Alibaba Cloud releases Qwen2 model series with long-context and multilingual capabilities

Alibaba Cloud has released the Qwen2 series of open-source language models, offering a range of sizes from 0.5 billion to 72 billion parameters, including a mixture-of-experts model. These models boast enhanced capabilities in long-context reasoning, supporting up to 128K tokens, and improved multilingual support with training data across 27 languages. The Qwen2 series demonstrates strong performance on various benchmarks, making it a competitive option for developers seeking powerful and flexible open-source AI solutions. AI

IMPACT Enhances the open-source AI landscape with powerful, versatile models, potentially shifting default choices for developers.

RANK_REASON Frontier-lab model release with system card. [lever_c_demoted from frontier_release: ic=1 ai=1.0]

Read on dev.to — LLM tag →

• Alibaba Cloud
• English
• Group Query Attention
• Hugging Face
• mixture of experts
• Qwen2
• Qwen2-72B-Instruct
• Standard Chinese
• transformers

• model release
• product

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →