{"schema_version":"onlylabs.public_analysis_evidence.v1","title":"Qwen (Alibaba Cloud) analysis evidence pack","description":"Public onlylabs evidence pack for cited agent analysis: captured pages, ranked public signals, and stored web-search provenance used by the background analysis workflow.","url":"https://onlylabs.fyi/analysis/qwen","json_url":"https://onlylabs.fyi/analysis/qwen/evidence.json","generated_at":"2026-06-11T18:09:17.686Z","org":{"slug":"qwen","name":"Qwen (Alibaba Cloud)","category":"frontier-lab","category_label":"Frontier lab","dossier_url":"https://onlylabs.fyi/labs/qwen"},"analysis":{"url":"https://onlylabs.fyi/analysis/qwen","json_url":"https://onlylabs.fyi/analysis/qwen/analysis.json","generated_at":"2026-06-08T15:59:09.823+00:00"},"workflow":{"version":"synthesize-analyses","provider":null,"model":null,"agent":null,"public_pack_mode":"local-pages-and-events","live_web_fetches":false,"note":"Public evidence exports do not trigger live Exa calls; stored Exa provenance is included when analysis metadata contains it."},"stats":{"pages":28,"events":140,"web":0,"evidence":88,"signal_desks":{"hiring":5,"forks":2,"releases":30,"talking":12,"repos":11},"data_radar_lanes":{"data":1,"evals":2,"infrastructure":2,"safety":1,"product":5},"data_radar_matches":7,"stored_analysis_evidence":null,"stored_analysis_web":null,"stored_analysis_signal_desks":null,"stored_analysis_data_radar_lanes":null,"stored_analysis_data_radar_matches":null},"stored_web_provenance":null,"evidence":[{"ref":"P1","kind":"page","title":"QwenLM/open-computer-use demo-assets","date":"2026-06-11T07:04:04.301032+00:00","date_source":null,"source_url":"https://github.com/QwenLM/open-computer-use/releases/tag/demo-assets","signal_url":null,"signal_json_url":null,"text":"# Demo Assets\n\nRepository: QwenLM/open-computer-use\n\nTag: demo-assets\n\nPublished: 2026-06-10T16:23:31Z\n\nPrerelease: no\n\nRelease notes:\nDemo video assets"},{"ref":"P2","kind":"page","title":"QwenLM/Qwen repository metadata","date":"2026-06-11T03:59:06.942095+00:00","date_source":null,"source_url":"https://github.com/QwenLM/Qwen","signal_url":null,"signal_json_url":null,"text":"# QwenLM/Qwen\n\nDescription: The official repo of Qwen (通义千问) chat & pretrained large language model proposed by Alibaba Cloud.\n\nLanguage: Python\n\nLicense: Apache-2.0\n\nStars: 21271\n\nForks: 1828\n\nOpen issues: 43\n\nCreated: 2023-08-03T04:56:38Z\n\nPushed: 2026-03-05T13:55:17Z\n\nDefault branch: main\n\nFork: no\n\nArchived: no\n\nREADME:\n<p align=\"left\">\n<a href=\"README_CN.md\">中文</a>&nbsp ｜ &nbspEnglish&nbsp ｜ &nbsp<a href=\"README_JA.md\">日本語</a> ｜ &nbsp<a href=\"README_FR.md\">Français</a> ｜ &nbsp<a href=\"README_ES.md\">Español</a>\n</p>\n<br><br>\n\n<p align=\"center\">\n<img src=\"https://qianwen-res.oss-cn-beijing.aliyuncs.com/logo_qwen.jpg\" width=\"400\"/>\n<p>\n<br>\n\n<p align=\"center\">\n🤗 <a href=\"https://huggingface.co/Qwen\">Hugging Face</a>&nbsp&nbsp | &nbsp&nbsp🤖 <a href=\"https://modelscope.cn/organization/qwen\">ModelScope</a>&nbsp&nbsp | &nbsp&nbsp 📑 <a href=\"https://arxiv.org/abs/2309.16609\">Paper</a> &nbsp&nbsp ｜ &nbsp&nbsp🖥️ <a href=\"https://modelscope.cn/studios/qwen/Qwen-72B-Chat-Demo/summary\">Demo</a>\n<br>\n<a href=\"assets/wechat.png\">WeChat (微信)</a>&nbsp&nbsp | &nbsp&nbsp<a href=\"https://discord.gg/CV4E9rpNSD\">Discord</a>&nbsp&nbsp ｜ &nbsp&nbsp<a href=\"https://dashscope.aliyun.com\">API</a> \n</p>\n<br><br>\n\n> [!Important]\n> Qwen2 is here! You are welcome to follow [QwenLM/Qwen2](https://github.com/QwenLM/Qwen2) and share your experience there.\n>\n> This repo ([QwenLM/Qwen](https://github.com/QwenLM/Qwen)) is no longer actively maintained, due to substantial codebase differences.\n\n<br>\n\n| | Qwen-Chat | Qwen-Chat (Int4) | Qwen-Chat (Int8) | Qwen |\n|-----|:------------------------------------------------------------------------------------------------------------------------------------:|:----------------------------------------------------------------------------------------------------------------------------------------------:|:---------------------------------------------------------------:|:--------------------------------------------------------------------------------------------------------------------------:|\n| 1.8B | <a href=\"https://modelscope.cn/models/qwen/Qwen-1_8B-Chat/summary\">🤖</a> <a href=\"https://huggingface.co/Qwen/Qwen-1_8B-Chat\">🤗</a> | <a href=\"https://m"},{"ref":"P3","kind":"page","title":"QwenLM/Qwen-VL repository metadata","date":"2026-06-11T03:59:06.678232+00:00","date_source":null,"source_url":"https://github.com/QwenLM/Qwen-VL","signal_url":null,"signal_json_url":null,"text":"# QwenLM/Qwen-VL\n\nDescription: The official repo of Qwen-VL (通义千问-VL) chat & pretrained large vision language model proposed by Alibaba Cloud.\n\nLanguage: Python\n\nLicense: NOASSERTION\n\nStars: 6666\n\nForks: 491\n\nOpen issues: 324\n\nCreated: 2023-08-21T07:57:15Z\n\nPushed: 2024-08-07T02:37:06Z\n\nDefault branch: master\n\nFork: no\n\nArchived: no\n\nREADME:\n<p align=\"left\">\n<a href=\"README_CN.md\">中文</a>&nbsp ｜ &nbspEnglish&nbsp&nbsp ｜ &nbsp<a href=\"README_JA.md\">日本語</a>&nbsp｜ &nbsp<a href=\"README_KO.md\">한국어</a>&nbsp\n</p>\n<br><br>\n\n<p align=\"center\">\n<img src=\"assets/logo.jpg\" width=\"400\"/>\n<p>\n<br>\n\n<p align=\"center\">\nQwen-VL \n<a href=\"https://huggingface.co/Qwen/Qwen-VL\">🤗</a>\n<a href=\"https://modelscope.cn/models/qwen/Qwen-VL/summary\">🤖</a>&nbsp ｜ \nQwen-VL-Chat \n<a href=\"https://huggingface.co/Qwen/Qwen-VL-Chat\">🤗</a>\n<a href=\"https://modelscope.cn/models/qwen/Qwen-VL-Chat/summary\">🤖</a>&nbsp \n(Int4: \n<a href=\"https://huggingface.co/Qwen/Qwen-VL-Chat-Int4\">🤗</a> \n<a href=\"https://modelscope.cn/models/qwen/Qwen-VL-Chat-Int4/summary\">🤖</a>&nbsp) ｜\nQwen-VL-Plus \n<a href=\"https://huggingface.co/spaces/Qwen/Qwen-VL-Plus\">🤗</a> \n<a href=\"https://modelscope.cn/studios/qwen/Qwen-VL-Chat-Demo/summary\">🤖</a>&nbsp ｜ \nQwen-VL-Max \n<a href=\"https://huggingface.co/spaces/Qwen/Qwen-VL-Max\">🤗</a>\n<a href=\"https://modelscope.cn/studios/qwen/Qwen-VL-Max/summary\">🤖</a>&nbsp\n<br>\n<a href=\"https://tongyi.aliyun.com/qianwen\">Web</a>&nbsp&nbsp | &nbsp&nbsp\n<a href=\"http://ofasys-wlcb.oss-accelerate-overseas.aliyuncs.com/QwenVL/blog/app_qrcode.jpg\">APP</a>&nbsp&nbsp | &nbsp&nbsp\n<a href=\"https://help.aliyun.com/zh/dashscope/developer-reference/vl-plus-quick-start\">API</a>&nbsp&nbsp | &nbsp&nbsp\n<a href=\"https://github.com/QwenLM/Qwen/blob/main/assets/wechat.png\">WeChat</a>&nbsp&nbsp | &nbsp&nbsp\n<a href=\"https://discord.gg/CV4E9rpNSD\">Discord</a>&nbsp&nbsp | &nbsp&nbsp\n<a href=\"https://arxiv.org/abs/2308.12966\">Paper</a>&nbsp&nbsp | &nbsp&nbsp\n<a href=\"TUTORIAL.md\">Tutorial</a>\n</p>\n<br><br>\n\n---\n## Qwen-VL-Plus & Qwen-VL-Max\n\nQwen-Vl-Plus and Qwen-VL-Max are the upgraded and latest versions of the Qwen-VL model family, currently supporting access for free through <a href=\"https://huggingf"},{"ref":"P4","kind":"page","title":"QwenLM/Qwen-Agent repository metadata","date":"2026-06-11T03:59:06.403235+00:00","date_source":null,"source_url":"https://github.com/QwenLM/Qwen-Agent","signal_url":null,"signal_json_url":null,"text":"# QwenLM/Qwen-Agent\n\nDescription: Agent framework and applications built upon Qwen>=3.0, featuring Function Calling, MCP, Code Interpreter, RAG, Chrome extension, etc.\n\nLanguage: Python\n\nLicense: Apache-2.0\n\nStars: 16511\n\nForks: 1631\n\nOpen issues: 508\n\nCreated: 2023-09-22T02:24:56Z\n\nPushed: 2026-03-04T08:15:07Z\n\nDefault branch: main\n\nFork: no\n\nArchived: no\n\nREADME:\n<!---\nCopyright 2023 The Qwen team, Alibaba Group. All rights reserved.\n\nLicensed under the Apache License, Version 2.0 (the \"License\");\nyou may not use this file except in compliance with the License.\nYou may obtain a copy of the License at\n\nhttp://www.apache.org/licenses/LICENSE-2.0\n\nUnless required by applicable law or agreed to in writing, software\ndistributed under the License is distributed on an \"AS IS\" BASIS,\nWITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.\nSee the License for the specific language governing permissions and\nlimitations under the License.\n-->\n\n[中文](https://github.com/QwenLM/Qwen-Agent/blob/main/README_CN.md) ｜ English\n\n<p align=\"center\">\n<img src=\"https://qianwen-res.oss-accelerate-overseas.aliyuncs.com/logo_qwen_agent.png\" width=\"400\"/>\n<p>\n<br>\n\n<p align=\"center\">\n💜 <a href=\"https://chat.qwen.ai/\"><b>Qwen Chat</b></a>&nbsp&nbsp | &nbsp&nbsp🤗 <a href=\"https://huggingface.co/Qwen\">Hugging Face</a>&nbsp&nbsp | &nbsp&nbsp🤖 <a href=\"https://modelscope.cn/organization/qwen\">ModelScope</a>&nbsp&nbsp | &nbsp&nbsp 📑 <a href=\"https://qwenlm.github.io/\">Blog</a> &nbsp&nbsp ｜ &nbsp&nbsp📖 <a href=\"https://qwenlm.github.io/Qwen-Agent/en/\">Documentation</a>\n\n<br>\n📊 <a href=\"https://qwenlm.github.io/Qwen-Agent/en/benchmarks/deepplanning/\">Benchmark</a>&nbsp&nbsp | &nbsp&nbsp💬 <a href=\"https://github.com/QwenLM/Qwen/blob/main/assets/wechat.png\">WeChat (微信)</a>&nbsp&nbsp | &nbsp&nbsp🫨 <a href=\"https://discord.gg/CV4E9rpNSD\">Discord</a>&nbsp&nbsp\n</p>\n\nQwen-Agent is a framework for developing LLM applications based on the instruction following, tool usage, planning, and\nmemory capabilities of Qwen.\nIt also comes with example applications such as Browser Assistant, Code Interpreter, and Custom Assistant.\nNow Qwen-Agent plays as the backend of [Qwen Chat](https://c"},{"ref":"P5","kind":"page","title":"QwenLM/qwen.cpp repository metadata","date":"2026-06-11T03:59:06.193175+00:00","date_source":null,"source_url":"https://github.com/QwenLM/qwen.cpp","signal_url":null,"signal_json_url":null,"text":"# QwenLM/qwen.cpp\n\nDescription: C++ implementation of Qwen-LM\n\nLanguage: C++\n\nLicense: NOASSERTION\n\nStars: 627\n\nForks: 64\n\nOpen issues: 68\n\nCreated: 2023-09-24T07:45:24Z\n\nPushed: 2024-12-06T08:32:28Z\n\nDefault branch: master\n\nFork: no\n\nArchived: yes\n\nREADME:\n> [!IMPORTANT]\n>\n> **End of Active Maintenance for qwen.cpp**\n> \n> Since December 2023, the core features of qwen.cpp have been integrated into llama.cpp. As of December 2024, qwen.cpp no longer offers the same level of functionality, efficiency, and device support as llama.cpp, including updates to newer Qwen models.\n>\n> We regret to announce that we will no longer actively maintain qwen.cpp. This means we will not be addressing issues, merging pull requests, or releasing updates. For ongoing development and support, we encourage you to explore [llama.cpp](https://github.com/ggerganov/llama.cpp), which continues to evolve with new features and improvements.\n>\n> Thank you for being part of our journey.\n\n# qwen.cpp\n\nC++ implementation of [Qwen-LM](https://github.com/QwenLM/Qwen) for real-time chatting on your MacBook.\n\n## Updates\n- **`2023/12/05`** qwen was merged to [llama.cpp](https://github.com/ggerganov/llama.cpp/pull/4281) and supports gguf format.\n\n## Features\n\nHighlights:\n* [x] Pure C++ implementation based on [ggml](https://github.com/ggerganov/ggml), working in the same way as [llama.cpp](https://github.com/ggerganov/llama.cpp).\n* [x] Pure C++ tiktoken implementation.\n* [x] Streaming generation with typewriter effect.\n* [x] Python binding.\n\nSupport Matrix:\n* Hardwares: x86/arm CPU, NVIDIA GPU\n* Platforms: Linux, MacOS\n* Models: [Qwen-LM](https://github.com/QwenLM/Qwen)\n\n## Getting Started\n\n**Preparation**\n\nClone the qwen.cpp repository into your local machine:\n```sh\ngit clone --recursive https://github.com/QwenLM/qwen.cpp && cd qwen.cpp\n```\n\nIf you forgot the `--recursive` flag when cloning the repository, run the following command in the `qwen.cpp` folder:\n```sh\ngit submodule update --init --recursive\n```\n\nDownload the qwen.tiktoken file from [Hugging Face](https://huggingface.co/Qwen/Qwen-7B-Chat/blob/main/qwen.tiktoken) or [modelscope](https://modelscope.cn/models/qwen/Qwen-7B-Chat/files).\n\n**Quant"},{"ref":"P6","kind":"page","title":"QwenLM/Qwen-Audio repository metadata","date":"2026-06-11T03:59:06.159779+00:00","date_source":null,"source_url":"https://github.com/QwenLM/Qwen-Audio","signal_url":null,"signal_json_url":null,"text":"# QwenLM/Qwen-Audio\n\nDescription: The official repo of Qwen-Audio (通义千问-Audio) chat & pretrained large audio language model proposed by Alibaba Cloud.\n\nLanguage: Python\n\nLicense: NOASSERTION\n\nStars: 1902\n\nForks: 145\n\nOpen issues: 63\n\nCreated: 2023-11-07T06:31:39Z\n\nPushed: 2024-07-05T09:17:49Z\n\nDefault branch: main\n\nFork: no\n\nArchived: no\n\nREADME:\n<p align=\"left\">\n<a href=\"README_CN.md\">中文</a> &nbsp｜ &nbsp English&nbsp&nbsp\n</p>\n<br><br>\n\n<p align=\"center\">\n<img src=\"assets/audio_logo.jpg\" width=\"400\"/>\n<p>\n<br>\n\n<p align=\"center\">\nQwen-Audio <a href=\"https://www.modelscope.cn/models/qwen/QWen-Audio/summary\">🤖 <a> | <a href=\"https://huggingface.co/Qwen/Qwen-Audio\">🤗</a>&nbsp ｜ Qwen-Audio-Chat <a href=\"https://www.modelscope.cn/models/qwen/QWen-Audio-Chat/summary\">🤖 <a>| <a href=\"https://huggingface.co/Qwen/Qwen-Audio-Chat\">🤗</a>&nbsp | &nbsp&nbsp Demo<a href=\"https://modelscope.cn/studios/qwen/Qwen-Audio-Chat-Demo/summary\"> 🤖</a> | <a href=\"https://huggingface.co/spaces/Qwen/Qwen-Audio\">🤗</a>&nbsp\n<br>\n&nbsp&nbsp<a href=\"https://qwen-audio.github.io/Qwen-Audio/\">Homepage</a>&nbsp ｜ &nbsp&nbsp<a href=\"http://arxiv.org/abs/2311.07919\">Paper</a>&nbsp&nbsp | &nbsp&nbsp&nbsp<a href=\"https://github.com/QwenLM/Qwen/blob/main/assets/wechat.png\">WeChat</a>&nbsp&nbsp | &nbsp&nbsp<a href=\"https://discord.gg/CV4E9rpNSD\">Discord</a>&nbsp&nbsp</a>\n</p>\n<br><br>\n\n[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/qwen-audio-advancing-universal-audio/speech-recognition-on-aishell-1)](https://paperswithcode.com/sota/speech-recognition-on-aishell-1?p=qwen-audio-advancing-universal-audio)\n[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/qwen-audio-advancing-universal-audio/speech-recognition-on-aishell-2-test-android-1)](https://paperswithcode.com/sota/speech-recognition-on-aishell-2-test-android-1?p=qwen-audio-advancing-universal-audio)\n[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/qwen-audio-advancing-universal-audio/speech-recognition-on-aishell-2-test-ios)](https://paperswithcode.com/sota/speech-recognition-on-aishell-2-test-ios?p=qwen-audio-advancing-universal-audio)\n[![PWC]("},{"ref":"P7","kind":"page","title":"QwenLM/qwenlm.github.io repository metadata","date":"2026-06-11T03:59:06.149709+00:00","date_source":null,"source_url":"https://github.com/QwenLM/qwenlm.github.io","signal_url":null,"signal_json_url":null,"text":"# QwenLM/qwenlm.github.io\n\nDescription: 👑 Qwen Blog. Visit https://qwen.ai/research for the latest news.