Paper summary
Paper summary: Qwen2 Technical Report
The Qwen2 report covers open dense models from 0.5B to 72B plus an MoE, with Qwen2-72B reaching 84.2 on MMLU as a base model and support for about 30 languages.
- A full family released together: dense models from 0.5B to 72B, plus a mixture-of-experts model.
- The flagship base model reports 84.2 MMLU, 64.6 HumanEval and 89.5 GSM8K.