025 • 4 • 1
Decoupling the "What" and "Where" With Polar Coordinate Positional Embeddings Paper • 2509.10534 • Published Sep 5, 2025 • 4