\n| \n 🌐 Web Demo for both CogVLM2: this lin"},{"ref":"P13","kind":"page","title":"zai-org/CogAgent repository metadata","date":"2026-06-11T01:45:59.695138+00:00","date_source":null,"source_url":"https://github.com/zai-org/CogAgent","signal_url":null,"signal_json_url":null,"text":"# zai-org/CogAgent\n\nDescription: An open-sourced end-to-end VLM-based GUI Agent\n\nLanguage: Python\n\nLicense: Apache-2.0\n\nStars: 1183\n\nForks: 99\n\nOpen issues: 29\n\nCreated: 2023-11-28T09:28:08Z\n\nPushed: 2025-04-04T13:29:55Z\n\nDefault branch: main\n\nFork: no\n\nArchived: no\n\nREADME:\n# CogAgent: An open-sourced VLM-based GUI Agent\n\n[中文文档](README_zh.md)\n\n- 🔥 🆕 **December 2024:** We open-sourced **the latest version of the CogAgent-9B-20241220 model**. Compared to the\nprevious version of CogAgent, `CogAgent-9B-20241220` features significant improvements in GUI perception, reasoning\naccuracy, action space completeness, task universality, and generalization. It supports bilingual (Chinese and\nEnglish) interaction through both screen captures and natural language.\n\n- 🏆 **June 2024:** CogAgent was accepted by **CVPR 2024** and recognized as a conference Highlight (top 3%).\n\n- **December 2023:** We **open-sourced the first GUI Agent**: **CogAgent** (with the former repository\navailable [here](https://github.com/THUDM/CogVLM)) and **published the corresponding paper:\n📖 [CogAgent Paper](https://arxiv.org/abs/2312.08914)**.\n\n## Model Introduction\n\n| Model | Model Download Links | Technical Documentation | Online Demo | \n|:--------------------:|:--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------:|---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------| \n| cogagent-9b-20241220 | [🤗 HuggingFace](https://huggingface.co/THUDM/cogagent-9b-20241220)
[🤖 ModelScope](https://modelscope.cn/models/ZhipuAI/cogagent-9b-20"},{"ref":"P14","kind":"page","title":"zai-org/ChatGLM3 repository metadata","date":"2026-06-11T01:45:59.619514+00:00","date_source":null,"source_url":"https://github.com/zai-org/ChatGLM3","signal_url":null,"signal_json_url":null,"text":"# zai-org/ChatGLM3\n\nDescription: ChatGLM3 series: Open Bilingual Chat LLMs | 开源双语对话语言模型\n\nLanguage: Python\n\nLicense: Apache-2.0\n\nStars: 13679\n\nForks: 1591\n\nOpen issues: 35\n\nCreated: 2023-10-26T06:22:47Z\n\nPushed: 2025-01-13T06:55:26Z\n\nDefault branch: main\n\nFork: no\n\nArchived: no\n\nREADME:\n# ChatGLM3\n\n\n📄 Report • 🤗 HF Repo • 🤖 ModelScope • 🟣 WiseModel • 📔 Document • 🧰 OpenXLab • 🐦 Twitter
\n \n\n👋 加入我们的 Discord 和 微信\n \n\n📍在 chatglm.cn 体验更大规模的 ChatGLM 模型。\n \n\n[Read this in English.](./README_en.md)\n\n📔 关于`ChatGLM3-6B` 更为详细的使用信息，可以参考\n\n+ [ChatGLM3 开放技术文档](https://lslfd0slxc.feishu.cn/wiki/WvQbwIJ9tiPAxGk8ywDck6yfnof?from=from_copylink)\n+ [Bilibili video](https://www.bilibili.com/video/BV1uC4y1J7yA)\n+ [YouTube video](https://www.youtube.com/watch?v=Pw9PB6R7ORA)\n\n## GLM-4 开源模型和API\n\n我们已经发布最新的 **GLM-4** 模型，该模型在多个指标上有了新的突破，您可以在以下两个渠道体验我们的最新模型。\n\n+ [GLM-4 开源模型](https://github.com/THUDM/GLM-4) 我们已经开源了 GLM-4-9B 系列模型，在各项指标的测试上有明显提升，欢迎尝试。\n+ [智谱清言](https://chatglm.cn/main/detail?fr=ecology_x) 体验最新版 GLM-4，包括 **GLMs，All tools**等功能。