Change
6f6fd22
6f6fd22d186b7589bca32fdd33bf00a2e594fd99 · commit on GitHub
qwen-blog-feed: changed (39167 bytes, HTTP 200)
raw/qwen-blog-feed/response.xml added
- Source
- qwen-blog-feed
- Lines added
- +473
- Lines removed
- -0
- Stored bytes at this commit
- 39,167
- Timestamp
- origin
- Raw artifact at this commit
- raw/qwen-blog-feed/response.xml
Recorded headers
| observed_at | 2026-09-01T23:17:48.460Z |
|---|---|
| origin_date | 2026-09-01T23:12:30.000Z |
| status | 200 |
| final URL | https://qwenlm.github.io/blog/index.xml |
| etag | W/"6970c244-98ff" |
| last-modified | Wed, 21 Jan 2026 12:10:44 GMT |
| date | Tue, 01 Sep 2026 23:17:48 GMT |
| age | 318 |
| cache-control | max-age=600 |
| cf-cache-status | null |
| content-encoding | gzip |
| content-length | 11328 |
@
@@ -0,0 +1,473 @@+
<?xml version="1.0" encoding="utf-8" standalone="yes"?>+
<rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom" xmlns:content="http://purl.org/rss/1.0/modules/content/">+
<channel>+
<title>Blog on Qwen</title>+
<link>https://qwenlm.github.io/blog/</link>+
<description>Recent content in Blog on Qwen</description>+
<image>+
<url>https://qwenlm.github.io/%3Clink%20or%20path%20of%20image%20for%20opengraph,%20twitter-cards%3E</url>+
<link>https://qwenlm.github.io/%3Clink%20or%20path%20of%20image%20for%20opengraph,%20twitter-cards%3E</link>+
</image>+
<generator>Hugo -- gohugo.io</generator>+
<lastBuildDate>Tue, 23 Sep 2025 04:00:00 +0800</lastBuildDate><atom:link href="https://qwenlm.github.io/blog/index.xml" rel="self" type="application/rss+xml" />+
<item>+
<title>Qwen3Guard: Real-time Safety for Your Token Stream</title>+
<link>https://qwenlm.github.io/blog/qwen3guard/</link>+
<pubDate>Tue, 23 Sep 2025 04:00:00 +0800</pubDate>+
+
<guid>https://qwenlm.github.io/blog/qwen3guard/</guid>+
<description>Tech Report GitHub Hugging Face ModelScope DISCORD+
Introduction We are excited to introduce Qwen3Guard, the first safety guardrail model in the Qwen family. Built upon the powerful Qwen3 foundation models and fine-tuned specifically for safety classificatoin, Qwen3Guard ensures responsible AI interactions by delivering precise safety detection for b…+
Qwen3Guard achieves state-of-the-art performance on major safety benchmarks, demonstrating strong capabilities in both prompt and response classification tasks across English, Chinese, and multilingual environments.</description>+
</item>+
+
<item>+
<title>Qwen-Image-Edit: Image Editing with Higher Quality and Efficiency</title>+
<link>https://qwenlm.github.io/blog/qwen-image-edit/</link>+
<pubDate>Tue, 19 Aug 2025 01:30:00 +0800</pubDate>+
+
<guid>https://qwenlm.github.io/blog/qwen-image-edit/</guid>+
<description>QWEN CHAT GITHUB HUGGING FACE MODELSCOPE DISCORD+
We are excited to introduce Qwen-Image-Edit, the image editing version of Qwen-Image. Built upon our 20B Qwen-Image model, Qwen-Image-Edit successfully extends Qwen-Image&rsquo;s unique text rendering capabilities to image editing tasks, enabling precise text editing. Furthermore, Qwen-Image-Edi…+
</item>+
+
<item>+
<title>Qwen-Image: Crafting with Native Text Rendering</title>+
<link>https://qwenlm.github.io/blog/qwen-image/</link>+
<pubDate>Mon, 04 Aug 2025 22:08:30 +0800</pubDate>+
+
<guid>https://qwenlm.github.io/blog/qwen-image/</guid>+
<description>GITHUB HUGGING FACE MODELSCOPE DEMO DISCORD+
We are thrilled to release Qwen-Image, a 20B MMDiT image foundation model that achieves significant advances in complex text rendering and precise image editing. To try the latest model, feel free to visit Qwen Chat and choose “Image Generation”.+
The key features include:+
Superior Text Rendering: Qwen-Image excels at complex text rendering, including multi-line layouts, paragraph-level semantics, and fine-grained details. It supports both alphabetic languages (e.</description>+
