Qwen2.5 14B Instruct
Alibaba · 2024-09-19 · 14.8B parameters
Qwen2.5-14B-Instruct is Alibaba's 14.7-billion-parameter instruction-tuned language model from the Qwen2.5 series, released September 19, 2024. It is multilingual across more than 29 languages and improves coding, mathematics, instruction following, and structured output generation over Qwen2. Its shipped configuration is set for 32,768-token contexts; Qwen documents extrapolated support to 131,072 tokens using YaRN and Dual Chunk Attention.