view article Article The 1 Billion Token Challenge: Finding the Perfect Pre-training Mix 26 days ago • 46
view article Article SmolVLA: Efficient Vision-Language-Action Model trained on Lerobot Community Data Jun 3 • 287
Qwen2.5-VL Collection Vision-language model series based on Qwen2.5 • 11 items • Updated Jul 21 • 547
BLING Models Collection Small CPU-based RAG-optimized, instruct-following 1B-3B parameter models • 27 items • Updated Jun 19 • 28