</item>+
+
<item>+
<title>GSPO: Towards Scalable Reinforcement Learning for Language Models</title>+
<link>https://qwenlm.github.io/blog/gspo/</link>+
<pubDate>Sun, 27 Jul 2025 15:00:00 +0800</pubDate>+
+
<guid>https://qwenlm.github.io/blog/gspo/</guid>+
<description>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. However, we observe that existing RL …+
To enable successful RL scaling, we propose the Group Sequence Policy Optimization (GSPO) algorithm.</description>+
</item>+
+
<item>+
<title>Qwen-MT: Where Speed Meets Smart Translation</title>+
<link>https://qwenlm.github.io/blog/qwen-mt/</link>+
<pubDate>Thu, 24 Jul 2025 22:00:00 +0800</pubDate>+
+
<guid>https://qwenlm.github.io/blog/qwen-mt/</guid>+
<description>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 translation capabilities. By integratin…+
Key Features:+
Multilingual Support for 92 Languages: Qwen-MT enables high-quality translation across 92 major official languages and prominent dialects, covering over 95% of the global population to meet diverse cross-lingual communication needs.</description>+
</item>+
+
<item>+
<title>Qwen3-Coder: Agentic Coding in the World</title>+
<link>https://qwenlm.github.io/blog/qwen3-coder/</link>+
<pubDate>Tue, 22 Jul 2025 21:00:00 +0800</pubDate>+
+
<guid>https://qwenlm.github.io/blog/qwen3-coder/</guid>+
<description>GITHUB HUGGING FACE MODELSCOPE DISCORD+
Today, we&rsquo;re announcing Qwen3-Coder, our most agentic code model to date. Qwen3-Coder is available in multiple sizes, but we&rsquo;re excited to introduce its most powerful variant first: Qwen3-Coder-480B-A35B-Instruct — a 480B-parameter Mixture-of-Experts model with 35B active paramet…+
</item>+
+
<item>+
<title>Time to Speak Some Dialects, Qwen-TTS!</title>+
<link>https://qwenlm.github.io/blog/qwen-tts/</link>+
<pubDate>Fri, 27 Jun 2025 15:01:30 +0800</pubDate>+
+
<guid>https://qwenlm.github.io/blog/qwen-tts/</guid>+
<description>API DISCORD+
Introduction Here we introduce the latest update of Qwen-TTS (qwen-tts-latest or qwen-tts-2025-05-22) through Qwen API . Trained on a large-scale dataset encompassing over millions of hours of speech, Qwen-TTS achieves human-level naturalness and expressiveness. Notably, Qwen-TTS automatically adjus…+
As of now, Qwen-TTS supports 7 Chinese-English bilingual voices, including Cherry, Ethan, Chelsie, Serena, Dylan (Pekingese), Jada (Shanghainese) and Sunny (Sichuanese).</description>+
</item>+
+
<item>+
<title>Qwen VLo: From "Understanding" the World to "Depicting" It</title>+
<link>https://qwenlm.github.io/blog/qwen-vlo/</link>+
<pubDate>Thu, 26 Jun 2025 22:00:04 +0800</pubDate>+
+
<guid>https://qwenlm.github.io/blog/qwen-vlo/</guid>+
<description>QWEN CHAT DISCORD+
Introduction The evolution of multimodal large models is continually pushing the boundaries of what we believe technology can achieve. From the initial QwenVL to the latest Qwen2.5 VL, we have made progress in enhancing the model&rsquo;s ability to understand image content. Today, we are excited…+
</item>+
+
<item>+
<title>Qwen3 Embedding: Advancing Text Embedding and Reranking Through Foundation Models</title>+
<link>https://qwenlm.github.io/blog/qwen3-embedding/</link>+
<pubDate>Thu, 05 Jun 2025 21:00:00 +0800</pubDate>+
+
<guid>https://qwenlm.github.io/blog/qwen3-embedding/</guid>+
<description>GITHUB HUGGING FACE MODELSCOPE DISCORD+
We release Qwen3 Embedding series, a new proprietary model of the Qwen model family. These models are specifically designed for text embedding, retrieval, and reranking tasks, built on the Qwen3 foundation model. Leveraging Qwen3’s robust multilingual text understanding capabilities, the series achi…+