\n+ [API平台](https://open.bigmodel.cn/?utm_campaign=open&_channel_track_key=OWTVNma9) 新一代 API 平台已经上线，您可以直接在\nAPI\n平台上体验 `GLM-4-0520`、`GLM-4-air`、`GLM-4-airx`、`GLM-4-flash`、`GLM-4`、`GLM-3-Turbo`、`CharacterGLM-3`，`CogView-3`\n等新模型。\n其中`GLM-4`、`GLM-3-Turbo`两个模型支持了 `System Prompt`、`Function Call`、 `Retrieval`、`Web_Search`等新功能，欢迎体验。\n\n+ [GLM-4 API 开源教程](https://github.com/MetaGLM/glm-cookbook/) GLM-4 API教程和基础应用，欢迎尝试。\nAPI相关问题可以在本开源教程疑问，或者使用 [GLM-4 API A"},{"ref":"P15","kind":"page","title":"zai-org/CogCoM repository metadata","date":"2026-06-11T01:45:59.226122+00:00","date_source":null,"source_url":"https://github.com/zai-org/CogCoM","signal_url":null,"signal_json_url":null,"text":"# zai-org/CogCoM\n\nLanguage: Jupyter Notebook\n\nLicense: NOASSERTION\n\nStars: 223\n\nForks: 14\n\nOpen issues: 20\n\nCreated: 2024-02-02T11:18:30Z\n\nPushed: 2024-07-05T09:56:19Z\n\nDefault branch: main\n\nFork: no\n\nArchived: no\n\nREADME:\n\n If you like our project, please give us a star ⭐ on GitHub for latest update.
\n\n[](https://huggingface.co/qijimrc/CogCoM)\n[](https://arxiv.org/pdf/2402.04236) \n[](https://github.com/THUDM/CogCoM/blob/main/LICENSE)\n\n\n💡 We also have other vision-language projects that may interest you ✨. \n\n\n> [**CogVLM: Visual Expert for Pretrained Language Models**](https://github.com/THUDM/CogVLM)
\n[](https://github.com/THUDM/CogVLM) [](https://github.com/THUDM/CogVLM)
\n> [**CogAgent: A Visual Language Model for GUI Agents**](https://github.com/THUDM/CogVLM)
\n[](https://github.com/THUDM/CogVLM) [](https://github.com/THUDM/CogVLM)
\n\n \n \n\n\n \n👋 Join our Wechat · 💡Try CogVLM2 Online 💡Try CogVLM2-Video Online\n \n\n📍Experience the larger-scale CogVLM model on the ZhipuAI Open Platform.\n \n\n## Recent updates\n- 🔥 **News**: ``2024/8/30``: The [CogVLM2 paper](https://arxiv.org/abs/2408.16500) has been published on arXiv.\n- 🔥 **News**: ``2024/7/12``: We have released CogVLM2-Video [online web demo](http://cogvlm2-online.cogviewai.cn:7868/), welcome to experience it.\n- 🔥 **News**: ``2024/7/8``: We released the video understanding version of the CogVLM2 model, the CogVLM2-Video model.\nBy extracting keyframes, it can interpret continuous images. The model can support videos of up to 1 minute. See more\nin our [blog](https://cogvlm2-video.github.io/).\n- 🔥 **News**: ``2024/6/8``:We release [CogVLM2 TGI Weight](https://huggingface.co/THUDM/cogvlm2-llama3-chat-19B-tgi),\nwhich is a model can be inferred in [TGI](https://huggingface.co/docs/text-generation-inference/en/index). See\nInference Code in [here](https://github.com/leizhao1234/cogvlm2)\n- 🔥 **News**: ``2024/6/5``:We release [GLM-4V-9B](https://huggingface.co/THUDM/glm-4v-9b), which use the same data and\ntraining recipes as CogVLM2 but with GLM-9B as the language backbone. We removed visual experts to reduce the model\nsize to 13B. More details at [GLM-4 repo](https://github.com/THUDM/GLM-4/).