Wait, We Don't Need to "Wait"! Removing Thinking Tokens Improves Reasoning Efficiency Paper โข 2506.08343 โข Published Jun 10 โข 54
view post Post 1725 Qwen is on fire this week ๐ฅThey just released Qwen3-MT ๐ a translation model supports 92 languages. Demo is available on the hub. Qwen/Qwen3-MT-Demoโจ Highly Customizable: Supports custom terms, domain prompts, and translation memory for accurate, context-aware results.โจ Fast and affordable: $0.5 per million tokens. See translation ๐ฅ 6 6 + Reply