\n\nLanguage: HTML\n\nStars: 106\n\nForks: 33\n\nOpen issues: 8\n\nCreated: 2024-01-23T14:52:45Z\n\nPushed: 2026-01-21T12:15:45Z\n\nDefault branch: main\n\nFork: no\n\nArchived: no\n\nREADME:\n# Qwen's Blog\n\n> [!IMPORTANT]\n> This blog is no longer being updated. For the latest news, please visit [qwen.ai](https://qwen.ai/research)."},{"ref":"P8","kind":"page","title":"QwenLM/Qwen3 repository metadata","date":"2026-06-11T03:59:05.932962+00:00","date_source":null,"source_url":"https://github.com/QwenLM/Qwen3","signal_url":null,"signal_json_url":null,"text":"# QwenLM/Qwen3\n\nDescription: Qwen3 is the large language model series developed by Qwen team, Alibaba Cloud.\n\nLanguage: Python\n\nStars: 27302\n\nForks: 1993\n\nOpen issues: 53\n\nCreated: 2024-02-05T05:45:08Z\n\nPushed: 2026-01-09T03:05:47Z\n\nDefault branch: main\n\nFork: no\n\nArchived: no\n\nREADME:\n# Qwen3\n\n<p align=\"center\">\n<img src=\"https://qianwen-res.oss-accelerate-overseas.aliyuncs.com/logo_qwen3.png\" width=\"400\"/>\n<p>\n\n<p align=\"center\">\n💜 <a href=\"https://chat.qwen.ai/\"><b>Qwen Chat</b></a>&nbsp&nbsp | &nbsp&nbsp🤗 <a href=\"https://huggingface.co/Qwen\">Hugging Face</a>&nbsp&nbsp | &nbsp&nbsp🤖 <a href=\"https://modelscope.cn/organization/qwen\">ModelScope</a>&nbsp&nbsp | &nbsp&nbsp 📑 <a href=\"https://arxiv.org/abs/2505.09388\">Paper</a> &nbsp&nbsp | &nbsp&nbsp 📑 <a href=\"https://qwenlm.github.io/blog/qwen3/\">Blog</a> &nbsp&nbsp ｜ &nbsp&nbsp📖 <a href=\"https://qwen.readthedocs.io/\">Documentation</a>\n<br>\n🖥️ <a href=\"https://huggingface.co/spaces/Qwen/Qwen3-Demo\">Demo</a>&nbsp&nbsp | &nbsp&nbsp💬 <a href=\"https://github.com/QwenLM/Qwen/blob/main/assets/wechat.png\">WeChat (微信)</a>&nbsp&nbsp | &nbsp&nbsp🫨 <a href=\"https://discord.gg/CV4E9rpNSD\">Discord</a>&nbsp&nbsp\n</p>\n\nVisit our Hugging Face or ModelScope organization (click links above), search checkpoints with names starting with `Qwen3-` or visit the [Qwen3 collection](https://huggingface.co/collections/Qwen/qwen3-67dd247413f0e2e4f653967f), and you will find all you need! Enjoy!\n\nTo learn more about Qwen3, feel free to read our documentation \\[[EN](https://qwen.readthedocs.io/en/latest/)|[ZH](https://qwen.readthedocs.io/zh-cn/latest/)\\]. Our documentation consists of the following sections:\n\n- Quickstart: the basic usages and demonstrations;\n- Inference: the guidance for the inference with Transformers, including batch inference, streaming, etc.;\n- Run Locally: the instructions for running LLM locally on CPU and GPU, with frameworks like llama.cpp, Ollama, and LM Studio;\n- Deployment: the demonstration of how to deploy Qwen for large-scale inference with frameworks like SGLang, vLLM, TGI, etc.;\n- Quantization: the practice of quantizing LLMs with GPTQ, AWQ, as well as the guidance for how to make high-quality qua"},{"ref":"P9","kind":"page","title":"QwenLM/Qwen3-Coder repository metadata","date":"2026-06-11T03:59:05.682536+00:00","date_source":null,"source_url":"https://github.com/QwenLM/Qwen3-Coder","signal_url":null,"signal_json_url":null,"text":"# QwenLM/Qwen3-Coder\n\nDescription: Qwen3-Coder is the code version of Qwen3, the large language model series developed by Qwen team.\n\nLanguage: Python\n\nStars: 16611\n\nForks: 1200\n\nOpen issues: 108\n\nCreated: 2024-04-16T11:49:01Z\n\nPushed: 2026-03-24T08:22:10Z\n\nDefault branch: main\n\nFork: no\n\nArchived: no\n\nREADME:\n<a name=\"readme-top\"></a>\n\n<p align=\"center\">\n<img src=\"https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen3-Coder/qwen3_coder.png\" width=\"400\"/>\n</p>\n\n<p align=\"center\">\n<img src=\"https://qianwen-res.oss-accelerate-overseas.aliyuncs.com/Qwen3-Coder-Next/swebench_pro.png\" width=\"800\"/>\n</p>\n\n<p align=\"center\">\n💜 <a href=\"https://chat.qwen.ai/\"><b>Qwen Chat</b></a>&nbsp&nbsp | &nbsp&nbsp🤗 <a href=\"https://huggingface.co/collections/Qwen/qwen3-coder-687fc861e53c939e52d52d10\">Hugging Face</a>&nbsp&nbsp | &nbsp&nbsp🤖 <a href=\"https://modelscope.cn/organization/qwen\">ModelScope</a>&nbsp&nbsp | &nbsp&nbsp 📑 <a href=\"https://qwenlm.github.io/blog/qwen3-coder-next/\">Blog</a> &nbsp&nbsp ｜ &nbsp&nbsp📖 <a href=\"https://qwen.readthedocs.io/\">Documentation</a>\n<br>\n🌍 <a href=\"https://huggingface.co/spaces/Qwen/Qwen3-Coder-WebDev\">WebDev</a>&nbsp&nbsp | &nbsp&nbsp💬 <a href=\"https://github.com/QwenLM/Qwen/blob/main/assets/wechat.png\">WeChat (微信)</a>&nbsp&nbsp | &nbsp&nbsp🫨 <a href=\"https://discord.gg/CV4E9rpNSD\"> Discord</a>&nbsp&nbsp | &nbsp&nbsp 📄 <a href=\"https://github.com/QwenLM/Qwen3-Coder/blob/main/qwen3_coder_next_tech_report.pdf\">Arxiv</a>&nbsp&nbsp | &nbsp&nbsp 👽 <a href=\"https://github.com/QwenLM/qwen-code\">Qwen Code</a>\n</p>\n\nVisit our Hugging Face or ModelScope organization (click links above), search checkpoints with names starting with `Qwen3-Coder-`, and you will find all you need! Enjoy!\n\n---\n\n## Table of Contents\n- [Introduction](#introduction)\n- [Key Features](#key-features)\n- [Basic Information](#basic-information)\n- [Quick Start](#quick-start)\n- [👉🏻 Chat with Qwen3-Coder](#-chat-with-qwen3-coder)\n- [Fill in the middle with Qwen3-Coder](#fill-in-the-middle-with-qwen3-coder)\n- [Use Cases](#use-cases)\n- [Example: Releasing a Website](#example-releasing-a-website)\n- [Example: Desktop Tidy](#example-desktop-tidy)\n- [Example: Zombies vs. Plant"},{"ref":"P10","kind":"page","title":"QwenLM/online_merging_optimizers repository metadata","date":"2026-06-11T03:59:05.337107+00:00","date_source":null,"source_url":"https://github.com/QwenLM/online_merging_optimizers","signal_url":null,"signal_json_url":null,"text":"# QwenLM/online_merging_optimizers\n\nDescription: Implementations of online merging optimizers proposed by Online Merging Optimizers for Boosting Rewards and Mitigating Tax in Alignment\n\nLanguage: Python\n\nLicense: Apache-2.0\n\nStars: 83\n\nForks: 14\n\nOpen issues: 2\n\nCreated: 2024-05-28T03:57:37Z\n\nPushed: 2024-06-19T12:52:34Z\n\nDefault branch: main\n\nFork: no\n\nArchived: no\n\nREADME:\n# Online Merging Optimizers\n\n*Keming Lu, Bowen Yu, Fei Huang, Yang Fan, Runji Lin, Chang Zhou*\n\nQwen, Alibaba Inc.\n\nThis is the repository contains core implementations of the online merging optimizers, proposed by [Online Merging Optimizers for Boosting Rewards and\nMitigating Tax in Alignment]().\n\n## Update\n\nThanks for the interest in online merging optimizers! We are working on a PR to merge our optimizers into LLaMa-Factory. Stay tune!\n\n## Introduction\n\nEffectively aligning Large Language Models (LLMs) with human-centric values while preventing the degradation of abilities acquired through Pre-training and Supervised Fine-tuning (SFT) poses a central challenge in Reinforcement Learning from Human Feedback (RLHF). In this paper, we first discover that interpolating RLHF and SFT model parameters can adjust the trade-off between human preference and basic capabilities, thereby reducing the alignment tax at the cost of alignment reward. Inspired by this, we propose integrating the RL policy and SFT models at each optimization step in RLHF to continuously regulate the training direction, introducing the Online Merging Optimizer. Specifically, we merge gradients with the parameter differences between SFT and pretrained models, effectively steering the gradient towards maximizing rewards in the direction of SFT optimization. We demonstrate that our optimizer works well with different LLM families, such as Qwen and LLaMA, across various model sizes ranging from 1.8B to 8B, various RLHF algorithms like DPO and KTO, and existing model merging methods. It significantly enhances alignment reward while mitigating alignment tax, achieving higher overall performance across 14 benchmarks. A more detailed manuscript in [paper](assets/online_merging_arxiv_review.pdf).\n\n<img src=\"assets/main.jpg\">\n\n## Insta"},{"ref":"P11","kind":"page","title":"QwenLM/ConsisEval repository metadata","date":"2026-06-11T03:59:05.329164+00:00","date_source":null,"source_url":"https://github.com/QwenLM/ConsisEval","signal_url":null,"signal_json_url":null,"text":"# QwenLM/ConsisEval\n\nLanguage: Python\n\nLicense: MIT\n\nStars: 15\n\nForks: 9\n\nOpen issues: 0\n\nCreated: 2024-06-17T07:46:23Z\n\nPushed: 2024-07-05T07:54:29Z\n\nDefault branch: preview\n\nFork: no\n\nArchived: no\n\nREADME:\n<div align=\"center\">\n<h2><i>ConsisEval:</i> A Hard-to-Easy Consistency Evaluation<br>Benchmark for Large Language Models</h2> \n</div>\n\n<!-- <p align=\"center\">\n| <b>Paper</b> | <b>Leaderboard</b> |\n</p> -->\n\n<!-- This is the repo for our paper: Can Large Language Models Always Solve Easy Problems if They Can Solve Harder Ones? -->\n- This repo is for paper [Can Large Language Models Always Solve Easy Problems if They Can Solve Harder Ones?](https://arxiv.org/abs/2406.12809)\n\n## Overview\n\nConsisEval is developed to systematically evaluate the hard-to-easy consistency of LLMs. Here the hard-to-easy inconsistency refers to the counter-intuitive phenomenons where LLMs, while capable of solving hard problems, can paradoxically fail at easier ones. \n\nConsisEval includes 732 pair of questions from code (164), mathematics (298), and instruction-following (270) domains. It is noteworthy that there are only pairwise data in ConsisEval: one datum is comprised of two questions (an easy question and a harder one), and there is a strict order of difficulty between these two questions.\n\n## Data\n\n- Easy data is collected from [gsm8k](https://github.com/openai/grade-school-math), [IFEval](https://github.com/google-research/google-research/tree/master/instruction_following_eval) and [HumanEval](https://github.com/openai/human-eval).\n- hard data derived from easy data by automatic generation and human annotation.\n- ConsisEval (the combination of easy and hard data) is in directory [`data`](./data).\n\n## Evaluation Metric\n\n- Consistency Score (CS): conditional probability of a model correctly answering easy questions provided that it has correctly answered harder ones. \n\n<!-- - Relative Consistency Score (RCS): the rank of CS among a series of models with similar capabilities, indicating the potential for consistency improvement at current capability. -->\n\nFor more details about metrics, please refer to our paper.\n\n## Environments\n\nAll Python packages required to run are listed in"},{"ref":"P12","kind":"page","title":"QwenLM/AutoIF repository metadata","date":"2026-06-11T03:59:05.309908+00:00","date_source":null,"source_url":"https://github.com/QwenLM/AutoIF","signal_url":null,"signal_json_url":null,"text":"# QwenLM/AutoIF\n\nLanguage: Python\n\nLicense: Apache-2.0\n\nStars: 333\n\nForks: 32\n\nOpen issues: 2\n\nCreated: 2024-06-19T12:38:08Z\n\nPushed: 2024-07-25T05:43:27Z\n\nDefault branch: main\n\nFork: no\n\nArchived: no\n\nREADME:\n# Self-play with Execution Feedback: Improving Instruction-following Capabilities of Large Language Models\n\n[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/self-play-with-execution-feedback-improving/instruction-following-on-ifeval)](https://paperswithcode.com/sota/instruction-following-on-ifeval?p=self-play-with-execution-feedback-improving)\n\n*Guanting Dong, Keming Lu, Chengpeng Li, Tingyu Xia, Bowen Yu, Chang Zhou, Jingren Zhou*\n\nQwen, Alibaba Inc.\n\n---\n\n## :sparkles: Overview\n\nThis is the repository contains core implementations of the **AutoIF**, proposed by [Self-play with Execution Feedback: Improving Instruction-following Capabilities of Large Language Models](https://arxiv.org/abs/2406.13542).\n\n**AutoIF** is the first scalable and reliable method for automatically generating instruction-following data and verifying its quality using code execution feedback.\n\n![image](https://github.com/dongguanting/AutoIF/assets/60767110/6c222465-25a4-4dec-ade6-d3a5af80ba39)\n\n## :rocket: Data Synthesis of AutoIF\nWe divided the AutoIF's data synthesis process into steps and provided 10-20 samples per step to facilitate your reproduction. Please remember to replace them with your own input.\n\n### :wrench: Dependencies\nGeneral Setup Environment:\n- Python 3.9\n- [PyTorch](http://pytorch.org/) (currently tested on version 2.1.2+cu121)\n- [Transformers](http://huggingface.co/transformers/) (version 4.41.2, unlikely to work lower than this version)\n\n```bash\ncd ./AutoIF/\npip install -r requirements.txt\n```\n---\n\n## Instruction Augmentation and Verification\n\nFirstly, we hand-write 36 seed instructions：\n![image](https://github.com/dongguanting/AutoIF/assets/60767110/62518bd7-f5d9-4a33-a85f-1327b77e4dcb)\n\n**Step1: Self-instruct Seed Instructions** \n\nConcatenate the instruction with the RFT prompt.