\n- 🔥 **News**: ``2024/5/24``: We have released\nthe [Int4 version model](https://huggingface.co/THUDM/cogvlm2-llama3-chat-19B-int4), which re"},{"ref":"P17","kind":"page","title":"zai-org/Inf-DiT repository metadata","date":"2026-06-11T01:45:59.008486+00:00","date_source":null,"source_url":"https://github.com/zai-org/Inf-DiT","signal_url":null,"signal_json_url":null,"text":"# zai-org/Inf-DiT\n\nDescription: Official implementation of Inf-DiT: Upsampling Any-Resolution Image with Memory-Efficient Diffusion Transformer\n\nLanguage: Python\n\nLicense: Apache-2.0\n\nStars: 445\n\nForks: 25\n\nOpen issues: 24\n\nCreated: 2024-05-07T07:02:59Z\n\nPushed: 2024-07-05T10:35:10Z\n\nDefault branch: main\n\nFork: no\n\nArchived: no\n\nREADME:\n# Inf-DiT\n\n[](https://arxiv.org/abs/2405.04312)[](https://badges.toozhao.com/stats/01HXBVPE6J3YKGEWCFSBRAXFAK \"Get your own page views count badge on badges.toozhao.com\")\n\nOfficial implementation of Inf-DiT: Upsampling Any-Resolution Image with Memory-Efficient Diffusion Transformer\n\n\n\n## 🆕 News\n\n* **2024.07.01**: Inf-DiT has been accepted by ECCV2024!\n* **2024.05.20**: This code and model weight is released.\n* **2024.05.08**: This repo is released.\n\n## ⏳ TODO\n\n- [x] Code release\n- [x] Model weight release\n- [x] Complete the explanation for the inference code and hyperparameter\n- [ ] Demo\n- [ ] Comfyui\n\n## 🔆 Abstract\n\nDiffusion models have shown remarkable performance in image generation in recent years. However, due to a quadratic increase in memory during generating ultra-high-resolution images (e.g. 4096 × 4096), the resolution of generated images is often limited to 1024×1024. In this work, we propose a unidirectional block attention mechanism that can adaptively adjust the memory overhead during the inference process and handle global dependencies. Building on this module, we adopt the DiT structure for upsampling and develop an infinite super-resolution model capable of upsampling images of various shapes and resolutions. Comprehensive experiments show that our model achieves excellent performance in generating ultra-high-resolution images. Compared to commonly used UNet structures, our model can save more than 5× memory when generating 4096 × 4096 images.\n\n## 📚 Model Inference\nModel weights can be downloaded from [here](https://cloud.tsinghua.edu.cn/f/6e313f7e1236468e973b/?dl=1)\n\n1. Download the model weights and put them i"},{"ref":"P18","kind":"page","title":"zai-org/GLM-4 repository metadata","date":"2026-06-11T01:45:58.868982+00:00","date_source":null,"source_url":"https://github.com/zai-org/GLM-4","signal_url":null,"signal_json_url":null,"text":"# zai-org/GLM-4\n\nDescription: GLM-4 series: Open Multilingual Multimodal Chat LMs | 开源多语言多模态对话模型\n\nLanguage: Python\n\nLicense: Apache-2.0\n\nStars: 7065\n\nForks: 616\n\nOpen issues: 38\n\nCreated: 2024-05-15T05:17:08Z\n\nPushed: 2025-07-04T04:16:36Z\n\nDefault branch: main\n\nFork: no\n\nArchived: no\n\nREADME:\n# GLM-4-0414 Model Series\n\n\n👋 Join our Discord, X and WeChat (Chinese) \n \n\n📍The open-source models released this time can be experienced for free at Z.ai; for GLM commercial model services, please visit bigmodel.cn.\n \n\nRead this in [中文](README_zh.md)\n\n## Project Updates\n\n- 🔥 **News**: ```2025/07/02```: We are releasing the [GLM-4.1V-9B-Thinking](https://huggingface.co/collections/THUDM/glm-41v-thinking-6862bbfc44593a8601c2578d) series VLM, check [this github repo](https://github.com/THUDM/GLM-4.1V-Thinking) to get more information.\n- **News**: ```2025/04/14```: We are releasing the [GLM-4-32B-0414](https://huggingface.co/collections/THUDM/glm-4-0414-67f3cbcb34dd9d252707cb2e) series models, scaled up to 32B parameters, including models with capabilities for dialogue, reasoning, and rumination.