Qwen/Qwen2-7B

Qwen/Qwen2-7B is a 7.6 billion parameter base language model developed by Qwen, part of the new Qwen2 series. This Transformer-based model features SwiGLU activation and group query attention, demonstrating strong performance across language understanding, generation, multilingual tasks, coding, mathematics, and reasoning benchmarks. It is designed as a foundational model for further fine-tuning and post-training applications.