\n\n```bash\npython 1_RFT.py\n```\n\nPlease perform k times RFT with a supervised model (e.g., GPT-4, Qwen2-72B), save as format in seed_instruction.txt.\n\n**St"},{"ref":"P13","kind":"page","title":"QwenLM/Qwen2-Audio repository metadata","date":"2026-06-11T03:59:05.156148+00:00","date_source":null,"source_url":"https://github.com/QwenLM/Qwen2-Audio","signal_url":null,"signal_json_url":null,"text":"# QwenLM/Qwen2-Audio\n\nDescription: The official repo of Qwen2-Audio chat & pretrained large audio language model proposed by Alibaba Cloud.\n\nLanguage: Python\n\nStars: 2078\n\nForks: 165\n\nOpen issues: 115\n\nCreated: 2024-06-24T06:11:27Z\n\nPushed: 2025-04-21T08:50:49Z\n\nDefault branch: main\n\nFork: no\n\nArchived: no\n\nREADME:\n<p align=\"left\">\n<a href=\"README_CN.md\">中文</a> &nbsp｜ &nbsp English&nbsp&nbsp\n</p>\n<br><br>\n\n<p align=\"center\">\n<img src=\"https://qianwen-res.oss-cn-beijing.aliyuncs.com/assets/blog/qwenaudio/qwen2audio_logo.png\" width=\"400\"/>\n<p>\n\n<p align=\"center\">\nQwen2-Audio-7B <a href=\"https://modelscope.cn/models/qwen/Qwen2-Audio-7B\">🤖 </a> | <a href=\"https://huggingface.co/Qwen/Qwen2-Audio-7B\">🤗</a>&nbsp ｜ Qwen-Audio-7B-Instruct <a href=\"https://modelscope.cn/models/qwen/Qwen2-Audio-7B-Instruct\">🤖 </a>| <a href=\"https://huggingface.co/Qwen/Qwen2-Audio-7B-Instruct\">🤗</a>&nbsp ｜ Demo<a href=\"https://modelscope.cn/studios/qwen/Qwen2-Audio-Instruct-Demo\"> 🤖</a> | <a href=\"https://huggingface.co/spaces/Qwen/Qwen2-Audio-Instruct-Demo\">🤗</a>&nbsp\n<br>\n📑 <a href=\"https://arxiv.org/abs/2407.10759\">Paper</a> &nbsp&nbsp | &nbsp&nbsp 📑 <a href=\"https://qwenlm.github.io/blog/qwen2-audio\">Blog</a> &nbsp&nbsp | &nbsp&nbsp 💬 <a href=\"https://github.com/QwenLM/Qwen/blob/main/assets/wechat.png\">WeChat (微信)</a>&nbsp&nbsp | &nbsp&nbsp <a href=\"https://discord.gg/CV4E9rpNSD\">Discord</a>&nbsp&nbsp\n</p>\n\nWe introduce the latest progress of Qwen-Audio, a large-scale audio-language model called Qwen2-Audio, which is capable of accepting various audio signal inputs and performing audio analysis or direct textual responses with regard to speech instructions. We introduce two distinct audio interaction modes:\n\n* voice chat: users can freely engage in voice interactions with Qwen2-Audio without text input;\n* audio analysis: users could provide audio and text instructions for analysis during the interaction;\n\n**We've released two models of the Qwen2-Audio series: Qwen2-Audio-7B and Qwen2-Audio-7B-Instruct.**\n\n## Architecture\n\nThe overview of three-stage training process of Qwen2-Audio.\n\n<p align=\"center\">\n<img src=\"assets/framework.png\" width=\"80%\"/>\n<p>\n\n## News and Updates\n* 2024"},{"ref":"P14","kind":"page","title":"QwenLM/Qwen2.5-Math repository metadata","date":"2026-06-11T03:59:04.841951+00:00","date_source":null,"source_url":"https://github.com/QwenLM/Qwen2.5-Math","signal_url":null,"signal_json_url":null,"text":"# QwenLM/Qwen2.5-Math\n\nDescription: A series of math-specific large language models of our Qwen2 series.\n\nLanguage: Python\n\nStars: 1078\n\nForks: 160\n\nOpen issues: 43\n\nCreated: 2024-08-08T08:55:39Z\n\nPushed: 2025-01-11T17:30:43Z\n\nDefault branch: main\n\nFork: no\n\nArchived: no\n\nREADME:\n<a name=\"readme-top\"></a>\n\n<p align=\"center\">\n<img src=\"https://qianwen-res.oss-accelerate-overseas.aliyuncs.com/assets/logo/qwen2.5_math.png\" width=\"400\"/>\n<p>\n\n<p align=\"center\">\n<img src=\"https://qianwen-res.oss-accelerate-overseas.aliyuncs.com/Qwen2.5/2024-08-qwen2.5-math-allsize.png\" width=\"800\"/>\n<p>\n\n<p align=\"center\">\n💜 <a href=\"https://chat.qwenlm.ai/\"><b>Qwen Chat</b></a>&nbsp&nbsp | &nbsp&nbsp🤗 <a href=\"https://huggingface.co/Qwen\">Hugging Face</a>&nbsp&nbsp | &nbsp&nbsp🤖 <a href=\"https://modelscope.cn/organization/qwen\">ModelScope</a>&nbsp&nbsp | &nbsp&nbsp<a href=\"https://www.kaggle.com/models/qwen-lm/qwen2-math\">Kaggle</a>&nbsp&nbsp | &nbsp&nbsp 📑 <a href=\"https://qwenlm.github.io/blog/qwen2.5-math/\">Blog</a> &nbsp&nbsp ｜ &nbsp&nbsp📖 <a href=\"https://qwen.readthedocs.io/\">Documentation</a>\n<br>\n<a href=\"https://github.com/QwenLM/Qwen/blob/main/assets/wechat.png\">WeChat (微信)</a>&nbsp&nbsp | &nbsp&nbsp🫨 <a href=\"https://discord.gg/CV4E9rpNSD\">Discord</a>&nbsp&nbsp\n</p>\n\nVisit our Hugging Face or ModelScope organization (click the links above). Search checkpoints with names starting with `Qwen2.5-Math-`, and you will find all you need! Enjoy!\n\n## Introduction\n\nA month ago, we released the first series of mathematical LLMs - [Qwen2-Math](https://qwenlm.github.io/blog/qwen2-math/) - of our Qwen family. Today, we have upgraded it and open-sourced **Qwen2.5-Math** series, including base models **Qwen2.5-Math-1.5B/7B/72B**, instruction-tuned models **Qwen2.5-Math-1.5B/7B/72B-Instruct**, and mathematical reward model **Qwen2.5-Math-RM-72B**. \n\nUnlike Qwen2-Math series which only supports using Chain-of-Thught (CoT) to solve English math problems, Qwen2.5-Math series is expanded to support using both CoT and Tool-integrated Reasoning (TIR) to solve math problems in both Chinese and English. The Qwen2.5-Math series models have achieved significant performance improvements compa"},{"ref":"P15","kind":"page","title":"QwenLM/Qwen3-VL repository metadata","date":"2026-06-11T03:59:04.592791+00:00","date_source":null,"source_url":"https://github.com/QwenLM/Qwen3-VL","signal_url":null,"signal_json_url":null,"text":"# QwenLM/Qwen3-VL\n\nDescription: Qwen3-VL is the multimodal large language model series developed by Qwen team, Alibaba Cloud.\n\nLanguage: Jupyter Notebook\n\nLicense: Apache-2.0\n\nStars: 19353\n\nForks: 1783\n\nOpen issues: 413\n\nCreated: 2024-08-29T08:30:38Z\n\nPushed: 2026-01-30T04:47:30Z\n\nDefault branch: main\n\nFork: no\n\nArchived: no\n\nREADME:\n# Qwen3-VL\n\n<p align=\"center\">\n<img src=\"https://qianwen-res.oss-accelerate.aliyuncs.com/Qwen3-VL/qwen3vllogo.png\" width=\"400\"/>\n<p>\n\n<p align=\"center\">\n💜 <a href=\"https://chat.qwenlm.ai/\"><b>Qwen Chat</b></a>&nbsp&nbsp | &nbsp&nbsp🤗 <a href=\"https://huggingface.co/collections/Qwen/qwen3-vl-68d2a7c1b8a8afce4ebd2dbe\">Hugging Face</a>&nbsp&nbsp | &nbsp&nbsp🤖 <a href=\"https://modelscope.cn/collections/Qwen3-VL-5c7a94c8cb144b\">ModelScope</a>&nbsp&nbsp | &nbsp&nbsp📑 <a href=\"https://qwen.ai/blog?id=99f0335c4ad9ff6153e517418d48535ab6d8afef&from=research.latest-advancements-list\">Blog</a>&nbsp&nbsp | &nbsp&nbsp📚 <a href=\"https://github.com/QwenLM/Qwen3-VL/tree/main/cookbooks\">Cookbooks</a>&nbsp&nbsp | &nbsp&nbsp📑 <a href=\"https://arxiv.org/pdf/2511.21631\">Paper</a>&nbsp&nbsp\n<br>\n🖥️ <a href=\"https://huggingface.co/spaces/Qwen/Qwen3-VL-Demo\">Demo</a>&nbsp&nbsp | &nbsp&nbsp💬 <a href=\"https://github.com/QwenLM/Qwen/blob/main/assets/wechat.png\">WeChat (微信)</a>&nbsp&nbsp | &nbsp&nbsp🫨 <a href=\"https://discord.gg/CV4E9rpNSD\">Discord</a>&nbsp&nbsp | &nbsp&nbsp📑 <a href=\"https://help.aliyun.com/zh/model-studio/developer-reference/qwen-vl-api\">API</a>&nbsp&nbsp | &nbsp&nbsp🖥️ <a href=\"https://gallery.pai-ml.com/#/preview/deepLearning/cv/qwen2.5-vl\">PAI-DSW</a>\n</p>\n\n## Introduction\nMeet Qwen3-VL — the most powerful vision-language model in the Qwen series to date.\n\nThis generation delivers comprehensive upgrades across the board: superior text understanding & generation, deeper visual perception & reasoning, extended context length, enhanced spatial and video dynamics comprehension, and stronger agent interaction capabilities.\n\nAvailable in Dense and MoE architectures that scale from edge to cloud, with Instruct and reasoning‑enhanced Thinking editions for flexible, on‑demand deployment.\n\n#### Key Enhancements:\n\n* **Visual Agent**: Opera"},{"ref":"P16","kind":"page","title":"QwenLM/Qwen-Cookbook repository metadata","date":"2026-06-11T03:59:04.589706+00:00","date_source":null,"source_url":"https://github.com/QwenLM/Qwen-Cookbook","signal_url":null,"signal_json_url":null,"text":"# QwenLM/Qwen-Cookbook\n\nDescription: Open-source examples and guides for building with the Qwen. Browse a collection of snippets, advanced techniques and walkthroughs.\n\nStars: 38\n\nForks: 13\n\nOpen issues: 4\n\nCreated: 2024-11-20T05:24:49Z\n\nPushed: 2024-11-20T05:24:49Z\n\nDefault branch: main\n\nFork: no\n\nArchived: no\n\nREADME:\n# Qwen-Cookbook\nOpen-source examples and guides for building with the Qwen. Browse a collection of snippets, advanced techniques and walkthroughs."},{"ref":"P17","kind":"page","title":"QwenLM/Self-Lengthen repository metadata","date":"2026-06-11T03:59:04.540043+00:00","date_source":null,"source_url":"https://github.com/QwenLM/Self-Lengthen","signal_url":null,"signal_json_url":null,"text":"# QwenLM/Self-Lengthen\n\nLanguage: Python\n\nLicense: Apache-2.0\n\nStars: 99\n\nForks: 12\n\nOpen issues: 1\n\nCreated: 2024-11-01T02:50:43Z\n\nPushed: 2024-11-06T07:44:13Z\n\nDefault branch: main\n\nFork: no\n\nArchived: no\n\nREADME:\n# Language Models Can Self-Lengthen to Generate Long Texts\n\n*Shanghaoran Quan, Tianyi Tang, Bowen Yu, An Yang, Dayiheng Liu, Bofei Gao, Jianhong Tu, Yichang Zhang, Jingren Zhou, Junyang Lin*\n\nQwen Team, Alibaba Inc.\n\n---\n\n## :sparkles: Overview\n\nThis repository contains core implementations of the **Self-Lengthen**, proposed by [Language Models Can Self-Lengthen to Generate Long Texts](https://arxiv.org/abs/2410.23933).\n\n**Self-Lengthen** is a novel and effective data-driven technique for extrapolating **long output**, designed to stimulate long-generation ability from scratch using only the LLM's intrinsic knowledge and skills. This is achieved by iteratively self-lengthening the output and inductively self-aligning to generate increasingly longer texts. By applying **Self-Lengthen**, we successfully increased the maximum output length of Qwen from 1,000 words to 8,000 words.\n\n![image](https://qianwen-res.oss-accelerate.aliyuncs.com/assets/self-lengthen/self-lengthen_approach.png)\n\n- **Low resource**: Self-Lengthen does not require high-quality human-written text; only a set of seed user long output instructions is needed.\n\n- **Intrinsic ability**: Self-Lengthen utilizes only the seed LLM's intrinsic knowledge and skills, without any form of distillation from stronger LLMs.\n\n- **Free form**: Self-Lengthen can generate suitable responses to a wide range of long output instructions and is not confined to strictly structured formats.\n\n---\n\n## :rocket: Data Synthesis of Self-Lengthen\n\n### :wrench: Getting Started\n\n1. Clone this repository.\n1. We have made several crucial changes in `FastChat` project to support vLLM LoRA requests and extra decoding parameters like `repetition_penalty` and `top_k`. Please clone [this repository](https://github.com/quanshr/FastChat/tree/self-lengthen) and run `pip install -e \".[model_worker,webui]\"` to install.\n1. Run `pip install -r requirements.txt` to install other required packages.\n1. The repository contains code for"},{"ref":"P18","kind":"page","title":"QwenLM/ProcessBench repository metadata","date":"2026-06-11T03:59:04.404306+00:00","date_source":null,"source_url":"https://github.com/QwenLM/ProcessBench","signal_url":null,"signal_json_url":null,"text":"# QwenLM/ProcessBench\n\nDescription: Official repository for ACL 2025 paper \"ProcessBench: Identifying Process Errors in Mathematical Reasoning\"\n\nLanguage: Python\n\nStars: 191\n\nForks: 18\n\nOpen issues: 7\n\nCreated: 2024-12-09T06:21:41Z\n\nPushed: 2025-05-20T06:43:45Z\n\nDefault branch: main\n\nFork: no\n\nArchived: no\n\nREADME:\n# ProcessBench\n\n📄 [**[paper]**](https://huggingface.co/papers/2412.06559) 🤗 [**[data]**](https://huggingface.co/datasets/Qwen/ProcessBench)\n\nThis is the official repository for **ACL 2025** paper \"[ProcessBench: Identifying Process Errors in Mathematical Reasoning](https://huggingface.co/papers/2412.06559)\"\n\nIf you find this work relevant or helpful to your work, please kindly cite us:\n\n```latex\n@inproceedings{\nprocessbench,\ntitle={ProcessBench: Identifying Process Errors in Mathematical Reasoning}, \nauthor={\nChujie Zheng and Zhenru Zhang and Beichen Zhang and Runji Lin and Keming Lu and\nBowen Yu and Dayiheng Liu and Jingren Zhou and Junyang Lin\n},\nbooktitle={The 63rd Annual Meeting of the Association for Computational Linguistics\n},\nyear={2025}\n}\n```\n\n## Data Usage\n\nYou can use the following code to preview the ProcessBench data:\n\n```python\nimport json\nfrom datasets import load_dataset\n\ndataset = load_dataset('Qwen/ProcessBench', split='gsm8k')\nprint(json.dumps(dataset[0], indent=2))\n\n# Expected output:\n\"\"\"\n{\n\"id\": \"gsm8k-0\",\n\"generator\": \"Qwen2-7B-Instruct\",\n\"problem\": \"Sue lives in a fun neighborhood...\",\n\"steps\": [\n\"To find out how many more pink plastic flamingos were out than...\",\n...