\n- **News**: ``2024/06/18``: We have released our [Technical Report](https://arxiv.org/pdf/2406.12793), feel free to check it out.\n- **News**: ``2024/06/05``: We released the `GLM-4-9B` series of open-source models. Details can be found [here](README_20240605.md).\n\n## Model Introduction\n\nThe GLM family welcomes new members, the **GLM-4-32B-0414** series models, featuring 32 billion parameters. Its performance is comparable to OpenAI’s GPT series and DeepSeek’s V3/R1 series. It also supports very user-friendly local deployment features. GLM-4-32B-Base-0414 was pre-trained on 15T of high-quality data, including substantial reasoning-type synthetic data. This lays the foundation for subsequent reinforcement learning extensions. In the post-training stage, we employed human preference alignment for dialogue scenarios. Add"},{"ref":"P19","kind":"page","title":"zai-org/LVBench repository metadata","date":"2026-06-11T01:45:58.837142+00:00","date_source":null,"source_url":"https://github.com/zai-org/LVBench","signal_url":null,"signal_json_url":null,"text":"# zai-org/LVBench\n\nDescription: [ICCV 2025] LVBench: An Extreme Long Video Understanding Benchmark\n\nLanguage: Python\n\nStars: 143\n\nForks: 6\n\nOpen issues: 12\n\nCreated: 2024-05-29T07:48:02Z\n\nPushed: 2025-07-09T07:47:57Z\n\nDefault branch: main\n\nFork: no\n\nArchived: no\n\nREADME:\n# LVBench: An Extreme Long Video Understanding Benchmark\n\n\n\n \n\n\n\n\n\n [[🍎 Project Page](https://lvbench.github.io/)] [[📖 arXiv Paper](https://arxiv.org/abs/2406.08035)] [[📊 Dataset](https://huggingface.co/datasets/THUDM/LVBench)][[🏆 Leaderboard](https://lvbench.github.io/#leaderboard)][[🏆 Huggingface Leaderboard](https://huggingface.co/spaces/THUDM/LVBench)] \n\n\n![](\"./docs/images/cover.png\") \n \n\nLVBench is a benchmark designed to evaluate and enhance the capabilities of multimodal models in understanding and\nextracting information from long videos up to two hours in duration.\n\n---\n\n## 🔥 News\n\n* **`2024.08.2`** 🌟 We setup the LVBench Leaderboard on Huggingface Spaces! Have a check on the [Leaderboard](https://huggingface.co/spaces/THUDM/LVBench).\n* **`2024.06.11`** 🌟 We released LVBench, a new benchmark for long video understanding!\n\n## 👀 Introduce to LVBench\n\nLVBench is a benchmark designed to evaluate the capabilities of models in understanding long videos. We collected\nextensive long video data from public sources, annotated through a mix of manual effort and model assistance. Our\nbenchmark provides a robust foundation for testing models on extended temporal contexts, ensuring high-quality\nassessment through meticulous human annotation and multi-stage quality control.\n\n### Features\n\n1. **Core Capabilities**: Six core capabilities for long video understanding, enabling"},{"ref":"P20","kind":"page","title":"zai-org/CogView4 repository metadata","date":"2026-06-11T01:45:58.358175+00:00","date_source":null,"source_url":"https://github.com/zai-org/CogView4","signal_url":null,"signal_json_url":null,"text":"# zai-org/CogView4\n\nDescription: CogView4, CogView3-Plus and CogView3(ECCV 2024)\n\nLanguage: Python\n\nLicense: Apache-2.0\n\nStars: 1103\n\nForks: 81\n\nOpen issues: 12\n\nCreated: 2024-09-23T06:38:31Z\n\nPushed: 2025-03-29T07:09:58Z\n\nDefault branch: main\n\nFork: no\n\nArchived: no\n\nREADME:\n# CogView4 & CogView3 & CogView-3Plus\n\n[阅读中文版](./README_zh.md)\n[日本語で読む](./README_ja.md)\n\n\n \n \n 🤗 HuggingFace Space\n 🤖ModelScope Space\n 🛠️ZhipuAI MaaS(Faster)\n