</item>+
+
<item>+
<title>Qwen3: Think Deeper, Act Faster</title>+
<link>https://qwenlm.github.io/blog/qwen3/</link>+
<pubDate>Tue, 29 Apr 2025 04:00:00 +0800</pubDate>+
+
<guid>https://qwenlm.github.io/blog/qwen3/</guid>+
<description>QWEN CHAT GitHub Hugging Face ModelScope Kaggle DEMO DISCORD+
Introduction Today, we are excited to announce the release of Qwen3, the latest addition to the Qwen family of large language models. Our flagship model, Qwen3-235B-A22B, achieves competitive results in benchmark evaluations of coding, math, general capabilities, etc., when compared to other top-tie…+
</item>+
+
<item>+
<title>QVQ-Max: Think with Evidence</title>+
<link>https://qwenlm.github.io/blog/qvq-max-preview/</link>+
<pubDate>Fri, 28 Mar 2025 00:00:04 +0800</pubDate>+
+
<guid>https://qwenlm.github.io/blog/qvq-max-preview/</guid>+
<description>QWEN CHAT GITHUB HUGGING FACE MODELSCOPE DISCORD+
Introduction Last December, we launched QVQ-72B-Preview as an exploratory model, but it had many issues. Today, we are officially releasing the first version of QVQ-Max, our visual reasoning model. This model can not only &ldquo;understand&rdquo; the content in images and videos but also ana…+
</item>+
+
<item>+
<title>Qwen2.5 Omni: See, Hear, Talk, Write, Do It All!</title>+
<link>https://qwenlm.github.io/blog/qwen2.5-omni/</link>+
<pubDate>Thu, 27 Mar 2025 00:00:45 +0800</pubDate>+
+
<guid>https://qwenlm.github.io/blog/qwen2.5-omni/</guid>+
<description>QWEN CHAT HUGGING FACE MODELSCOPE DASHSCOPE GITHUB PAPER DEMO DISCORD+
We release Qwen2.5-Omni, the new flagship end-to-end multimodal model in the Qwen series. Designed for comprehensive multimodal perception, it seamlessly processes diverse inputs including text, images, audio, and video, while delivering real-time streaming responses through both text generation and…+
</item>+
+
<item>+
<title>Qwen2.5-VL-32B: Smarter and Lighter</title>+
<link>https://qwenlm.github.io/blog/qwen2.5-vl-32b/</link>+
<pubDate>Mon, 24 Mar 2025 00:00:04 +0800</pubDate>+
+
<guid>https://qwenlm.github.io/blog/qwen2.5-vl-32b/</guid>+
<description>QWEN CHAT GITHUB HUGGING FACE MODELSCOPE DISCORD+
Introduction At the end of January this year, we launched the Qwen2.5-VL series of models, which received widespread attention and positive feedback from the community. Building on the Qwen2.5-VL series, we continued to optimize the model using reinforcement learning and open-sourced the new VL mode…+
</item>+
+
<item>+
<title>QwQ-32B: Embracing the Power of Reinforcement Learning</title>+
<link>https://qwenlm.github.io/blog/qwq-32b/</link>+
<pubDate>Thu, 06 Mar 2025 00:00:04 +0800</pubDate>+
+
<guid>https://qwenlm.github.io/blog/qwq-32b/</guid>+
<description>QWEN CHAT Hugging Face ModelScope DEMO DISCORD+
Scaling Reinforcement Learning (RL) has the potential to enhance model performance beyond conventional pretraining and post-training methods. Recent studies have demonstrated that RL can significantly improve the reasoning capabilities of models. For instance, DeepSeek R1 has achieved state-of-the-a…+
Our research explores the scalability of Reinforcement Learning (RL) and its impact on enhancing the intelligence of large language models.</description>+
</item>+
+
<item>+
<title><think>...</think> QwQ-Max-Preview</title>+
<link>https://qwenlm.github.io/blog/qwq-max-preview/</link>+
<pubDate>Tue, 25 Feb 2025 02:00:04 +0800</pubDate>+
+
<guid>https://qwenlm.github.io/blog/qwq-max-preview/</guid>+
<description>QWEN CHAT DISCORD+
This is a blog created by QwQ-Max-Preview. We hope you enjoy it!+
Introduction &lt;think&gt;+
