Retour à Qwen2.5
Alibaba's 14B Qwen 2.5 instruct model — strong coding, math, and instruction-following at a mid-size, cost-efficient deployment point.
131K tokensGratuit / Poids ouvertsTransformerApache 2.0
Benchmarks
Qwen2.5-14B-Instruct
42.6%Qwen2.5-14B-Instruct FC — estimated from Qwen2.5 family (between 7B and 32B scores)