\n],\n\"final_answer_correct\": false,\n\"label\": 1\n}\n\"\"\"\n```\n\n## Evaluation\n\nYou can refer to the [code](./code) folder for the evaluation code and the prompt templates we use in this work"},{"ref":"P19","kind":"page","title":"QwenLM/CodeElo repository metadata","date":"2026-06-11T03:59:04.139775+00:00","date_source":null,"source_url":"https://github.com/QwenLM/CodeElo","signal_url":null,"signal_json_url":null,"text":"# QwenLM/CodeElo\n\nDescription: CodeElo: Benchmarking Competition-level Code Generation of LLMs with Human-comparable Elo Ratings\n\nLanguage: Python\n\nStars: 75\n\nForks: 9\n\nOpen issues: 7\n\nCreated: 2025-02-03T19:52:01Z\n\nPushed: 2025-02-03T20:27:19Z\n\nDefault branch: main\n\nFork: no\n\nArchived: no\n\nREADME:\n# CodeElo\n\n<div align=\"center\" style=\"line-height: 1;\">\n<a href=\"https://arxiv.org/abs/2501.01257\" target=\"_blank\" style=\"margin: 2px;\">\n<img alt=\"\" src=\"https://img.shields.io/badge/Paper-gray?logo=arxiv\" style=\"display: inline-block; vertical-align: middle;\"/>\n</a>\n<a href=\"https://huggingface.co/datasets/Qwen/CodeElo\" target=\"_blank\" style=\"margin: 2px;\">\n<img alt=\"\" src=\"https://img.shields.io/badge/🤗%20%20Dataset-gray\" style=\"display: inline-block; vertical-align: middle;\"/>\n</a>\n<a href=\"https://codeelo-bench.github.io/\" target=\"_blank\" style=\"margin: 2px;\">\n<img alt=\"\" src=\"https://img.shields.io/badge/🏆%20%20Leaderboard-gray\" style=\"display: inline-block; vertical-align: middle;\"/>\n</a>\n</div>\n\nThis repository is used to evaluate a model's competition-level code generation abilities on [CodeForces](https://codeforces.com/) with human-comparable Elo ratings and percentiles among humans, using the method proposed in [CodeElo: Benchmarking Competition-level Code Generation of LLMs with Human-comparable Elo Ratings](https://arxiv.org/abs/2501.01257).\n\n> [!IMPORTANT]\n> We have open-sourced all of the Elo calculation logic and ranking methods. The `BASE_URL` provided here points to our automated submission system. In order to prevent meaningless mass submissions and to comply with CodeForces policies, we require verified submissions. Due to ethical considerations, you need to agree to the AGREEMENT to obtain a `TOKEN` and `BASE_URL` to use the repository. Please fill in the blanks and email the letter to `binyuan.hby@alibaba-inc.com`, and we will review it and respond as soon as possible. If you prefer not to use our automated system, you are free to implement your own submission mechanism by configuring the interfaces in `api.py`.\n\n### Quick Start\n\n1. Send a request via email to obtain your access `TOKEN`, then set `TOKEN` variable in environment.\n\n```bash\nexport"},{"ref":"P20","kind":"page","title":"QwenLM/QwQ repository metadata","date":"2026-06-11T03:59:03.898413+00:00","date_source":null,"source_url":"https://github.com/QwenLM/QwQ","signal_url":null,"signal_json_url":null,"text":"# QwenLM/QwQ\n\nDescription: QwQ is the reasoning model series developed by Qwen team, Alibaba Cloud. \n\nLanguage: Python\n\nLicense: Apache-2.0\n\nStars: 518\n\nForks: 26\n\nOpen issues: 16\n\nCreated: 2025-03-11T06:07:08Z\n\nPushed: 2025-03-27T15:48:52Z\n\nDefault branch: main\n\nFork: no\n\nArchived: no\n\nREADME:\n# QwQ\n\n<p align=\"center\">\n<img src=\"https://qianwen-res.oss-cn-beijing.aliyuncs.com/QwQ/QwQ_logo.png\" width=\"400\"/>\n<p>\n\n<p align=\"center\">\n💜 <a href=\"https://chat.qwen.ai/\"><b>Qwen Chat</b></a>&nbsp&nbsp | &nbsp&nbsp🤗 <a href=\"https://huggingface.co/Qwen/QwQ-32B\">Hugging Face</a>&nbsp&nbsp | &nbsp&nbsp🤖 <a href=\"https://modelscope.cn/organization/qwen\">ModelScope</a>&nbsp&nbsp | &nbsp&nbsp📑 <a href=\"https://qwenlm.github.io/blog/qwq-32b/\">Blog</a>&nbsp&nbsp<br>\n🖥️ <a href=\"https://huggingface.co/spaces/Qwen/QwQ-32B-Demo\">Demo</a>&nbsp&nbsp | &nbsp&nbsp💬 <a href=\"https://github.com/QwenLM/Qwen/blob/main/assets/wechat.png\">WeChat (微信)</a>&nbsp&nbsp | &nbsp&nbsp🫨 <a href=\"https://discord.gg/CV4E9rpNSD\">Discord</a>&nbsp&nbsp | &nbsp&nbsp📑 <a href=\"https://www.alibabacloud.com/help/en/model-studio/developer-reference/what-is-qwen-llm\">API</a>&nbsp&nbsp\n</p>\n\n## Introduction\n\nQwQ is the reasoning-specialized model within the Qwen series. Unlike traditional instruction-tuned models, QwQ leverages advanced reasoning and critical thinking abilities to achieve superior performance on downstream tasks, especially those involving complex problem-solving. Our latest release, QwQ-32B, is a mid-sized model that competes effectively with top-tier reasoning models like DeepSeek-R1 and o1-mini, delivering robust and competitive results.\n\n**Note:** Please review the [Usage Guidelines](#usage-guidelines) before deploying QwQ models, especially if you encounter **endless repetitions or significant performance issues**.\n\n## Performance\n\n<img src=\"https://qianwen-res.oss-accelerate-overseas.aliyuncs.com/qwq-32b-final.jpg\"/>\n\nTo reproduce the results, please refer to [our evaluation code](./eval).\n\n## Quickstart with HuggingFace's transformers\n\nQwQ is based on Qwen2.5, which has been in the latest Huggingface `transformers`. We advise you to use the latest version of `transformers`.\n\nWi"},{"ref":"P21","kind":"page","title":"QwenLM/Qwen2.5-Omni repository metadata","date":"2026-06-11T03:59:03.828125+00:00","date_source":null,"source_url":"https://github.com/QwenLM/Qwen2.5-Omni","signal_url":null,"signal_json_url":null,"text":"# QwenLM/Qwen2.5-Omni\n\nDescription: Qwen2.5-Omni is an end-to-end multimodal model by Qwen team at Alibaba Cloud, capable of understanding text, audio, vision, video, and performing real-time speech generation.\n\nLanguage: Jupyter Notebook\n\nLicense: Apache-2.0\n\nStars: 4021\n\nForks: 324\n\nOpen issues: 220\n\nCreated: 2025-03-22T01:43:13Z\n\nPushed: 2025-06-12T11:03:07Z\n\nDefault branch: main\n\nFork: no\n\nArchived: no\n\nREADME:\n# Qwen2.5-Omni\n<p align=\"left\">\n<a href=\"README_CN.md\">中文</a> &nbsp｜ &nbsp English&nbsp&nbsp\n</p>\n<br>\n\n<p align=\"center\">\n<img src=\"https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen2.5-Omni/Omni_logo.png\" width=\"400\"/>\n<p>\n\n<p align=\"center\">\n💜 <a href=\"https://chat.qwenlm.ai/\"><b>Qwen Chat</b></a>&nbsp&nbsp | &nbsp&nbsp🤗 <a href=\"https://huggingface.co/collections/Qwen/qwen25-omni-67de1e5f0f9464dc6314b36e\">Hugging Face</a>&nbsp&nbsp | &nbsp&nbsp🤖 <a href=\"https://modelscope.cn/collections/Qwen25-Omni-a2505ce0d5514e\">ModelScope</a>&nbsp&nbsp | &nbsp&nbsp📑 <a href=\"https://qwenlm.github.io/blog/qwen2.5-omni/\">Blog</a>&nbsp&nbsp | &nbsp&nbsp📚 <a href=\"https://github.com/QwenLM/Qwen2.5-Omni/tree/main/cookbooks\">Cookbooks</a>&nbsp&nbsp | &nbsp&nbsp📑 <a href=\"https://arxiv.org/abs/2503.20215\">Paper</a>&nbsp&nbsp\n<br>\n🖥️ <a href=\"https://huggingface.co/spaces/Qwen/Qwen2.5-Omni-7B-Demo \">Demo</a>&nbsp&nbsp | &nbsp&nbsp💬 <a href=\"https://github.com/QwenLM/Qwen/blob/main/assets/wechat.png\">WeChat (微信)</a>&nbsp&nbsp | &nbsp&nbsp🫨 <a href=\"https://discord.gg/CV4E9rpNSD\">Discord</a>&nbsp&nbsp | &nbsp&nbsp📑 <a href=\"https://help.aliyun.com/zh/model-studio/user-guide/qwen-omni\">API</a>\n<!-- &nbsp&nbsp | &nbsp&nbsp🖥️ <a href=\"https://gallery.pai-ml.com/#/preview/deepLearning/cv/qwen2.5-vl\">PAI-DSW</a> -->\n</p>\n\nWe 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 natural speech synthesis. Let's click the video below for more information 😃\n\n<a href=\"https://youtu.be/yKcANdkRuNI\" target=\"_blank\">\n<img src"},{"ref":"P22","kind":"page","title":"QwenLM/PolyMath repository metadata","date":"2026-06-11T03:59:03.808295+00:00","date_source":null,"source_url":"https://github.com/QwenLM/PolyMath","signal_url":null,"signal_json_url":null,"text":"# QwenLM/PolyMath\n\nDescription: [NeurIPS 2025 D&B Track] Evaluation Code Repo for Paper \"PolyMath: Evaluating Mathematical Reasoning in Multilingual Contexts\"\n\nLanguage: Python\n\nStars: 44\n\nForks: 9\n\nOpen issues: 4\n\nCreated: 2025-04-25T02:58:32Z\n\nPushed: 2025-05-22T05:00:13Z\n\nDefault branch: main\n\nFork: no\n\nArchived: no\n\nREADME:\n<div align=\"center\">\n\n<h2>\n<img src=\"ASSETS/pyramid.png\" alt=\"logo\" width=\"25\"/>\nPolyMath: Evaluating Mathematical Reasoning in Multilingual Contexts\n</h2>\n\n</div>\n\n<p align=\"center\">\n<a href=\"https://arxiv.org/abs/2504.18428\">\n<img src=\"https://img.shields.io/badge/arXiv-2504.18428-b31b1b.svg?logo=arxiv\" alt=\"arXiv Badge\"/>\n</a>\n<a href=\"https://huggingface.co/datasets/Qwen/PolyMath\">\n<img src=\"https://img.shields.io/badge/HuggingFace-Dataset-yellow?logo=huggingface\" alt=\"Hugging Face Badge\"/>\n</a>\n<a href=\"https://qwen-polymath.github.io/\">\n<img src=\"https://img.shields.io/badge/Leaderboard-Website-brightgreen?logo=trophy\" alt=\"Leaderboard Badge\"/>\n</a>\n<a href=\"./LICENSE\">\n<img src=\"https://img.shields.io/badge/License-Apache 2.0-blue.svg?logo=open-source-initiative\" alt=\"Apache-2.0 License Badge\"/>\n</a>\n</p>\n\nThis is the official repository for the paper **\"PolyMath: Evaluating Mathematical Reasoning in Multilingual Contexts\"**.\n\n## 📖 Introduction\n\n**PolyMath** is a multilingual mathematical reasoning benchmark covering 18 languages and 4 easy-to-hard difficulty levels, with 9,000 high-quality problem samples. Our benchmark ensures difficulty comprehensiveness, language diversity, and high-quality translation, making it a highly discriminative multilingual mathematical benchmark in the era of reasoning LLMs.\n\n## ✨ Features\n\n- 📈 **Broad Difficulty Range:** PolyMath defines and partitions **mathematical difficulty across four levels** using two core dimensions: *Thought Depth* and *Knowledge Breadth*, ranging from K-12 to Olympiad and advanced frontier mathematics, with **125 problems per language at each level**.\n\n<div align=\"center\">\n<img src=\"ASSETS/level.png\" alt=\"logo\" width=\"85%\"/>\n</div>\n\n- 🌍 **Language Diversity:** Each problem in PolyMath is available in **18 parallel language versions**, encompassing over 75% of the world’s"},{"ref":"P23","kind":"page","title":"QwenLM/ParScale repository metadata","date":"2026-06-11T03:59:03.604232+00:00","date_source":null,"source_url":"https://github.com/QwenLM/ParScale","signal_url":null,"signal_json_url":null,"text":"# QwenLM/ParScale\n\nDescription: Parallel Scaling Law for Language Model — Beyond Parameter and Inference Time Scaling\n\nLanguage: Python\n\nStars: 478\n\nForks: 26\n\nOpen issues: 7\n\nCreated: 2025-05-15T09:49:05Z\n\nPushed: 2025-05-17T18:06:25Z\n\nDefault branch: main\n\nFork: no\n\nArchived: no\n\nREADME:\n<div align=\"center\">\n\n# Parallel Scaling Law for Language Model\n\n_Yet Another Scaling Law beyond Parameters and Inference Time Scaling_\n\n[![Paper](https://img.shields.io/badge/arXiv-2505.10475-red)](https://arxiv.org/abs/2505.10475)\n[![huggingface](https://img.shields.io/badge/%F0%9F%A4%97%20Hugging%20Face-Models-FFD21E)](https://huggingface.co/ParScale)\n\n<div align=\"center\">\n<img src=\"figures/logo.jpg\" style=\"width: 10%;\" />\n</div>\n\n<p align=\"center\">\n💡&nbsp;<a href=\"#-key-findings\">Key Findings</a>\n| 📈&nbsp;<a href=\"#-scaling-law\">Scaling Law</a>\n| ⚡&nbsp;<a href=\"#-cost-analysis\">Cost Analysis</a>\n| 🔥&nbsp;<a href=\"#-models\">Models</a>\n| 📚&nbsp;<a href=\"#-citation\">Citation</a>\n</p>\n</div>\n\n## 🌟 About\n\n- Most believe that scaling language models requires a heavy cost in either **space** (parameter scaling) or **time** (inference-time scaling). \n- We introduce the *third* scaling paradigm for scaling LLMs: leverages **parallel computation** during both training and inference time (Parallel Scaling, or *ParScale*).\n- We apply $P$ diverse and learnable transformations to the input, execute forward passes of the model in parallel, and dynamically aggregate the $P$ outputs. \n<div align=\"center\">\n<img src=\"figures/teaser.png\" style=\"width: 80%;\" />\n</div>\n\n---\n\n## 💡 Key Findings\n<div align=\"center\">\n<img src=\"figures/scaling_comparison.png\" style=\"width: 80%;\" />\n</div>\n\nHere are the core insights and benefits distilled from our theoretical analysis and empirical evaluations:\n\n📈 **Logarithmic Scaling Law**: We theoretically and empirically establish that **scaling with $P$ parallel streams is comparable to scaling the number of parameters by** $O(\\log P)$. This suggests that parallel computation can serve as an efficient substitute for parameter growth, especially for larger models.\n\n✅ **Universal Applicability**: Unlike inference-time scaling which requires specialized da"},{"ref":"P24","kind":"page","title":"QwenLM/WorldPM repository metadata","date":"2026-06-11T03:59:03.311538+00:00","date_source":null,"source_url":"https://github.com/QwenLM/WorldPM","signal_url":null,"signal_json_url":null,"text":"# QwenLM/WorldPM\n\nStars: 94\n\nForks: 8\n\nOpen issues: 4\n\nCreated: 2025-05-16T06:59:43Z\n\nPushed: 2025-05-16T14:02:30Z\n\nDefault branch: main\n\nFork: no\n\nArchived: no\n\nREADME:\n# WorldPM 🌍\n\n[![License](https://img.shields.io/badge/License-Apache%202.0-blue.svg)](https://opensource.org/licenses/Apache-2.0)\n[![arXiv](https://img.shields.io/badge/arXiv-2505.10527-b31b1b.svg)](https://arxiv.org/abs/2505.10527)\n[![GitHub](https://img.shields.io/badge/GitHub-WorldPM-4b32c3?logo=github)](https://github.com/QwenLM/WorldPM)\n[![Hugging Face](https://img.shields.io/badge/🤗%20Hugging%20Face-yellow)](https://huggingface.co/Qwen/WorldPM-72B)\n[![ModelScope](https://img.shields.io/badge/🤖%20ModelScope-purple)](https://modelscope.cn/models/Qwen/WorldPM-72B)\n\n[English](./README.md) | [中文](./README_CN.md)\n\n## 📚 Introduction\n📄 [WorldPM](https://arxiv.org/abs/2505.10527) (World Preference Modeling) demonstrates that preference modeling follows similar **scaling laws** as language modeling. Through large-scale training on 15M preference data, we reveal that preference models can learn unified preference representations.\n\n![main-loss](http://qianwen-res.oss-accelerate-overseas.aliyuncs.com/WorldPM/main-loss.png)\n\n<details>\n<summary>🔍 Key Findings</summary>\n\n* **In adversarial evaluation, test losses demonstrate a power law decrease**, indicating the model's enhanced ability to identify responses with intentional errors and those that are well-written but irrelevant or incomplete.