\n 👋 WeChat Community 📚 CogView3 Paper\n \n\n\n\n## Project Updates\n\n- 🔥🔥 ```2025/03/24```: We are launching [CogKit](https://github.com/THUDM/CogKit), a powerful toolkit for fine-tuning and inference of the **CogView4** and **CogVideoX** series, allowing you to fully explore our multimodal generation models.\n- ```2025/03/04```: We've adapted and open-sourced the [diffusers](https://github.com/huggingface/diffusers) version\nof **CogView-4** model, which has 6B parameters, supports native Chinese input, and Chinese text-to-image generation.\nYou can try it [online](https://huggingface.co/spaces/THUDM-HF-SPACE/CogView4).\n- ```2024/10/13```: We've adapted and open-sourced the [diffusers](https://github.com/huggingface/diffusers) version of\n**CogView-3Plus-3B** model. You can try\nit [online](https://huggingface.co/spaces/THUDM-HF-SPACE/CogView3-Plus-3B-Space).\n- ```2024/9/29```: We've open-sourced **CogView3** and **CogView-3Plus-3B**. **CogView3** is a text-to-image system\nbased on cascading diffusion, using a relay diffusion framework. **CogView-3Plus** is a series of newly developed\ntext-to-image models based on Diffusion Transformer.\n\n## Project Plan\n\n- [X] Diffusers workflow adaptation\n- [X] Cog series fine-tuning kits (coming soon)\n- [ ] ControlNet model"},{"ref":"P21","kind":"page","title":"zai-org/GLM-4-Voice repository metadata","date":"2026-06-11T01:45:58.293995+00:00","date_source":null,"source_url":"https://github.com/zai-org/GLM-4-Voice","signal_url":null,"signal_json_url":null,"text":"# zai-org/GLM-4-Voice\n\nDescription: GLM-4-Voice | 端到端中英语音对话模型\n\nLanguage: Python\n\nLicense: Apache-2.0\n\nStars: 3187\n\nForks: 281\n\nOpen issues: 68\n\nCreated: 2024-10-24T12:12:32Z\n\nPushed: 2024-12-05T07:10:01Z\n\nDefault branch: main\n\nFork: no\n\nArchived: no\n\nREADME:\n# GLM-4-Voice\n\n📄 Report • 🤗 HF Repo • 🤖 Demo • 🐦 Twitter\n \n\nRead this in [English](./README_en.md)\n\nGLM-4-Voice 是智谱 AI 推出的端到端语音模型。GLM-4-Voice 能够直接理解和生成中英文语音，进行实时语音对话，并且能够遵循用户的指令要求改变语音的情感、语调、语速、方言等属性。\n\n## Model Architecture\n\n\nGLM-4-Voice 由三个部分组成：\n* GLM-4-Voice-Tokenizer: 通过在 [Whisper](https://github.com/openai/whisper) 的 Encoder 部分增加 Vector Quantization 并在 ASR 数据上有监督训练，将连续的语音输入转化为离散的 token。每秒音频平均只需要用 12.5 个离散 token 表示。\n* GLM-4-Voice-Decoder: 基于 [CosyVoice](https://github.com/FunAudioLLM/CosyVoice) 的 Flow Matching 模型结构训练的支持流式推理的语音解码器，将离散化的语音 token 转化为连续的语音输出。最少只需要 10 个语音 token 即可开始生成，降低端到端对话延迟。\n* GLM-4-Voice-9B: 在 [GLM-4-9B](https://github.com/THUDM/GLM-4) 的基础上进行语音模态的预训练和对齐，从而能够理解和生成离散化的语音 token。\n\n预训练方面，为了攻克模型在语音模态下的智商和合成表现力两个难关，我们将 Speech2Speech 任务解耦合为“根据用户音频做出文本回复”和“根据文本回复和用户语音合成回复语音”两个任务，并设计两种预训练目标，分别基于文本预训练数据和无监督音频数据合成语音-文本交错数据以适配这两种任务形式。GLM-4-Voice-9B 在 GLM-4-9B 的基座模型基础之上，经过了数百万小时音频和数千亿 token 的音频文本交错数据预训练，拥有很强的音频理解和建模能力。\n\n对齐方面，为了支持高质量的语音对话，我们设计了一套流式思考架构：根据用户语音，GLM-4-Voice 可以流式交替输出文本和语音两个模态的内容，其中语音模态以文本作为参照保证回复内容的高质量，并根据用户的语音指令要求做出相应的声音变化，在最大程度保留语言模型智商的情况下仍然具有端到端建模的能力，同时具备低延迟性，最低只需要输出 20 个 token 便可以合成语音。