Okay, the user wants me to create a title and introduction for their blog announcing the release of QwQ-Max-Preview. Let me start by understanding the key points they mentioned. First, the model is part of the Qwen series, built on Qwen2.5-Max. It&rsquo;s a preview version, so they probably want…+
</item>+
+
<item>+
<title>Qwen2.5-Max: Exploring the Intelligence of Large-scale MoE Model</title>+
<link>https://qwenlm.github.io/blog/qwen2.5-max/</link>+
<pubDate>Tue, 28 Jan 2025 23:00:04 +0800</pubDate>+
+
<guid>https://qwenlm.github.io/blog/qwen2.5-max/</guid>+
<description>QWEN CHAT API DEMO DISCORD+
It is widely recognized that continuously scaling both data size and model size can lead to significant improvements in model intelligence. However, the research and industry community has limited experience in effectively scaling extremely large models, whether they are dense or Mixture-of-Expert (…+
</item>+
+
<item>+
<title>Qwen2.5-1M: Deploy Your Own Qwen with Context Length up to 1M Tokens</title>+
<link>https://qwenlm.github.io/blog/qwen2.5-1m/</link>+
<pubDate>Mon, 27 Jan 2025 00:00:03 +0800</pubDate>+
+
<guid>https://qwenlm.github.io/blog/qwen2.5-1m/</guid>+
<description>Tech Report HuggingFace ModelScope Qwen Chat HuggingFace Demo ModelScope Demo DISCORD+
Introduction Two months after upgrading Qwen2.5-Turbo to support context length up to one million tokens, we are back with the open-source Qwen2.5-1M models and the corresponding inference framework support. Here&rsquo;s what you can expect from this release:+
Opensource Models: We&rsquo;re releasing two new checkpoints, Qwen2.5-7B-Instruct-1M and Qwen2.5-14B-Instruct-1M, marking the first time we&rsquo;ve upgraded our opensource Qwen models to handle 1M-token contexts.</description>+
</item>+
+
<item>+
<title>Qwen2.5 VL! Qwen2.5 VL! Qwen2.5 VL!</title>+
<link>https://qwenlm.github.io/blog/qwen2.5-vl/</link>+
<pubDate>Sun, 26 Jan 2025 19:08:30 +0800</pubDate>+
+
<guid>https://qwenlm.github.io/blog/qwen2.5-vl/</guid>+
<description>QWEN CHAT GITHUB HUGGING FACE MODELSCOPE DISCORD+
We release Qwen2.5-VL, the new flagship vision-language model of Qwen and also a significant leap from the previous Qwen2-VL. To try the latest model, feel free to visit Qwen Chat and choose Qwen2.5-VL-72B-Instruct. Also, we open both base and instruct models in 3 sizes, including 3B, 7B, and 72B, i…+
The key features include:+
Understand things visually: Qwen2.</description>+
</item>+
+
<item>+
<title>Global-batch load balance almost free lunch to improve your MoE LLM training</title>+
<link>https://qwenlm.github.io/blog/global-load-balance/</link>+
<pubDate>Tue, 21 Jan 2025 00:00:03 +0800</pubDate>+
+
<guid>https://qwenlm.github.io/blog/global-load-balance/</guid>+
<description>GITHUB HUGGING FACE MODELSCOPE DISCORD+
Background The Mixture-of-Experts (MoEs) architecture has become a popular model-parameter-scale-up technique. Typically, one MoE layer consists of a router (often parameterized as one single Linear layer) and a group of experts (for transformer-based models, each expert is one feedforward layer). G…+
</item>+
+
<item>+
<title>Towards Effective Process Supervision in Mathematical Reasoning</title>+
<link>https://qwenlm.github.io/blog/qwen2.5-math-prm/</link>+
<pubDate>Tue, 14 Jan 2025 00:00:03 +0800</pubDate>+
+
<guid>https://qwenlm.github.io/blog/qwen2.5-math-prm/</guid>+
<description>GITHUB HUGGING FACE MODELSCOPE DISCORD+
Introduction In recent years, Large Language Models (LLMs) have made remarkable advances in mathematical reasoning, yet they can make mistakes, such as miscalculations or logical errors, leading to wrong conclusions. Moreover, even when achieving correct final answers, these powerful models can stil…+
</item>+
+
<item>+
<title>QVQ: To See the World with Wisdom</title>+
<link>https://qwenlm.github.io/blog/qvq-72b-preview/</link>+