\n* **The objective metrics reveal an emergent phenomenon**, where larger models demonstrate a power law decrease in test losses across more benchmarks. WorldPM represents a challenging task that requires larger models to elicit preferences for objective knowledge, pointing to its substantial potential for further advancement.\n* **Subjective evaluations show no apparent scaling trends.** We analyze potential reasons from the perspective of style preferences. While WorldPM becomes more style-neutral as it scales up, some subjective evaluations exhibit style preferences, resulting in lower evaluation performance.\n\n</details>\n\n<details>\n<summary>🤔 Deep Dive: Understanding Scaling in Preference Modeling</summary>\n\n"},{"ref":"P25","kind":"page","title":"QwenLM/Qwen3-Embedding repository metadata","date":"2026-06-11T03:59:03.174354+00:00","date_source":null,"source_url":"https://github.com/QwenLM/Qwen3-Embedding","signal_url":null,"signal_json_url":null,"text":"# QwenLM/Qwen3-Embedding\n\nLanguage: Python\n\nStars: 1954\n\nForks: 123\n\nOpen issues: 133\n\nCreated: 2025-06-05T08:07:26Z\n\nPushed: 2025-09-30T06:10:27Z\n\nDefault branch: main\n\nFork: no\n\nArchived: no\n\nREADME:\n<p align=\"center\">\n<img src=\"https://qianwen-res.oss-accelerate.aliyuncs.com/logo_qwen_embedding.png\" width=\"400\"/>\n<p>\n\n<p align=\"center\">\n&nbsp&nbsp <a href=\"https://huggingface.co/collections/Qwen/qwen3-embedding-6841b2055b99c44d9a4c371f\">Huggingface</a>&nbsp&nbsp | &nbsp&nbsp <a href=\"https://modelscope.cn/collections/Qwen3-Embedding-3edc3762d50f48\">ModelScope</a>&nbsp&nbsp | &nbsp&nbsp <a href=\"https://qwenlm.github.io/blog/qwen3-embedding/\">Blog</a> &nbsp&nbsp | &nbsp&nbsp <a href=\"https://arxiv.org/abs/2506.05176\">Arxiv</a> &nbsp&nbsp | &nbsp&nbsp <a href=\"https://bailian.console.aliyun.com/?tab=model#/model-market/detail/text-embedding-v4\">API</a> ｜ &nbsp&nbsp <a href=\"https://discord.gg/yPEP2vHTu4\">Discord</a> \n</p>\n\n# Qwen3 Embedding\n\n## Highlights\n\nThe Qwen3 Embedding model series is the latest proprietary model of the Qwen family, specifically designed for text embedding and ranking tasks. Building upon the dense foundational models of the Qwen3 series, it provides a comprehensive range of text embeddings and reranking models in various sizes (0.6B, 4B, and 8B). This series inherits the exceptional multilingual capabilities, long-text understanding, and reasoning skills of its foundational model. The Qwen3 Embedding series represents significant advancements in multiple text embedding and ranking tasks, including text retrieval, code retrieval, text classification, text clustering, and bitext mining.\n\n**Exceptional Versatility**: The embedding model has achieved state-of-the-art performance across a wide range of downstream application evaluations. The 8B size embedding model ranks **No.1** in the MTEB multilingual leaderboard (as of June 5, 2025, score **70.58**), while the reranking model excels in various text retrieval scenarios.\n\n**Comprehensive Flexibility**: The Qwen3 Embedding series offers a full spectrum of sizes (from 0.6B to 8B) for both embedding and reranking models, catering to diverse use cases that prioritize efficiency and effectivene"},{"ref":"P26","kind":"page","title":"QwenLM/qwen-code repository metadata","date":"2026-06-11T03:59:03.134425+00:00","date_source":null,"source_url":"https://github.com/QwenLM/qwen-code","signal_url":null,"signal_json_url":null,"text":"# QwenLM/qwen-code\n\nDescription: An open-source AI coding agent that lives in your terminal.\n\nLanguage: TypeScript\n\nLicense: Apache-2.0\n\nStars: 25088\n\nForks: 2494\n\nOpen issues: 803\n\nCreated: 2025-06-26T01:37:46Z\n\nPushed: 2026-06-11T03:51:50Z\n\nDefault branch: main\n\nFork: no\n\nArchived: no\n\nREADME:\n<div align=\"center\">\n\n[![npm version](https://img.shields.io/npm/v/@qwen-code/qwen-code.svg)](https://www.npmjs.com/package/@qwen-code/qwen-code)\n[![License](https://img.shields.io/github/license/QwenLM/qwen-code.svg)](./LICENSE)\n[![Node.js Version](https://img.shields.io/badge/node-%3E%3D22.0.0-brightgreen.svg)](https://nodejs.org/)\n[![Downloads](https://img.shields.io/npm/dm/@qwen-code/qwen-code.svg)](https://www.npmjs.com/package/@qwen-code/qwen-code)\n\n<a href=\"https://trendshift.io/repositories/15287\" target=\"_blank\"><img src=\"https://trendshift.io/api/badge/repositories/15287\" alt=\"QwenLM%2Fqwen-code | Trendshift\" style=\"width: 250px; height: 55px;\" width=\"250\" height=\"55\"/></a>\n\n**An open-source AI agent that lives in your terminal.**\n\n<a href=\"https://qwenlm.github.io/qwen-code-docs/zh/users/overview\">中文</a> |\n<a href=\"https://qwenlm.github.io/qwen-code-docs/de/users/overview\">Deutsch</a> |\n<a href=\"https://qwenlm.github.io/qwen-code-docs/fr/users/overview\">français</a> |\n<a href=\"https://qwenlm.github.io/qwen-code-docs/ja/users/overview\">日本語</a> |\n<a href=\"https://qwenlm.github.io/qwen-code-docs/ru/users/overview\">Русский</a> |\n<a href=\"https://qwenlm.github.io/qwen-code-docs/pt-BR/users/overview\">Português (Brasil)</a>\n\n</div>\n\n## 🎉 News\n\n- **2026-04-15**: Qwen OAuth free tier has been discontinued. To continue using Qwen Code, switch to [Alibaba Cloud Coding Plan](https://modelstudio.console.alibabacloud.com/?tab=coding-plan#/efm/coding-plan-index), [OpenRouter](https://openrouter.ai), [Fireworks AI](https://app.fireworks.ai), or bring your own API key. Run `qwen auth` to configure.\n\n- **2026-04-13**: Qwen OAuth free tier policy update: daily quota adjusted to 100 requests/day (from 1,000).\n\n- **2026-04-02**: Qwen3.6-Plus is now live! Get an API key from [Alibaba Cloud ModelStudio](https://modelstudio.console.alibabacloud.com/ap-southeast-1?tab=doc#/doc/?type="},{"ref":"P27","kind":"page","title":"QwenLM/qwen-code-action repository metadata","date":"2026-06-11T03:59:03.117118+00:00","date_source":null,"source_url":"https://github.com/QwenLM/qwen-code-action","signal_url":null,"signal_json_url":null,"text":"# QwenLM/qwen-code-action\n\nDescription: A GitHub Action that integrates Qwen Code into your development workflow.\n\nLanguage: Shell\n\nLicense: Apache-2.0\n\nStars: 29\n\nForks: 8\n\nOpen issues: 3\n\nCreated: 2025-08-03T07:51:20Z\n\nPushed: 2026-01-05T05:53:00Z\n\nDefault branch: main\n\nFork: no\n\nArchived: no\n\nREADME:\n# qwen-code-action\n\n## Overview\n\n`qwen-code-action` is a GitHub Action that integrates [Qwen Code] into your development workflow. It acts both as an autonomous agent for critical routine coding tasks, and an on-demand collaborator you can quickly delegate work to.\n\nUse it to perform GitHub pull request reviews, triage issues, perform code analysis and modification, and more using [Qwen Code] conversationally (e.g., `@qwencoder fix this issue`) directly inside your GitHub repositories.\n\n- [qwen-code-action](#qwen-code-action)\n- [Overview](#overview)\n- [Features](#features)\n- [Quick Start](#quick-start)\n- [1. Get a Qwen API Key](#1-get-a-qwen-api-key)\n- [2. Add it as a GitHub Secret](#2-add-it-as-a-github-secret)\n- [3. Update your .gitignore](#3-update-your-gitignore)\n- [4. Choose a Workflow](#4-choose-a-workflow)\n- [5. Try it out](#5-try-it-out)\n- [Workflows](#workflows)\n- [Qwen Code Dispatch](#qwen-code-dispatch)\n- [Issue Triage](#issue-triage)\n- [Pull Request Review](#pull-request-review)\n- [Qwen Code Assistant](#qwen-code-assistant)\n- [Configuration](#configuration)\n- [Inputs](#inputs)\n- [Outputs](#outputs)\n- [Repository Variables](#repository-variables)\n- [Secrets](#secrets)\n- [Authentication](#authentication)\n- [GitHub Authentication](#github-authentication)\n- [Extensions](#extensions)\n- [Best Practices](#best-practices)\n- [Customization](#customization)\n- [Contributing](#contributing)\n\n## Features\n\n- **Automation**: Trigger workflows based on events (e.g. issue opening) or schedules (e.g. nightly).\n- **On-demand Collaboration**: Trigger workflows in issue and pull request\ncomments by mentioning the [Qwen Code] (e.g., `@qwencoder /review`).\n- **Extensible with Tools**: Leverage [Qwen Code] models' tool-calling capabilities to\ninteract with other CLIs like the [GitHub CLI] (`gh`).\n- **Customizable**: Use a `QWEN.md` file in your repository to provide\nproject-"},{"ref":"P28","kind":"page","title":"QwenLM/Qwen-Image repository metadata","date":"2026-06-11T03:59:02.882492+00:00","date_source":null,"source_url":"https://github.com/QwenLM/Qwen-Image","signal_url":null,"signal_json_url":null,"text":"# QwenLM/Qwen-Image\n\nDescription: Qwen-Image is a powerful image generation foundation model capable of complex text rendering and precise image editing.\n\nLanguage: Python\n\nLicense: Apache-2.0\n\nStars: 7987\n\nForks: 502\n\nOpen issues: 232\n\nCreated: 2025-08-03T11:03:25Z\n\nPushed: 2026-02-10T07:37:37Z\n\nDefault branch: main\n\nFork: no\n\nArchived: no\n\nREADME:\n<p align=\"center\">\n<img src=\"https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-Image/qwen_image_logo.png\" width=\"400\"/>\n<p> \n<p align=\"center\">&nbsp&nbsp💜 <a href=\"https://chat.qwen.ai/\">Qwen Chat</a>&nbsp&nbsp |\n&nbsp&nbsp🤗 <a href=\"https://huggingface.co/Qwen/Qwen-Image\">HuggingFace(T2I)</a>&nbsp&nbsp |\n&nbsp&nbsp🤗 <a href=\"https://huggingface.co/Qwen/Qwen-Image-Edit-2511\">HuggingFace(Edit)</a>&nbsp&nbsp | &nbsp&nbsp🤖 <a href=\"https://modelscope.cn/models/Qwen/Qwen-Image\">ModelScope-T2I</a>&nbsp&nbsp | &nbsp&nbsp🤖 <a href=\"https://modelscope.cn/models/Qwen/Qwen-Image-Edit-2511\">ModelScope-Edit</a>&nbsp&nbsp| &nbsp&nbsp 📑 <a href=\"https://arxiv.org/abs/2508.02324\">Tech Report</a> &nbsp&nbsp | &nbsp&nbsp 📑 <a href=\"https://qwenlm.github.io/blog/qwen-image/\">Blog(T2I)</a> &nbsp&nbsp | &nbsp&nbsp 📑 <a href=\"https://qwenlm.github.io/blog/qwen-image-edit-2511/\">Blog(Edit)</a> &nbsp&nbsp \n<br>\n🖥️ <a href=\"https://huggingface.co/spaces/Qwen/Qwen-Image\">T2I Demo</a>&nbsp&nbsp | 🖥️ <a href=\"https://huggingface.co/spaces/Qwen/Qwen-Image-Edit-2511\">Edit Demo</a>&nbsp&nbsp | &nbsp&nbsp💬 <a href=\"https://github.com/QwenLM/Qwen-Image/blob/main/assets/wechat.png\">WeChat (微信)</a>&nbsp&nbsp | &nbsp&nbsp🫨 <a href=\"https://discord.gg/CV4E9rpNSD\">Discord</a>&nbsp&nbsp\n</p>\n\n<p align=\"center\">\n<img src=\"https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-Image/merge3.jpg\" width=\"1024\"/>\n<p>\n\n## Introduction\nWe are thrilled to release **Qwen-Image**, a 20B MMDiT image foundation model that achieves significant advances in **complex text rendering** and **precise image editing**. Experiments show strong general capabilities in both image generation and editing, with exceptional performance in text rendering, especially for Chinese.\n\n![](https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-Image/bench.png#center)\n\n## News\n-"},{"ref":"E1","kind":"event","title":"QwenLM/Qwen3-Omni","date":"2025-09-21T09:46:10+00:00","date_source":"source","source_url":"https://github.com/QwenLM/Qwen3-Omni","signal_url":"https://onlylabs.fyi/signals/1a0a42da-845a-42b5-880d-dae921c841ff","signal_json_url":"https://onlylabs.fyi/signals/1a0a42da-845a-42b5-880d-dae921c841ff/signal.json","text":"repo_new · QwenLM/Qwen3-Omni · signal_desk=repos · occurred_at=2025-09-21T09:46:10+00:00 · url=https://github.com/QwenLM/Qwen3-Omni · stars=3823 · hn=571 points/142 comments · raw={\"repo\":\"QwenLM/Qwen3-Omni\",\"description\":\"Qwen3-omni is a natively end-to-end, omni-modal LLM developed by the Qwen team at Alibaba Cloud, capable of understanding text, audio, images, and video, as well as generating speech in real time.\",\"language\":\"Jupyter Notebook\"}"},{"ref":"E2","kind":"event","title":"Qwen/Qwen3.6-35B-A3B","date":"2026-04-15T05:59:19+00:00","date_source":"source","source_url":"https://huggingface.co/Qwen/Qwen3.6-35B-A3B","signal_url":"https://onlylabs.fyi/signals/c3639d1d-6e59-4eea-8c3d-826f5fb74b9d","signal_json_url":"https://onlylabs.fyi/signals/c3639d1d-6e59-4eea-8c3d-826f5fb74b9d/signal.json","text":"model_released · Qwen/Qwen3.6-35B-A3B · signal_desk=releases · occurred_at=2026-04-15T05:59:19+00:00 · url=https://huggingface.co/Qwen/Qwen3.6-35B-A3B · hf_downloads=5129777 · hf_likes=2069 · hf_params=35951822704 · pipeline=image-text-to-text · license=apache-2.0"},{"ref":"E3","kind":"event","title":"QwQ: Reflect Deeply on the Boundaries of the Unknown","date":"2024-11-28T00:00:00.000Z","date_source":"page.visible_date","source_url":"https://qwenlm.github.io/blog/qwq-32b-preview/","signal_url":"https://onlylabs.fyi/signals/c03ca337-7590-42a4-8e8d-6291f45c9247","signal_json_url":"https://onlylabs.fyi/signals/c03ca337-7590-42a4-8e8d-6291f45c9247/signal.json","text":"post_published · QwQ: Reflect Deeply on the Boundaries of the Unknown · signal_desk=talking · occurred_at=2024-11-28T00:00:00.000Z · url=https://qwenlm.github.io/blog/qwq-32b-preview/ · hn=438 points/421 comments · raw={\"excerpt\":\"GITHUB HUGGING FACE MODELSCOPE DEMO DISCORD\\nNote: This is the pronunciation of QwQ: /kwju:/ , similar to the word “quill”.\\nWhat 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 philosophical spirit: it knows that it knows nothing, and that’s precisely what drives its curiosity.