\n\n## Model List\n\n| Model | Type | Download |\n|:---------------------:|:----------------:|:------------------------------------------------------------------------------------------------------------------------------------------------:|\n| GLM-4-Voice-Tokenizer | Speech Tokenizer | [🤗 Huggingface](https://huggingface.co/THUDM/glm-4-voice-tokenizer) [🤖 ModelScope](https://modelscope.cn/models/ZhipuAI/glm-4-voice-tokenizer) |\n| GLM-4-Voice-9B | Chat Model | "},{"ref":"P22","kind":"page","title":"zai-org/CodeGeeX4 repository metadata","date":"2026-06-11T01:45:58.288131+00:00","date_source":null,"source_url":"https://github.com/zai-org/CodeGeeX4","signal_url":null,"signal_json_url":null,"text":"# zai-org/CodeGeeX4\n\nDescription: CodeGeeX4-ALL-9B, a versatile model for all AI software development scenarios, including code completion, code interpreter, web search, function calling, repository-level Q&A and much more.\n\nLanguage: Python\n\nLicense: Apache-2.0\n\nStars: 2530\n\nForks: 264\n\nOpen issues: 120\n\nCreated: 2024-07-03T11:01:55Z\n\nPushed: 2024-08-25T14:26:16Z\n\nDefault branch: main\n\nFork: no\n\nArchived: no\n\nREADME:\n\n\n\n🏠 Homepage｜🛠 Extensions VS Code, Jetbrains｜🤗 HF Repo | 🪧 HF DEMO\n \n\n[English](./README.md) | [中文](./README_zh.md) | [日本語](./README_ja.md)\n\n# CodeGeeX4: Open Multilingual Code Generation Model\n\nWe introduce CodeGeeX4-ALL-9B, the open-source version of the latest CodeGeeX4 model series. It is a multilingual code generation model continually trained on the [GLM-4-9B](https://github.com/THUDM/GLM-4), significantly enhancing its code generation capabilities. Using a single CodeGeeX4-ALL-9B model, it can support comprehensive functions such as code completion and generation, code interpreter, web search, function call, repository-level code Q&A, covering various scenarios of software development. CodeGeeX4-ALL-9B has achieved highly competitive performance on public benchmarks, such as [BigCodeBench](https://huggingface.co/datasets/bigcode/bigcodebench) and [NaturalCodeBench](https://github.com/THUDM/NaturalCodeBench). It is currently the most powerful code generation model with less than 10B parameters, even surpassing much larger general-purpose models, achieving the best balance in terms of inference speed and model performance.\n\n## Model List\n\n| Model | Type | Seq Length | Download |\n|-------------------|------|------------|-------------------------------------------------------------------------------------------------------"},{"ref":"P23","kind":"page","title":"zai-org/GLM-Edge repository metadata","date":"2026-06-11T01:45:58.135892+00:00","date_source":null,"source_url":"https://github.com/zai-org/GLM-Edge","signal_url":null,"signal_json_url":null,"text":"# zai-org/GLM-Edge\n\nDescription: GLM Series Edge Models\n\nLanguage: Python\n\nLicense: Apache-2.0\n\nStars: 163\n\nForks: 17\n\nOpen issues: 7\n\nCreated: 2024-11-19T03:26:48Z\n\nPushed: 2025-06-12T02:10:02Z\n\nDefault branch: main\n\nFork: no\n\nArchived: no\n\nREADME:\n# GLM-Edge\n\nRead this in [English](README_en.md)\n\n在 🤗 这里 体验 GLM-Edge-1.5B-Chat 端侧模型\n\n在 🤗 这里 或者 🤖 这里 体验 GLM-Edge-V-5B 端侧模型\n\n## 模型介绍\n\n**GLM-Edge** 系列是我们在面向端侧真实落地使用的场景下的一次尝试，由两种尺寸的大语言对话模型和多模态理解模型组成（\n`GLM-Edge-1.5B-Chat`，`GLM-Edge-4B-Chat`，`GLM-Edge-V-2B`，`GLM-Edge-V-5B`）。