Demons in the Detail: On Implementing Load Balancing Loss for Training Specialized Mixture-of-Expert Models Paper • 2501.11873 • Published Jan 21 • 66
Qwen2 Collection Qwen2 language models, including pretrained and instruction-tuned models of 5 sizes, including 0.5B, 1.5B, 7B, 57B-A14B, and 72B. • 39 items • Updated Jul 21 • 371