<pubDate>Wed, 25 Dec 2024 00:00:03 +0800</pubDate>+
+
<guid>https://qwenlm.github.io/blog/qvq-72b-preview/</guid>+
<description>GITHUB HUGGING FACE MODELSCOPE KAGGLE DEMO DISCORD+
Language and vision intertwine in the human mind, shaping how we perceive and understand the world around us. Our ability to reason is deeply rooted in both linguistic thought and visual memory - but what happens when we extend these capabilities to AI? Today&rsquo;s large language models have d…+
</item>+
+
<item>+
<title>QwQ: Reflect Deeply on the Boundaries of the Unknown</title>+
<link>https://qwenlm.github.io/blog/qwq-32b-preview/</link>+
<pubDate>Thu, 28 Nov 2024 00:00:03 +0800</pubDate>+
+
<guid>https://qwenlm.github.io/blog/qwq-32b-preview/</guid>+
<description>GITHUB HUGGING FACE MODELSCOPE DEMO DISCORD+
Note: This is the pronunciation of QwQ: /kwju:/ , similar to the word &ldquo;quill&rdquo;.+
What does it mean to think, to question, to understand? These are the deep waters that QwQ (Qwen with Questions) wades into. Like an eternal student of wisdom, it approaches every problem - be it mathematics, code, or knowledge of our world - with genuine wonder and doubt. QwQ embodies that ancient …+
</item>+
+
<item>+
<title>Extending the Context Length to 1M Tokens!</title>+
<link>https://qwenlm.github.io/blog/qwen2.5-turbo/</link>+
<pubDate>Fri, 15 Nov 2024 00:00:03 +0800</pubDate>+
+
<guid>https://qwenlm.github.io/blog/qwen2.5-turbo/</guid>+
<description>API Documentation (Chinese) HuggingFace Demo ModelScope Demo+
Introduction After the release of Qwen2.5, we heard the community&rsquo;s demand for processing longer contexts. In recent months, we have made many optimizations for the model capabilities and inference performance of extremely long context. Today, we are proud to introduce the new Qwen2.5-Turb…+
Longer Context Support: We have extended the model&rsquo;s context length from 128k to 1M, which is approximately 1 million English words or 1.</description>+
</item>+
+
<item>+
<title>Qwen2.5-Coder Series: Powerful, Diverse, Practical.</title>+
<link>https://qwenlm.github.io/blog/qwen2.5-coder-family/</link>+
<pubDate>Tue, 12 Nov 2024 00:00:02 +0800</pubDate>+
+
<guid>https://qwenlm.github.io/blog/qwen2.5-coder-family/</guid>+
<description>GITHUB HUGGING FACE MODELSCOPE KAGGLE DEMO DISCORD+
Introduction Today, we are excited to open source the &ldquo;Powerful&rdquo;, &ldquo;Diverse&rdquo;, and &ldquo;Practical&rdquo; Qwen2.5-Coder series, dedicated to continuously promoting the development of Open CodeLLMs.+
Powerful: Qwen2.5-Coder-32B-Instruct has become the current SOTA open-source code model, matching the coding capabilities of GPT-4o. While demonstrating strong and comprehensive coding abilities, it also possesses good general and mathematical skills; Diverse: Building on the previously open-sourced…+
</item>+
+
<item>+
<title>Qwen2.5: A Party of Foundation Models!</title>+
<link>https://qwenlm.github.io/blog/qwen2.5/</link>+
<pubDate>Thu, 19 Sep 2024 00:00:04 +0800</pubDate>+
+
<guid>https://qwenlm.github.io/blog/qwen2.5/</guid>+
<description>GITHUB HUGGING FACE MODELSCOPE DEMO DISCORD+
Introduction In the past three months since Qwen2&rsquo;s release, numerous developers have built new models on the Qwen2 language models, providing us with valuable feedback. During this period, we have focused on creating smarter and more knowledgeable language models. Today, we are excited to…+
</item>+
+
<item>+
<title>Qwen2.5-LLM: Extending the boundary of LLMs</title>+
<link>https://qwenlm.github.io/blog/qwen2.5-llm/</link>+
<pubDate>Thu, 19 Sep 2024 00:00:03 +0800</pubDate>+
+
<guid>https://qwenlm.github.io/blog/qwen2.5-llm/</guid>+
<description>GITHUB HUGGING FACE MODELSCOPE DEMO DISCORD+
