TechFeed

PAPER DISCORD 介绍 强化学习（RL）已成为扩展语言模型并提升其深度推理和问题解决能力的关键范式。要扩展 RL，首要前提是保持稳定且强健的训练动态。如何…

PAPER DISCORD Introduction Reinforcement Learning (RL) has emerged as a pivotal paradigm for scaling language models and enhancing their deep reasoning and problem-solving capabilities. To scale RL, the foremost prerequisite is maintaining stable and robust training dynamics. How…

DEMO API DISCORD 介绍 在此我们通过 Qwen API 介绍 Qwen-MT（qwen-mt-turbo）的最新更新。此更新基于强大的 Qwen3，利用数万亿的多语言和翻译 token，全面提升模型的多语言理解和…

DEMO API DISCORD Introduction Here we introduce the latest update of Qwen-MT (qwen-mt-turbo) via Qwen API. This update builds upon the powerful Qwen3, leveraging trillions multilingual and translation tokens to comprehensively enhance the model’s multilingual understanding and tr…

GITHUB HUGGING FACE MODELSCOPE DISCORD 今天，我们宣布 Qwen3-Coder，这是迄今为止最具自主性的代码模型。Qwen3-Coder 提供多种规模，但我们首先推出其最强变体：Qwen3-Coder-480B-A35B-Instruct —— 一个 480B 参数的 Mixture‑o…

GITHUB HUGGING FACE MODELSCOPE DISCORD Today, we’re announcing Qwen3-Coder, our most agentic code model to date. Qwen3-Coder is available in multiple sizes, but we’re excited to introduce its most powerful variant first: Qwen3-Coder-480B-A35B-Instruct — a 480B-parameter Mixture-o…