\"}"},{"ref":"E4","kind":"event","title":"Qwen/Qwen3.5-9B","date":"2026-02-27T12:58:26+00:00","date_source":"source","source_url":"https://huggingface.co/Qwen/Qwen3.5-9B","signal_url":"https://onlylabs.fyi/signals/98203e45-863b-462f-a745-ebc81cbc4dea","signal_json_url":"https://onlylabs.fyi/signals/98203e45-863b-462f-a745-ebc81cbc4dea/signal.json","text":"model_released · Qwen/Qwen3.5-9B · signal_desk=releases · occurred_at=2026-02-27T12:58:26+00:00 · url=https://huggingface.co/Qwen/Qwen3.5-9B · hf_downloads=8700726 · hf_likes=1549 · hf_params=9653104368 · pipeline=image-text-to-text · license=apache-2.0 · raw={\"derived_reason\":\"first-party-finetune\"}"},{"ref":"E5","kind":"event","title":"Qwen/Qwen3.6-27B","date":"2026-04-21T07:50:43+00:00","date_source":"source","source_url":"https://huggingface.co/Qwen/Qwen3.6-27B","signal_url":"https://onlylabs.fyi/signals/c05562d5-982b-456a-9d80-5882e5cecb60","signal_json_url":"https://onlylabs.fyi/signals/c05562d5-982b-456a-9d80-5882e5cecb60/signal.json","text":"model_released · Qwen/Qwen3.6-27B · signal_desk=releases · occurred_at=2026-04-21T07:50:43+00:00 · url=https://huggingface.co/Qwen/Qwen3.6-27B · hf_downloads=5276956 · hf_likes=1669 · hf_params=27781427952 · pipeline=image-text-to-text · license=apache-2.0"},{"ref":"E6","kind":"event","title":"Qwen/Qwen3.5-35B-A3B","date":"2026-02-24T09:39:25+00:00","date_source":"source","source_url":"https://huggingface.co/Qwen/Qwen3.5-35B-A3B","signal_url":"https://onlylabs.fyi/signals/2e35b612-da94-49c0-a98e-40004c682d81","signal_json_url":"https://onlylabs.fyi/signals/2e35b612-da94-49c0-a98e-40004c682d81/signal.json","text":"model_released · Qwen/Qwen3.5-35B-A3B · signal_desk=releases · occurred_at=2026-02-24T09:39:25+00:00 · url=https://huggingface.co/Qwen/Qwen3.5-35B-A3B · hf_downloads=2379874 · hf_likes=1444 · hf_params=35951822704 · pipeline=image-text-to-text · license=apache-2.0 · raw={\"derived_reason\":\"first-party-finetune\"}"},{"ref":"E7","kind":"event","title":"Qwen/Qwen3.5-397B-A17B","date":"2026-02-16T04:55:12+00:00","date_source":"source","source_url":"https://huggingface.co/Qwen/Qwen3.5-397B-A17B","signal_url":"https://onlylabs.fyi/signals/96b73dc9-d96b-4f83-837d-350ed78a3c65","signal_json_url":"https://onlylabs.fyi/signals/96b73dc9-d96b-4f83-837d-350ed78a3c65/signal.json","text":"model_released · Qwen/Qwen3.5-397B-A17B · signal_desk=releases · occurred_at=2026-02-16T04:55:12+00:00 · url=https://huggingface.co/Qwen/Qwen3.5-397B-A17B · hf_downloads=921103 · hf_likes=1505 · hf_params=403397928944 · pipeline=image-text-to-text · license=apache-2.0"},{"ref":"E8","kind":"event","title":"Hello Qwen2","date":"2024-06-07T00:00:00.000Z","date_source":"page.visible_date","source_url":"https://qwenlm.github.io/blog/qwen2/","signal_url":"https://onlylabs.fyi/signals/18ad1968-66f5-49f9-a1fd-c22dc2cc274e","signal_json_url":"https://onlylabs.fyi/signals/18ad1968-66f5-49f9-a1fd-c22dc2cc274e/signal.json","text":"post_published · Hello Qwen2 · signal_desk=talking · occurred_at=2024-06-07T00:00:00.000Z · url=https://qwenlm.github.io/blog/qwen2/ · hn=261 points/130 comments · data_radar_lanes=Data demand, Evals and quality, Product and customer · data_radar_terms=data, eval, evaluation, benchmark, support · data_radar_reason=Qwen (Alibaba Cloud) has a writing signal matching data demand, evals and quality, product and customer. · raw={\"excerpt\":\"GITHUB HUGGING FACE MODELSCOPE DEMO DISCORD\\nIntroduction After months of efforts, we are pleased to announce the evolution from Qwen1.5 to Qwen2. This time, we bring to you:\\nPretrained 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 improved performance in coding and mathematics; Extended context length support up to 128K tokens with Qwen2-7B-Instruct and Qwen2-72B-Instruct.\"}"},{"ref":"E9","kind":"event","title":"Qwen/Qwen3.5-27B","date":"2026-02-24T09:41:56+00:00","date_source":"source","source_url":"https://huggingface.co/Qwen/Qwen3.5-27B","signal_url":"https://onlylabs.fyi/signals/b41fd634-db6c-445f-99ac-dc3f4ca466ca","signal_json_url":"https://onlylabs.fyi/signals/b41fd634-db6c-445f-99ac-dc3f4ca466ca/signal.json","text":"model_released · Qwen/Qwen3.5-27B · signal_desk=releases · occurred_at=2026-02-24T09:41:56+00:00 · url=https://huggingface.co/Qwen/Qwen3.5-27B · hf_downloads=2530993 · hf_likes=983 · hf_params=27781427952 · pipeline=image-text-to-text · license=apache-2.0"},{"ref":"E10","kind":"event","title":"Qwen/Qwen3.5-4B","date":"2026-02-27T14:45:03+00:00","date_source":"source","source_url":"https://huggingface.co/Qwen/Qwen3.5-4B","signal_url":"https://onlylabs.fyi/signals/20a35950-096a-4910-8481-20ac2ca5e2d8","signal_json_url":"https://onlylabs.fyi/signals/20a35950-096a-4910-8481-20ac2ca5e2d8/signal.json","text":"model_released · Qwen/Qwen3.5-4B · signal_desk=releases · occurred_at=2026-02-27T14:45:03+00:00 · url=https://huggingface.co/Qwen/Qwen3.5-4B · hf_downloads=8955908 · hf_likes=627 · hf_params=4659865088 · pipeline=image-text-to-text · license=apache-2.0 · raw={\"derived_reason\":\"first-party-finetune\"}"},{"ref":"E11","kind":"event","title":"Qwen2.5: A Party of Foundation Models!","date":"2024-09-19T00:00:00.000Z","date_source":"page.visible_date","source_url":"https://qwenlm.github.io/blog/qwen2.5/","signal_url":"https://onlylabs.fyi/signals/29bc5093-6b6b-443a-88a9-e9416b76cf10","signal_json_url":"https://onlylabs.fyi/signals/29bc5093-6b6b-443a-88a9-e9416b76cf10/signal.json","text":"post_published · Qwen2.5: A Party of Foundation Models! · signal_desk=talking · occurred_at=2024-09-19T00:00:00.000Z · url=https://qwenlm.github.io/blog/qwen2.5/ · hn=168 points/38 comments · raw={\"excerpt\":\"GITHUB HUGGING FACE MODELSCOPE DEMO DISCORD\\nIntroduction In the past three months since Qwen2’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 introduce the latest addition to the Qwen family: Qwen2.5. We are announcing what might be the largest opensource release in history!\"}"},{"ref":"E12","kind":"event","title":"Qwen/Qwen3.5-0.8B","date":"2026-02-28T23:57:01+00:00","date_source":"source","source_url":"https://huggingface.co/Qwen/Qwen3.5-0.8B","signal_url":"https://onlylabs.fyi/signals/c90a05f7-cf80-41e0-b8e9-adc788317064","signal_json_url":"https://onlylabs.fyi/signals/c90a05f7-cf80-41e0-b8e9-adc788317064/signal.json","text":"model_released · Qwen/Qwen3.5-0.8B · signal_desk=releases · occurred_at=2026-02-28T23:57:01+00:00 · url=https://huggingface.co/Qwen/Qwen3.5-0.8B · hf_downloads=2447518 · hf_likes=568 · hf_params=873438784 · pipeline=image-text-to-text · license=apache-2.0 · raw={\"derived_reason\":\"first-party-finetune\"}"},{"ref":"E13","kind":"event","title":"Introducing Qwen2-Math","date":"2024-08-08T00:00:00.000Z","date_source":"page.visible_date","source_url":"https://qwenlm.github.io/blog/qwen2-math/","signal_url":"https://onlylabs.fyi/signals/2271f7cb-6c6f-4b70-bebd-bef47729400b","signal_json_url":"https://onlylabs.fyi/signals/2271f7cb-6c6f-4b70-bebd-bef47729400b/signal.json","text":"post_published · Introducing Qwen2-Math · signal_desk=talking · occurred_at=2024-08-08T00:00:00.000Z · url=https://qwenlm.github.io/blog/qwen2-math/ · hn=128 points/38 comments · data_radar_lanes=Product and customer · data_radar_terms=support · data_radar_reason=Qwen (Alibaba Cloud) has a writing signal matching product and customer. · raw={\"excerpt\":\"GITHUB HUGGING FACE MODELSCOPE DISCORD\\n🚨 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 solve arithmetic and mathematical problems. Today, we are delighted to introduce a series of math-specific large language models of our Qwen2 series, Qwen2-Math and Qwen2-Math-Instruct-1.\"}"},{"ref":"E14","kind":"event","title":"Qwen/Qwen3.5-122B-A10B","date":"2026-02-24T09:43:37+00:00","date_source":"source","source_url":"https://huggingface.co/Qwen/Qwen3.5-122B-A10B","signal_url":"https://onlylabs.fyi/signals/cb6ddd97-04dc-4e34-a71a-1cec3c36227f","signal_json_url":"https://onlylabs.fyi/signals/cb6ddd97-04dc-4e34-a71a-1cec3c36227f/signal.json","text":"model_released · Qwen/Qwen3.5-122B-A10B · signal_desk=releases · occurred_at=2026-02-24T09:43:37+00:00 · url=https://huggingface.co/Qwen/Qwen3.5-122B-A10B · hf_downloads=750918 · hf_likes=568 · hf_params=125086497008 · pipeline=image-text-to-text · license=apache-2.0"},{"ref":"E15","kind":"event","title":"Extending the Context Length to 1M Tokens!","date":"2024-11-15T00:00:00.000Z","date_source":"page.visible_date","source_url":"https://qwenlm.github.io/blog/qwen2.5-turbo/","signal_url":"https://onlylabs.fyi/signals/97fc82a0-6ce4-4a20-b770-4f20bba8e47c","signal_json_url":"https://onlylabs.fyi/signals/97fc82a0-6ce4-4a20-b770-4f20bba8e47c/signal.json","text":"post_published · Extending the Context Length to 1M Tokens! · signal_desk=talking · occurred_at=2024-11-15T00:00:00.000Z · url=https://qwenlm.github.io/blog/qwen2.5-turbo/ · hn=116 points/107 comments · data_radar_lanes=Infrastructure, Product and customer · data_radar_terms=inference, support · data_radar_reason=Qwen (Alibaba Cloud) has a writing signal matching infrastructure, product and customer. · raw={\"excerpt\":\"API Documentation (Chinese) HuggingFace Demo ModelScope Demo\\nIntroduction After the release of Qwen2.5, we heard the community’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-Turbo version, which features:\\nLonger Context Support: We have extended the model’s context length from 128k to 1M, which is approximately 1 million English words or 1.\"}"},{"ref":"E16","kind":"event","title":"Qwen1.5-110B: The First 100B+ Model of the Qwen1.5 Series","date":"2024-04-25T05:33:00+00:00","date_source":"rss.item_date","source_url":"https://qwenlm.github.io/blog/qwen1.5-110b/","signal_url":"https://onlylabs.fyi/signals/165728cb-410a-4a97-843d-d4b04910dc8c","signal_json_url":"https://onlylabs.fyi/signals/165728cb-410a-4a97-843d-d4b04910dc8c/signal.json","text":"post_published · Qwen1.5-110B: The First 100B+ Model of the Qwen1.5 Series · signal_desk=talking · occurred_at=2024-04-25T05:33:00+00:00 · url=https://qwenlm.github.io/blog/qwen1.5-110b/ · hn=114 points/58 comments · data_radar_lanes=Evals and quality · data_radar_terms=eval, evaluation, benchmark · data_radar_reason=Qwen (Alibaba Cloud) has a writing signal matching evals and quality. · raw={\"excerpt\":\"GITHUB HUGGING FACE MODELSCOPE DEMO DISCORD\\nIntroduction 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, Qwen1.5-110B, which achieves comparable performance with Meta-Llama3-70B in the base model evaluation, and outstanding performance in the chat evaluation, including MT-Bench and AlpacaEval 2.\"}"},{"ref":"E17","kind":"event","title":"Qwen1.5-MoE: Matching 7B Model Performance with 1/3 Activated Parameters","date":"2024-03-28T03:31:44+00:00","date_source":"rss.item_date","source_url":"https://qwenlm.github.io/blog/qwen-moe/","signal_url":"https://onlylabs.fyi/signals/d079a56b-4d3e-4862-9e10-bade69e26fa4","signal_json_url":"https://onlylabs.fyi/signals/d079a56b-4d3e-4862-9e10-bade69e26fa4/signal.json","text":"post_published · Qwen1.5-MoE: Matching 7B Model Performance with 1/3 Activated Parameters · signal_desk=talking · occurred_at=2024-03-28T03:31:44+00:00 · url=https://qwenlm.github.io/blog/qwen-moe/ · hn=104 points/10 comments · raw={\"excerpt\":\"GITHUB HUGGING FACE MODELSCOPE DEMO DISCORD\\nIntroduction Since the surge in interest sparked by Mixtral, research on mixture-of-expert (MoE) models has gained significant momentum. Both researchers and practitioners are keenly interested in understanding how to effectively train such models and assessing their efficiency and effectiveness. Today, we introduce Qwen1.5-MoE-A2.7B, a small MoE model with only 2.7 billion activated parameters yet matching the performance of state-of-the-art 7B models like Mistral 7B and Qwen1.\"}"},{"ref":"E18","kind":"event","title":"Qwen/Qwen3.5-2B","date":"2026-02-28T23:56:16+00:00","date_source":"source","source_url":"https://huggingface.co/Qwen/Qwen3.5-2B","signal_url":"https://onlylabs.fyi/signals/e3d69d66-35fd-480c-8ea8-e055e65d63e3","signal_json_url":"https://onlylabs.fyi/signals/e3d69d66-35fd-480c-8ea8-e055e65d63e3/signal.json","text":"model_released · Qwen/Qwen3.5-2B · signal_desk=releases · occurred_at=2026-02-28T23:56:16+00:00 · url=https://huggingface.co/Qwen/Qwen3.5-2B · hf_downloads=1662918 · hf_likes=302 · hf_params=2274069824 · pipeline=image-text-to-text · license=apache-2.0 · raw={\"derived_reason\":\"first-party-finetune\"}"},{"ref":"E19","kind":"event","title":"Qwen1.5-32B: Fitting the Capstone of the Qwen1.5 Language Model Series","date":"2024-04-02T05:33:00+00:00","date_source":"rss.item_date","source_url":"https://qwenlm.github.io/blog/qwen1.5-32b/","signal_url":"https://onlylabs.fyi/signals/48270ccd-945e-48c6-9d00-5c7ea0c9210d","signal_json_url":"https://onlylabs.fyi/signals/48270ccd-945e-48c6-9d00-5c7ea0c9210d/signal.json","text":"post_published · Qwen1.5-32B: Fitting the Capstone of the Qwen1.5 Language Model Series · signal_desk=talking · occurred_at=2024-04-02T05:33:00+00:00 · url=https://qwenlm.github.io/blog/qwen1.5-32b/ · hn=36 points/6 comments · data_radar_lanes=Infrastructure · data_radar_terms=inference · data_radar_reason=Qwen (Alibaba Cloud) has a writing signal matching infrastructure. · raw={\"excerpt\":\"GITHUB HUGGING FACE MODELSCOPE DEMO DISCORD\\nIntroduction 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, slow inference speed, and substantial finetuning costs.\\nA growing consensus within the field now points to a model with approximately 30 billion parameters as the optimal “sweet spot” for achieving both strong performance and manageable resource requirements.\"}"},{"ref":"E20","kind":"event","title":"QwenLM/Qwen3","date":"2024-02-05T05:45:08+00:00","date_source":"source","source_url":"https://github.com/QwenLM/Qwen3","signal_url":"https://onlylabs.fyi/signals/478f836f-8a74-48fc-927b-b9ccf5e07c08","signal_json_url":"https://onlylabs.fyi/signals/478f836f-8a74-48fc-927b-b9ccf5e07c08/signal.json","text":"repo_new · QwenLM/Qwen3 · signal_desk=repos · occurred_at=2024-02-05T05:45:08+00:00 · url=https://github.com/QwenLM/Qwen3 · stars=27304 · hn=3 points/0 comments · raw={\"repo\":\"QwenLM/Qwen3\",\"description\":\"Qwen3 is the large language model series developed by Qwen team, Alibaba Cloud.