Introduction In this blog, we delve into the details of our latest Qwen2.5 series language models. We have developed a range of decoder-only dense models, with seven of them open-sourced, spanning from 0.5B to 72B parameters. Our research indicates a significant interest among users in models within…+
</item>+
+
<item>+
<title>Qwen2.5-Coder: Code More, Learn More!</title>+
<link>https://qwenlm.github.io/blog/qwen2.5-coder/</link>+
<pubDate>Thu, 19 Sep 2024 00:00:02 +0800</pubDate>+
+
<guid>https://qwenlm.github.io/blog/qwen2.5-coder/</guid>+
<description>GITHUB HUGGING FACE MODELSCOPE DEMO DISCORD+
Introduction In early April, we introduced CodeQwen1.5, which garnered significant attention from the community. Since then, we have been working to enhance the coding model. Today, we are excited to announce the release of the next generation of open-source coding models, Qwen2.5-Coder, and officia…+
</item>+
+
<item>+
<title>Qwen2.5-Math: The world's leading open-sourced mathematical LLMs</title>+
<link>https://qwenlm.github.io/blog/qwen2.5-math/</link>+
<pubDate>Thu, 19 Sep 2024 00:00:01 +0800</pubDate>+
+
<guid>https://qwenlm.github.io/blog/qwen2.5-math/</guid>+
<description>GITHUB HUGGING FACE MODELSCOPE DISCORD+
🚨 Qwen2.5-Math mainly supports solving English and Chinese math problems through CoT and TIR. We do not recommend using this series of models for other tasks. Introduction A month ago, we released the first series of mathematical LLMs - Qwen2-Math - of our Qwen family. Today, we have upgraded it an…+
</item>+
+
<item>+
<title>Qwen2-VL: To See the World More Clearly</title>+
<link>https://qwenlm.github.io/blog/qwen2-vl/</link>+
<pubDate>Thu, 29 Aug 2024 00:24:00 +0800</pubDate>+
+
<guid>https://qwenlm.github.io/blog/qwen2-vl/</guid>+
<description>DEMO GITHUB HUGGING FACE MODELSCOPE API DISCORD+
After a year&rsquo;s relentless efforts, today we are thrilled to release Qwen2-VL! Qwen2-VL is the latest version of the vision language models based on Qwen2 in the Qwen model familities. Compared with Qwen-VL, Qwen2-VL has the capabilities of:+
SoTA understanding of images of various resolution &amp; ratio: Qwen2-VL achieves state-of-the-art performance on visual understanding benchmarks, including MathVista, DocVQA, RealWorldQA, MTVQA, etc.+
Understanding videos of 20min+: Qwen2-VL can understand videos over 20 minutes for high-quality video-based question answering, dialog, content creation, etc.</description>+
</item>+
+
<item>+
<title>Qwen2-Audio: Chat with Your Voice!</title>+
<link>https://qwenlm.github.io/blog/qwen2-audio/</link>+
<pubDate>Fri, 09 Aug 2024 16:18:19 +0800</pubDate>+
+
<guid>https://qwenlm.github.io/blog/qwen2-audio/</guid>+
<description>DEMO PAPER GITHUB HUGGING FACE MODELSCOPE DISCORD+
To achieve the objective of building an AGI system, the model should be capable of understanding information from different modalities. Thanks to the rapid development of large language models, LLMs are now capable of understanding language and reasoning. Previously we have taken a step forward to e…+
</item>+
+
<item>+
<title>Introducing Qwen2-Math</title>+
<link>https://qwenlm.github.io/blog/qwen2-math/</link>+
<pubDate>Thu, 08 Aug 2024 00:00:00 +0800</pubDate>+
+
<guid>https://qwenlm.github.io/blog/qwen2-math/</guid>+
<description>GITHUB HUGGING FACE MODELSCOPE DISCORD+
🚨 This model mainly supports English. We will release bilingual (English and Chinese) math models soon. Introduction Over the past year, we have dedicated significant effort to researching and enhancing the reasoning capabilities of large language models, with a particular focus on their ability to…+
</item>+
+
<item>+
<title>Hello Qwen2</title>+
<link>https://qwenlm.github.io/blog/qwen2/</link>+
<pubDate>Fri, 07 Jun 2024 00:00:00 +0800</pubDate>+
+
<guid>https://qwenlm.github.io/blog/qwen2/</guid>+
<description>GITHUB HUGGING FACE MODELSCOPE DEMO DISCORD+
Introduction After months of efforts, we are pleased to announce the evolution from Qwen1.5 to Qwen2. This time, we bring to you:+
Pretrained and instruction-tuned models of 5 sizes, including Qwen2-0.5B, Qwen2-1.5B, Qwen2-7B, Qwen2-57B-A14B, and Qwen2-72B; Having been trained on data in 27 additional languages besides English and Chinese; State-of-the-art performance in a large number of benchmark evaluations; Significantly im…+
</item>+
+
<item>+
<title>Generalizing an LLM from 8k to 1M Context using Qwen-Agent</title>+
<link>https://qwenlm.github.io/blog/qwen-agent-2405/</link>+
<pubDate>Thu, 06 Jun 2024 11:59:59 +0800</pubDate>+
+
<guid>https://qwenlm.github.io/blog/qwen-agent-2405/</guid>+
<description>We&rsquo;ve created an agent using Qwen2 models with an 8k context size to understand documents with 1M tokens, surpassing RAG and native long-context models. This agent was also used to generate data for training new long-context Qwen models.</description>+
</item>+
+
<item>+
<title>Notes on Qwen-Max-0428</title>+
<link>https://qwenlm.github.io/blog/qwen-max-0428/</link>+
<pubDate>Sat, 11 May 2024 18:10:00 +0800</pubDate>+
+
<guid>https://qwenlm.github.io/blog/qwen-max-0428/</guid>+
<description>API DEMO DISCORD+
Previously, we opensourced a series of Qwen1.5 model ranging from 0.5 to 110 billion parameters. Now, we release a larger model, Qwen-Max-0428. Qwen-Max-0428 is an instruction-tuned model for chat service. Very recently, it is available via Chatbot Arena and it has now become the top-10 in the leade…+
Models MT-Bench Arena Qwen1.</description>+
</item>+
+
<item>+
<title>Qwen1.5-110B: The First 100B+ Model of the Qwen1.5 Series</title>+
<link>https://qwenlm.github.io/blog/qwen1.5-110b/</link>+
<pubDate>Thu, 25 Apr 2024 13:33:00 +0800</pubDate>+
+
<guid>https://qwenlm.github.io/blog/qwen1.5-110b/</guid>+
<description>GITHUB HUGGING FACE MODELSCOPE DEMO DISCORD+
Introduction Recently we have witnessed a burst of large-scale models with over 100 billion parameters in the opensource community. These models have demonstrated remarkable performance in both benchmark evaluation and chatbot arena. Today, we release the first 100B+ model of the Qwen1.5 series, Qwe…+
</item>+
+
<item>+
<title>Code with CodeQwen1.5</title>+
<link>https://qwenlm.github.io/blog/codeqwen1.5/</link>+
<pubDate>Tue, 16 Apr 2024 13:33:00 +0800</pubDate>+
+
<guid>https://qwenlm.github.io/blog/codeqwen1.5/</guid>+
<description>GITHUB HUGGING FACE MODELSCOPE DEMO DISCORD+
Introduction The advent of advanced programming tools, which harnesses the power of large language models (LLMs), has significantly enhanced programmer productivity and accuracy. Notwithstanding these advancements, dominant coding assistants like Github Copilot, built upon proprietary LLMs, pose not…+
</item>+
+
<item>+
<title>Qwen1.5-32B: Fitting the Capstone of the Qwen1.5 Language Model Series</title>+
<link>https://qwenlm.github.io/blog/qwen1.5-32b/</link>+
<pubDate>Tue, 02 Apr 2024 13:33:00 +0800</pubDate>+
+
<guid>https://qwenlm.github.io/blog/qwen1.5-32b/</guid>+
<description>GITHUB HUGGING FACE MODELSCOPE DEMO DISCORD+
Introduction The open-source community has long sought a model that strikes an ideal balance between performance, efficiency, and memory footprint. Despite the emergence of cutting-edge models like Qwen1.5-72B and DBRX, the models have faced persistent challenges such as large memory consumption, sl…Diff display stops at 400 lines. The line counts above are from the whole diff. 33 lines shown here cut at 300 characters. The raw artifact at this commit is linked above.