\",\"language\":\"Python\"}"},{"ref":"E21","kind":"event","title":"Qwen/Qwen3.5-35B-A3B-Base","date":"2026-02-24T09:42:42+00:00","date_source":"source","source_url":"https://huggingface.co/Qwen/Qwen3.5-35B-A3B-Base","signal_url":"https://onlylabs.fyi/signals/5597f708-5b24-442c-8ee5-224528dc908b","signal_json_url":"https://onlylabs.fyi/signals/5597f708-5b24-442c-8ee5-224528dc908b/signal.json","text":"model_released · Qwen/Qwen3.5-35B-A3B-Base · signal_desk=releases · occurred_at=2026-02-24T09:42:42+00:00 · url=https://huggingface.co/Qwen/Qwen3.5-35B-A3B-Base · hf_downloads=108400 · hf_likes=132 · hf_params=35951822704 · pipeline=image-text-to-text · license=apache-2.0"},{"ref":"E22","kind":"event","title":"QwenLM/qwen-code","date":"2025-06-26T01:37:46+00:00","date_source":"source","source_url":"https://github.com/QwenLM/qwen-code","signal_url":"https://onlylabs.fyi/signals/448e8c94-5d3f-4998-914b-166b0eccfe3c","signal_json_url":"https://onlylabs.fyi/signals/448e8c94-5d3f-4998-914b-166b0eccfe3c/signal.json","text":"repo_new · QwenLM/qwen-code · signal_desk=repos · occurred_at=2025-06-26T01:37:46+00:00 · url=https://github.com/QwenLM/qwen-code · stars=25097 · raw={\"repo\":\"QwenLM/qwen-code\",\"description\":\"An open-source AI coding agent that lives in your terminal.\",\"language\":\"TypeScript\"}"},{"ref":"E23","kind":"event","title":"Qwen2.5-Coder Series: Powerful, Diverse, Practical.","date":"2024-11-12T00:00:00.000Z","date_source":"page.visible_date","source_url":"https://qwenlm.github.io/blog/qwen2.5-coder-family/","signal_url":"https://onlylabs.fyi/signals/1ac75a82-594b-4587-8717-144af9a43cf5","signal_json_url":"https://onlylabs.fyi/signals/1ac75a82-594b-4587-8717-144af9a43cf5/signal.json","text":"post_published · Qwen2.5-Coder Series: Powerful, Diverse, Practical. · signal_desk=talking · occurred_at=2024-11-12T00:00:00.000Z · url=https://qwenlm.github.io/blog/qwen2.5-coder-family/ · hn=23 points/0 comments · raw={\"excerpt\":\"GITHUB HUGGING FACE MODELSCOPE KAGGLE DEMO DISCORD\\nIntroduction Today, we are excited to open source the “Powerful”, “Diverse”, and “Practical” Qwen2.5-Coder series, dedicated to continuously promoting the development of Open CodeLLMs.\\nPowerful: 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 two sizes of 1.\"}"},{"ref":"E24","kind":"event","title":"QwenLM/Qwen3-VL","date":"2024-08-29T08:30:38+00:00","date_source":"source","source_url":"https://github.com/QwenLM/Qwen3-VL","signal_url":"https://onlylabs.fyi/signals/3900272b-9582-410b-b4bb-e27ba64feb1b","signal_json_url":"https://onlylabs.fyi/signals/3900272b-9582-410b-b4bb-e27ba64feb1b/signal.json","text":"repo_new · QwenLM/Qwen3-VL · signal_desk=repos · occurred_at=2024-08-29T08:30:38+00:00 · url=https://github.com/QwenLM/Qwen3-VL · stars=19353 · raw={\"repo\":\"QwenLM/Qwen3-VL\",\"description\":\"Qwen3-VL is the multimodal large language model series developed by Qwen team, Alibaba Cloud.\",\"language\":\"Jupyter Notebook\"}"},{"ref":"E25","kind":"event","title":"Qwen/Qwen-Image-Bench","date":"2026-05-21T04:15:56+00:00","date_source":"source","source_url":"https://huggingface.co/Qwen/Qwen-Image-Bench","signal_url":"https://onlylabs.fyi/signals/d97dc28e-bebc-483d-beb8-e801edd051d5","signal_json_url":"https://onlylabs.fyi/signals/d97dc28e-bebc-483d-beb8-e801edd051d5/signal.json","text":"model_released · Qwen/Qwen-Image-Bench · signal_desk=releases · occurred_at=2026-05-21T04:15:56+00:00 · url=https://huggingface.co/Qwen/Qwen-Image-Bench · hf_downloads=13326 · hf_likes=56 · hf_params=27356728560 · pipeline=image-text-to-text · license=apache-2.0 · raw={\"derived_reason\":\"first-party-finetune\"}"},{"ref":"E26","kind":"event","title":"Qwen/Qwen3.5-9B-Base","date":"2026-02-26T16:20:10+00:00","date_source":"source","source_url":"https://huggingface.co/Qwen/Qwen3.5-9B-Base","signal_url":"https://onlylabs.fyi/signals/9296c0a0-b46e-44e1-8f03-187bbdaaad82","signal_json_url":"https://onlylabs.fyi/signals/9296c0a0-b46e-44e1-8f03-187bbdaaad82/signal.json","text":"model_released · Qwen/Qwen3.5-9B-Base · signal_desk=releases · occurred_at=2026-02-26T16:20:10+00:00 · url=https://huggingface.co/Qwen/Qwen3.5-9B-Base · hf_downloads=190775 · hf_likes=81 · hf_params=9653104368 · pipeline=image-text-to-text · license=apache-2.0"},{"ref":"E27","kind":"event","title":"Qwen/Qwen3.5-0.8B-Base","date":"2026-02-28T23:57:45+00:00","date_source":"source","source_url":"https://huggingface.co/Qwen/Qwen3.5-0.8B-Base","signal_url":"https://onlylabs.fyi/signals/8158c3b8-2dc7-403d-9b15-8774935f72d6","signal_json_url":"https://onlylabs.fyi/signals/8158c3b8-2dc7-403d-9b15-8774935f72d6/signal.json","text":"model_released · Qwen/Qwen3.5-0.8B-Base · signal_desk=releases · occurred_at=2026-02-28T23:57:45+00:00 · url=https://huggingface.co/Qwen/Qwen3.5-0.8B-Base · hf_downloads=188718 · hf_likes=79 · hf_params=873438784 · pipeline=image-text-to-text · license=apache-2.0"},{"ref":"E28","kind":"event","title":"QwenLM/Qwen3-Coder","date":"2024-04-16T11:49:01+00:00","date_source":"source","source_url":"https://github.com/QwenLM/Qwen3-Coder","signal_url":"https://onlylabs.fyi/signals/83e748ac-84d2-41ae-81d2-4d72f50a7c75","signal_json_url":"https://onlylabs.fyi/signals/83e748ac-84d2-41ae-81d2-4d72f50a7c75/signal.json","text":"repo_new · QwenLM/Qwen3-Coder · signal_desk=repos · occurred_at=2024-04-16T11:49:01+00:00 · url=https://github.com/QwenLM/Qwen3-Coder · stars=16611 · raw={\"repo\":\"QwenLM/Qwen3-Coder\",\"description\":\"Qwen3-Coder is the code version of Qwen3, the large language model series developed by Qwen team.\",\"language\":\"Python\"}"},{"ref":"E29","kind":"event","title":"Qwen/Qwen3.5-2B-Base","date":"2026-02-28T23:57:23+00:00","date_source":"source","source_url":"https://huggingface.co/Qwen/Qwen3.5-2B-Base","signal_url":"https://onlylabs.fyi/signals/eed9e7b5-ae24-4bb0-9c65-f70248d7875d","signal_json_url":"https://onlylabs.fyi/signals/eed9e7b5-ae24-4bb0-9c65-f70248d7875d/signal.json","text":"model_released · Qwen/Qwen3.5-2B-Base · signal_desk=releases · occurred_at=2026-02-28T23:57:23+00:00 · url=https://huggingface.co/Qwen/Qwen3.5-2B-Base · hf_downloads=130071 · hf_likes=76 · hf_params=2274069824 · pipeline=image-text-to-text · license=apache-2.0"},{"ref":"E30","kind":"event","title":"Qwen/Qwen3.5-4B-Base","date":"2026-02-27T13:20:09+00:00","date_source":"source","source_url":"https://huggingface.co/Qwen/Qwen3.5-4B-Base","signal_url":"https://onlylabs.fyi/signals/29322fca-2b57-48eb-b627-402cf360a22d","signal_json_url":"https://onlylabs.fyi/signals/29322fca-2b57-48eb-b627-402cf360a22d/signal.json","text":"model_released · Qwen/Qwen3.5-4B-Base · signal_desk=releases · occurred_at=2026-02-27T13:20:09+00:00 · url=https://huggingface.co/Qwen/Qwen3.5-4B-Base · hf_downloads=191545 · hf_likes=68 · hf_params=4659865088 · pipeline=image-text-to-text · license=apache-2.0"},{"ref":"E31","kind":"event","title":"QwenLM/Qwen3-TTS","date":"2026-01-21T06:41:32+00:00","date_source":"source","source_url":"https://github.com/QwenLM/Qwen3-TTS","signal_url":"https://onlylabs.fyi/signals/52f2ebf5-a1dd-4c7c-8e70-c70899d42b1a","signal_json_url":"https://onlylabs.fyi/signals/52f2ebf5-a1dd-4c7c-8e70-c70899d42b1a/signal.json","text":"repo_new · QwenLM/Qwen3-TTS · signal_desk=repos · occurred_at=2026-01-21T06:41:32+00:00 · url=https://github.com/QwenLM/Qwen3-TTS · stars=11864 · hn=1 points/0 comments · data_radar_lanes=Product and customer · data_radar_terms=support · data_radar_reason=Qwen (Alibaba Cloud) has a repo signal matching product and customer. · raw={\"repo\":\"QwenLM/Qwen3-TTS\",\"description\":\"Qwen3-TTS is an open-source series of TTS models developed by the Qwen team at Alibaba Cloud, supporting stable, expressive, and streaming speech generation, free-form voice design, and vivid voice cloning.\",\"language\":\"Python\"}"},{"ref":"E32","kind":"event","title":"QwenLM/Qwen3-VL-Embedding","date":"2026-01-08T03:42:57+00:00","date_source":"source","source_url":"https://github.com/QwenLM/Qwen3-VL-Embedding","signal_url":"https://onlylabs.fyi/signals/df19ca56-669c-4ea6-92be-efa14ae21996","signal_json_url":"https://onlylabs.fyi/signals/df19ca56-669c-4ea6-92be-efa14ae21996/signal.json","text":"repo_new · QwenLM/Qwen3-VL-Embedding · signal_desk=repos · occurred_at=2026-01-08T03:42:57+00:00 · url=https://github.com/QwenLM/Qwen3-VL-Embedding · stars=1283 · hn=11 points/1 comments · raw={\"repo\":\"QwenLM/Qwen3-VL-Embedding\",\"language\":\"Python\"}"},{"ref":"E33","kind":"event","title":"Qwen/SAE-Res-Qwen3.5-27B-W80K-L0_50","date":"2026-04-27T03:39:42+00:00","date_source":"source","source_url":"https://huggingface.co/Qwen/SAE-Res-Qwen3.5-27B-W80K-L0_50","signal_url":"https://onlylabs.fyi/signals/ec0a7ee3-9ba4-4102-b1ce-88a7134aaa32","signal_json_url":"https://onlylabs.fyi/signals/ec0a7ee3-9ba4-4102-b1ce-88a7134aaa32/signal.json","text":"model_released · Qwen/SAE-Res-Qwen3.5-27B-W80K-L0_50 · signal_desk=releases · occurred_at=2026-04-27T03:39:42+00:00 · url=https://huggingface.co/Qwen/SAE-Res-Qwen3.5-27B-W80K-L0_50 · hf_downloads=272 · hf_likes=38 · license=other · raw={\"derived_reason\":\"first-party-finetune\"}"},{"ref":"E34","kind":"event","title":"QwenLM/open-computer-use demo-assets","date":"2026-06-10T16:23:31+00:00","date_source":"source","source_url":"https://github.com/QwenLM/open-computer-use/releases/tag/demo-assets","signal_url":"https://onlylabs.fyi/signals/bae3cc2f-e1dc-48c6-b0b8-902a9a9d50d1","signal_json_url":"https://onlylabs.fyi/signals/bae3cc2f-e1dc-48c6-b0b8-902a9a9d50d1/signal.json","text":"release · QwenLM/open-computer-use demo-assets · signal_desk=releases · occurred_at=2026-06-10T16:23:31+00:00 · url=https://github.com/QwenLM/open-computer-use/releases/tag/demo-assets · raw={\"repo\":\"QwenLM/open-computer-use\"}"},{"ref":"E35","kind":"event","title":"QwenLM/qwen-code v0.18.0-preview.1","date":"2026-06-09T07:10:52+00:00","date_source":"source","source_url":"https://github.com/QwenLM/qwen-code/releases/tag/v0.18.0-preview.1","signal_url":"https://onlylabs.fyi/signals/99708a37-4440-45ac-bd84-28a75622569c","signal_json_url":"https://onlylabs.fyi/signals/99708a37-4440-45ac-bd84-28a75622569c/signal.json","text":"release · QwenLM/qwen-code v0.18.0-preview.1 · signal_desk=releases · occurred_at=2026-06-09T07:10:52+00:00 · url=https://github.com/QwenLM/qwen-code/releases/tag/v0.18.0-preview.1 · raw={\"repo\":\"QwenLM/qwen-code\"}"},{"ref":"E36","kind":"event","title":"QwenLM/qwen-code v0.18.0-preview.0","date":"2026-06-09T03:47:04+00:00","date_source":"source","source_url":"https://github.com/QwenLM/qwen-code/releases/tag/v0.18.0-preview.0","signal_url":"https://onlylabs.fyi/signals/8cb76745-e036-40b7-b03b-bd6a380e424b","signal_json_url":"https://onlylabs.fyi/signals/8cb76745-e036-40b7-b03b-bd6a380e424b/signal.json","text":"release · QwenLM/qwen-code v0.18.0-preview.0 · signal_desk=releases · occurred_at=2026-06-09T03:47:04+00:00 · url=https://github.com/QwenLM/qwen-code/releases/tag/v0.18.0-preview.0 · raw={\"repo\":\"QwenLM/qwen-code\"}"},{"ref":"E37","kind":"event","title":"QwenLM/qwen-code v0.17.1-nightly.20260608.aea34fa2c","date":"2026-06-08T00:43:36+00:00","date_source":"source","source_url":"https://github.com/QwenLM/qwen-code/releases/tag/v0.17.1-nightly.20260608.aea34fa2c","signal_url":"https://onlylabs.fyi/signals/10cb4fd7-4b46-49de-9325-0efbbb7107f9","signal_json_url":"https://onlylabs.fyi/signals/10cb4fd7-4b46-49de-9325-0efbbb7107f9/signal.json","text":"release · QwenLM/qwen-code v0.17.1-nightly.20260608.aea34fa2c · signal_desk=releases · occurred_at=2026-06-08T00:43:36+00:00 · url=https://github.com/QwenLM/qwen-code/releases/tag/v0.17.1-nightly.20260608.aea34fa2c · raw={\"repo\":\"QwenLM/qwen-code\"}"},{"ref":"E38","kind":"event","title":"QwenLM/qwen-code v0.17.1-nightly.20260607.cef26a86a","date":"2026-06-07T00:41:55+00:00","date_source":"source","source_url":"https://github.com/QwenLM/qwen-code/releases/tag/v0.17.1-nightly.20260607.cef26a86a","signal_url":"https://onlylabs.fyi/signals/06bac7fa-217c-4f86-8574-b7bb03d5abc2","signal_json_url":"https://onlylabs.fyi/signals/06bac7fa-217c-4f86-8574-b7bb03d5abc2/signal.json","text":"release · QwenLM/qwen-code v0.17.1-nightly.20260607.cef26a86a · signal_desk=releases · occurred_at=2026-06-07T00:41:55+00:00 · url=https://github.com/QwenLM/qwen-code/releases/tag/v0.17.1-nightly.20260607.cef26a86a · raw={\"repo\":\"QwenLM/qwen-code\"}"},{"ref":"E39","kind":"event","title":"QwenLM/qwen-code v0.17.1-nightly.20260606.16c1d9a5a","date":"2026-06-06T00:42:57+00:00","date_source":"source","source_url":"https://github.com/QwenLM/qwen-code/releases/tag/v0.17.1-nightly.20260606.16c1d9a5a","signal_url":"https://onlylabs.fyi/signals/5fe78ea9-4724-4993-8804-ce8ec4f79c95","signal_json_url":"https://onlylabs.fyi/signals/5fe78ea9-4724-4993-8804-ce8ec4f79c95/signal.json","text":"release · QwenLM/qwen-code v0.17.1-nightly.20260606.16c1d9a5a · signal_desk=releases · occurred_at=2026-06-06T00:42:57+00:00 · url=https://github.com/QwenLM/qwen-code/releases/tag/v0.17.1-nightly.20260606.16c1d9a5a · raw={\"repo\":\"QwenLM/qwen-code\"}"},{"ref":"E40","kind":"event","title":"通义大模型事业部-算法工程师","date":"2026-06-05T22:36:20.978+00:00","date_source":"source","source_url":"https://careers-tongyi.alibaba.com/","signal_url":"https://onlylabs.fyi/signals/9b63b040-385f-4d89-afc1-87169baae0b4","signal_json_url":"https://onlylabs.fyi/signals/9b63b040-385f-4d89-afc1-87169baae0b4/signal.json","text":"job_opened · 通义大模型事业部-算法工程师 · signal_desk=hiring · occurred_at=2026-06-05T22:36:20.978+00:00 · url=https://careers-tongyi.alibaba.com/ · raw={\"location\":\"杭州\",\"ats\":\"agent\"}"},{"ref":"E41","kind":"event","title":"通义大模型事业部-研发工程师","date":"2026-06-05T22:36:20.978+00:00","date_source":"source","source_url":"https://careers-tongyi.alibaba.com/","signal_url":"https://onlylabs.fyi/signals/d71a00a6-8599-4991-8416-1dded974925a","signal_json_url":"https://onlylabs.fyi/signals/d71a00a6-8599-4991-8416-1dded974925a/signal.json","text":"job_opened · 通义大模型事业部-研发工程师 · signal_desk=hiring · occurred_at=2026-06-05T22:36:20.978+00:00 · url=https://careers-tongyi.alibaba.com/ · raw={\"location\":\"杭州\",\"ats\":\"agent\"}"},{"ref":"E42","kind":"event","title":"通义大模型事业部-高级算法工程师","date":"2026-06-05T22:34:53.161+00:00","date_source":"source","source_url":"https://careers-tongyi.alibaba.com/","signal_url":"https://onlylabs.fyi/signals/aed997b1-2e3c-4625-a2c8-22ae5d303744","signal_json_url":"https://onlylabs.fyi/signals/aed997b1-2e3c-4625-a2c8-22ae5d303744/signal.json","text":"job_opened · 通义大模型事业部-高级算法工程师 · signal_desk=hiring · occurred_at=2026-06-05T22:34:53.161+00:00 · url=https://careers-tongyi.alibaba.com/ · raw={\"location\":\"杭州\",\"ats\":\"agent\"}"},{"ref":"E43","kind":"event","title":"通义大模型事业部-高级研发工程师","date":"2026-06-05T22:34:53.161+00:00","date_source":"source","source_url":"https://careers-tongyi.alibaba.com/","signal_url":"https://onlylabs.fyi/signals/cee26fa7-6e94-4636-b666-19cd3b517f58","signal_json_url":"https://onlylabs.fyi/signals/cee26fa7-6e94-4636-b666-19cd3b517f58/signal.json","text":"job_opened · 通义大模型事业部-高级研发工程师 · signal_desk=hiring · occurred_at=2026-06-05T22:34:53.161+00:00 · url=https://careers-tongyi.alibaba.com/ · raw={\"location\":\"杭州\",\"ats\":\"agent\"}"},{"ref":"E44","kind":"event","title":"通义大模型事业部招聘官网","date":"2026-06-05T22:31:57.578+00:00","date_source":"source","source_url":"https://careers-tongyi.alibaba.com/","signal_url":"https://onlylabs.fyi/signals/4daaf156-c6af-4ddd-a4bc-724a78291418","signal_json_url":"https://onlylabs.fyi/signals/4daaf156-c6af-4ddd-a4bc-724a78291418/signal.json","text":"job_opened · 通义大模型事业部招聘官网 · signal_desk=hiring · occurred_at=2026-06-05T22:31:57.578+00:00 · url=https://careers-tongyi.alibaba.com/ · raw={\"ats\":\"agent\"}"},{"ref":"E45","kind":"event","title":"QwenLM/qwen-code v0.17.1-nightly.20260605.715266537","date":"2026-06-05T00:43:29+00:00","date_source":"source","source_url":"https://github.com/QwenLM/qwen-code/releases/tag/v0.17.1-nightly.20260605.715266537","signal_url":"https://onlylabs.fyi/signals/6604b5db-487d-4e72-9587-8cd5014e28cd","signal_json_url":"https://onlylabs.fyi/signals/6604b5db-487d-4e72-9587-8cd5014e28cd/signal.json","text":"release · QwenLM/qwen-code v0.17.1-nightly.20260605.715266537 · signal_desk=releases · occurred_at=2026-06-05T00:43:29+00:00 · url=https://github.com/QwenLM/qwen-code/releases/tag/v0.17.1-nightly.20260605.715266537 · raw={\"repo\":\"QwenLM/qwen-code\"}"},{"ref":"E46","kind":"event","title":"QwenLM/qwen-code v0.17.1-nightly.20260604.16dd99fa3","date":"2026-06-04T00:51:43+00:00","date_source":"source","source_url":"https://github.com/QwenLM/qwen-code/releases/tag/v0.17.1-nightly.20260604.16dd99fa3","signal_url":"https://onlylabs.fyi/signals/9cbb800d-7ed4-4c3b-a647-1df0807cb0bc","signal_json_url":"https://onlylabs.fyi/signals/9cbb800d-7ed4-4c3b-a647-1df0807cb0bc/signal.json","text":"release · QwenLM/qwen-code v0.17.1-nightly.20260604.16dd99fa3 · signal_desk=releases · occurred_at=2026-06-04T00:51:43+00:00 · url=https://github.com/QwenLM/qwen-code/releases/tag/v0.17.1-nightly.20260604.16dd99fa3 · raw={\"repo\":\"QwenLM/qwen-code\"}"},{"ref":"E47","kind":"event","title":"QwenLM/qwen-code v0.17.1","date":"2026-06-03T11:58:14+00:00","date_source":"source","source_url":"https://github.com/QwenLM/qwen-code/releases/tag/v0.17.1","signal_url":"https://onlylabs.fyi/signals/c1bdd251-16d3-497e-9606-4ca69a43dee9","signal_json_url":"https://onlylabs.fyi/signals/c1bdd251-16d3-497e-9606-4ca69a43dee9/signal.json","text":"release · QwenLM/qwen-code v0.17.1 · signal_desk=releases · occurred_at=2026-06-03T11:58:14+00:00 · url=https://github.com/QwenLM/qwen-code/releases/tag/v0.17.1 · raw={\"repo\":\"QwenLM/qwen-code\"}"},{"ref":"E48","kind":"event","title":"QwenLM/open-computer-use v0.2.0","date":"2026-06-03T03:03:12+00:00","date_source":"source","source_url":"https://github.com/QwenLM/open-computer-use/releases/tag/v0.2.0","signal_url":"https://onlylabs.fyi/signals/cdf541c0-1ae1-4b75-b6db-573c3ddef86d","signal_json_url":"https://onlylabs.fyi/signals/cdf541c0-1ae1-4b75-b6db-573c3ddef86d/signal.json","text":"release · QwenLM/open-computer-use v0.2.0 · signal_desk=releases · occurred_at=2026-06-03T03:03:12+00:00 · url=https://github.com/QwenLM/open-computer-use/releases/tag/v0.2.0 · raw={\"repo\":\"QwenLM/open-computer-use\"}"},{"ref":"E49","kind":"event","title":"QwenLM/qwen-code v0.17.0-preview.0","date":"2026-06-03T00:55:38+00:00","date_source":"source","source_url":"https://github.com/QwenLM/qwen-code/releases/tag/v0.17.0-preview.0","signal_url":"https://onlylabs.fyi/signals/da941fda-dece-427c-88a3-500f83644ae2","signal_json_url":"https://onlylabs.fyi/signals/da941fda-dece-427c-88a3-500f83644ae2/signal.json","text":"release · QwenLM/qwen-code v0.17.0-preview.0 · signal_desk=releases · occurred_at=2026-06-03T00:55:38+00:00 · url=https://github.com/QwenLM/qwen-code/releases/tag/v0.17.0-preview.0 · raw={\"repo\":\"QwenLM/qwen-code\"}"},{"ref":"E50","kind":"event","title":"QwenLM/qwen-code v0.17.0-nightly.20260603.68408c30c","date":"2026-06-03T00:51:19+00:00","date_source":"source","source_url":"https://github.com/QwenLM/qwen-code/releases/tag/v0.17.0-nightly.20260603.68408c30c","signal_url":"https://onlylabs.fyi/signals/bcebadb4-51e3-419b-9d94-759417fdb522","signal_json_url":"https://onlylabs.fyi/signals/bcebadb4-51e3-419b-9d94-759417fdb522/signal.json","text":"release · QwenLM/qwen-code v0.17.0-nightly.20260603.68408c30c · signal_desk=releases · occurred_at=2026-06-03T00:51:19+00:00 · url=https://github.com/QwenLM/qwen-code/releases/tag/v0.17.0-nightly.20260603.68408c30c · raw={\"repo\":\"QwenLM/qwen-code\"}"},{"ref":"E51","kind":"event","title":"QwenLM/Qwen-VLA","date":"2026-05-28T03:46:53+00:00","date_source":"source","source_url":"https://github.com/QwenLM/Qwen-VLA","signal_url":"https://onlylabs.fyi/signals/ed913285-e7b2-4360-9597-781340861ca6","signal_json_url":"https://onlylabs.fyi/signals/ed913285-e7b2-4360-9597-781340861ca6/signal.json","text":"repo_new · QwenLM/Qwen-VLA · signal_desk=repos · occurred_at=2026-05-28T03:46:53+00:00 · url=https://github.com/QwenLM/Qwen-VLA · stars=556 · raw={\"repo\":\"QwenLM/Qwen-VLA\",\"description\":\"The official repository of Qwen-VLA\"}"},{"ref":"E52","kind":"event","title":"QwenLM/open-computer-use","date":"2026-06-01T08:10:48+00:00","date_source":"source","source_url":"https://github.com/QwenLM/open-computer-use","signal_url":"https://onlylabs.fyi/signals/cf5152e4-92e2-4b30-8b9c-39fcaa9decd0","signal_json_url":"https://onlylabs.fyi/signals/cf5152e4-92e2-4b30-8b9c-39fcaa9decd0/signal.json","text":"repo_new · QwenLM/open-computer-use · signal_desk=repos · occurred_at=2026-06-01T08:10:48+00:00 · url=https://github.com/QwenLM/open-computer-use · stars=62 · raw={\"repo\":\"QwenLM/open-computer-use\",\"description\":\"MCP-based Computer Use service for Qwen Code and any AI agent — controls macOS, Linux, and Windows via accessibility APIs.\",\"language\":\"Swift\"}"},{"ref":"E53","kind":"event","title":"QwenLM/Qwen-Image","date":"2025-08-03T11:03:25+00:00","date_source":"source","source_url":"https://github.com/QwenLM/Qwen-Image","signal_url":"https://onlylabs.fyi/signals/71b0a729-1590-42d5-a124-54d7e8ceab79","signal_json_url":"https://onlylabs.fyi/signals/71b0a729-1590-42d5-a124-54d7e8ceab79/signal.json","text":"repo_new · QwenLM/Qwen-Image · signal_desk=repos · occurred_at=2025-08-03T11:03:25+00:00 · url=https://github.com/QwenLM/Qwen-Image · stars=7989 · raw={\"repo\":\"QwenLM/Qwen-Image\",\"description\":\"Qwen-Image is a powerful image generation foundation model capable of complex text rendering and precise image editing.\",\"language\":\"Python\"}"},{"ref":"E54","kind":"event","title":"Qwen/SAE-Res-Qwen3.5-27B-W80K-L0_100","date":"2026-04-27T03:39:43+00:00","date_source":"source","source_url":"https://huggingface.co/Qwen/SAE-Res-Qwen3.5-27B-W80K-L0_100","signal_url":"https://onlylabs.fyi/signals/7a175d59-aed8-4f0d-8833-3ee98d46a714","signal_json_url":"https://onlylabs.fyi/signals/7a175d59-aed8-4f0d-8833-3ee98d46a714/signal.json","text":"model_released · Qwen/SAE-Res-Qwen3.5-27B-W80K-L0_100 · signal_desk=releases · occurred_at=2026-04-27T03:39:43+00:00 · url=https://huggingface.co/Qwen/SAE-Res-Qwen3.5-27B-W80K-L0_100 · hf_downloads=88 · hf_likes=13 · license=other · raw={\"derived_reason\":\"first-party-finetune\"}"},{"ref":"E55","kind":"event","title":"QwenLM/Qwen-Image-Bench","date":"2026-05-21T03:41:40+00:00","date_source":"source","source_url":"https://github.com/QwenLM/Qwen-Image-Bench","signal_url":"https://onlylabs.fyi/signals/34eb5dfd-321d-4e8f-b0da-49498c12414c","signal_json_url":"https://onlylabs.fyi/signals/34eb5dfd-321d-4e8f-b0da-49498c12414c/signal.json","text":"repo_new · QwenLM/Qwen-Image-Bench · signal_desk=repos · occurred_at=2026-05-21T03:41:40+00:00 · url=https://github.com/QwenLM/Qwen-Image-Bench · stars=84 · raw={\"repo\":\"QwenLM/Qwen-Image-Bench\",\"language\":\"Python\"}"},{"ref":"E56","kind":"event","title":"QVQ: To See the World with Wisdom","date":"2024-12-25T00:00:00.000Z","date_source":"page.visible_date","source_url":"https://qwenlm.github.io/blog/qvq-72b-preview/","signal_url":"https://onlylabs.fyi/signals/26d01925-79d0-4742-8394-67d8947dd7ce","signal_json_url":"https://onlylabs.fyi/signals/26d01925-79d0-4742-8394-67d8947dd7ce/signal.json","text":"post_published · QVQ: To See the World with Wisdom · signal_desk=talking · occurred_at=2024-12-25T00:00:00.000Z · url=https://qwenlm.github.io/blog/qvq-72b-preview/ · hn=5 points/0 comments · raw={\"excerpt\":\"GITHUB HUGGING FACE MODELSCOPE KAGGLE DEMO DISCORD\\nLanguage 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’s large language models have demonstrated remarkable reasoning abilities, but we wondered: could they harness the power of visual understanding to reach new heights of cognitive capability?\"}"},{"ref":"E57","kind":"event","title":"Introducing Qwen1.5","date":"2024-02-04T05:33:00+00:00","date_source":"rss.item_date","source_url":"https://qwenlm.github.io/blog/qwen1.5/","signal_url":"https://onlylabs.fyi/signals/3ae010dc-4d40-4cfc-bcb3-049eaf5f1adb","signal_json_url":"https://onlylabs.fyi/signals/3ae010dc-4d40-4cfc-bcb3-049eaf5f1adb/signal.json","text":"post_published · Introducing Qwen1.5 · signal_desk=talking · occurred_at=2024-02-04T05:33:00+00:00 · url=https://qwenlm.github.io/blog/qwen1.5/ · hn=5 points/2 comments · raw={\"excerpt\":\"GITHUB HUGGING FACE MODELSCOPE DEMO DISCORD\\nIntroduction In recent months, our focus has been on developing a “good” model while optimizing the developer experience. As we progress towards Qwen1.5, the next iteration in our Qwen series, this update arrives just before the Chinese New Year.\\nWith Qwen1.5, we are open-sourcing base and chat models across six sizes: 0.5B, 1.8B, 4B, 7B, 14B, 32B, 72B, and 110B, and also an MoE model (see blog for more information).\"}"},{"ref":"E58","kind":"event","title":"Code with CodeQwen1.5","date":"2024-04-16T05:33:00+00:00","date_source":"rss.item_date","source_url":"https://qwenlm.github.io/blog/codeqwen1.5/","signal_url":"https://onlylabs.fyi/signals/b35e22a6-8968-43ca-9428-33077834700f","signal_json_url":"https://onlylabs.fyi/signals/b35e22a6-8968-43ca-9428-33077834700f/signal.json","text":"post_published · Code with CodeQwen1.5 · signal_desk=talking · occurred_at=2024-04-16T05:33:00+00:00 · url=https://qwenlm.github.io/blog/codeqwen1.5/ · hn=3 points/0 comments · data_radar_lanes=Safety and policy, Product and customer · data_radar_terms=security, privacy, product · data_radar_reason=Qwen (Alibaba Cloud) has a writing signal matching safety and policy, product and customer. · raw={\"excerpt\":\"GITHUB HUGGING FACE MODELSCOPE DEMO DISCORD\\nIntroduction 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 notable challenges in terms of cost, privacy, security, and potential copyright infringement. Recognizing the imperative for a more transparent and accessible alternative, the open-source community has embarked on a concerted endeavor to develop open codeLLMs.\"}"},{"ref":"E59","kind":"event","title":"QwenLM/vllm-gptq","date":"2023-12-14T07:53:09+00:00","date_source":"source","source_url":"https://github.com/QwenLM/vllm-gptq","signal_url":"https://onlylabs.fyi/signals/d431ceb2-4f7c-434e-ab35-adf343d37084","signal_json_url":"https://onlylabs.fyi/signals/d431ceb2-4f7c-434e-ab35-adf343d37084/signal.json","text":"repo_forked · QwenLM/vllm-gptq · signal_desk=forks · occurred_at=2023-12-14T07:53:09+00:00 · url=https://github.com/QwenLM/vllm-gptq · stars=142 · raw={\"repo\":\"QwenLM/vllm-gptq\",\"parent\":\"vllm-project/vllm\"}"},{"ref":"E60","kind":"event","title":"QwenLM/vllm","date":"2025-01-25T12:36:14+00:00","date_source":"source","source_url":"https://github.com/QwenLM/vllm","signal_url":"https://onlylabs.fyi/signals/aebcb78c-24e8-4c2a-811d-82fd23416b73","signal_json_url":"https://onlylabs.fyi/signals/aebcb78c-24e8-4c2a-811d-82fd23416b73/signal.json","text":"repo_forked · QwenLM/vllm · signal_desk=forks · occurred_at=2025-01-25T12:36:14+00:00 · url=https://github.com/QwenLM/vllm · stars=42 · raw={\"repo\":\"QwenLM/vllm\",\"parent\":\"vllm-project/vllm\"}"}]}