其中，`1.5B / 2B`模型主要面向手机、车机等平台，\n`4B / 5B` 模型主要面向PC等平台。\n\n基于GLM-4系列的技术积累，我们针对端侧实际部署情况，对模型结构和尺寸做了针对性的调整，以求在模型表现、实机推理效果和落地便利度之间达到平衡。同时，通过与伙伴企业的深入合作和在推理优化上的不懈努力，在一些端侧平台上，GLM-Edge系列模型能以极快的速度运行。\n\n例如，在高通骁龙8 Elite平台上，借助其强大的NPU算力，GLM-Edge通过混合量化方案，1.5B对话模型、2B多模态模型能实现每秒60\ntokens以上的解码速度。在应用投机采样技术之后，两个模型能以峰值每秒100 tokens以上的解码速度运行。**这些推理方案会由我们或合作伙伴后续放出。暂时不会在本仓库提供。**\n模型下载地址：\n\n| Model | HuggingFace Model | GGUF Model |\n|:------------------:|:--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------:|:-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------:|\n| GLM-Edge-1.5B-Chat | [🤗 Huggingface](https://huggingface.co/THUDM/glm-edge-1.5b-chat)
[🤖 ModelScope](https://modelscope.cn/models/ZhipuAI/glm-edge-1.5b-chat)
[🟣 WiseModel](https://wisemodel.cn/models/ZhipuAI/glm-edge-1.5b-chat) | [🤗 Huggingface](https://huggingface.co/THUDM/glm-edge-1.5b-chat-gguf)
[🤖 ModelScope](https://modelscope.cn/models/ZhipuAI/glm-edge-1.5b-chat-gguf)
[🟣 WiseModel](https://wisemodel.cn/models/ZhipuAI/glm-edge-1.5b-chat-gguf) |\n| GLM-Edge-4B-Chat | [🤗 Huggi"},{"ref":"P24","kind":"page","title":"zai-org/MotionBench repository metadata","date":"2026-06-11T01:45:57.878871+00:00","date_source":null,"source_url":"https://github.com/zai-org/MotionBench","signal_url":null,"signal_json_url":null,"text":"# zai-org/MotionBench\n\nDescription: Official code for MotionBench (CVPR 2025)\n\nLanguage: Python\n\nLicense: Apache-2.0\n\nStars: 74\n\nForks: 3\n\nOpen issues: 9\n\nCreated: 2024-11-25T12:03:53Z\n\nPushed: 2025-03-03T06:36:49Z\n\nDefault branch: main\n\nFork: no\n\nArchived: no\n\nREADME:\n# MotionBench: Benchmarking and Improving Fine-grained Video Motion Understanding for Vision Language Models\n\n\n\n \n\n [[🍎 Project Page](https://motion-bench.github.io/)] [[📖 arXiv Paper](https://arxiv.org/abs/2501.02955)] [[📊 Dataset](https://huggingface.co/datasets/THUDM/MotionBench)][[🏆 Leaderboard](https://motion-bench.github.io/#leaderboard)][[🏆 Huggingface Leaderboard](https://huggingface.co/spaces/THUDM/MotionBench)] \n\n \n![](\"./docs/image1.png\") \n \n\nMotionBench aims to guide and motivate the development of more capable video understanding models, emphasizing the importance of fine-grained motion comprehension.\n\n---\n\n## 🔥 News\n\n* **`2025.02.27`** 🎉🎉🎉 MotionBench is accepted by CVPR 2025!!\n* **`2025.01.06`** 🌟🌟🌟 We released MotionBench, a new benchmark for fine-grained motion comprehension!\n\n## Introduction\n\nIn recent years, vision language models (VLMs) have made significant advancements in video understanding. However, a crucial capability — fine-grained motion comprehension — remains under-explored in current benchmarks. To address this gap, we propose MotionBench, a comprehensive evaluation benchmark designed to assess the fine-grained motion comprehension of video understanding models. \n\n### Features\n\n1. **Core Capabilities**: Six core capabilities for fine-grained motion understanding, enabling the evaluation of motion-level perception.\n2. **Diverse Data**: MotionBench collects diverse video from the web, public datasets, and self-synthetic videos generated via Unity3, capturing a broad distribution of real-world\napplication.\n3. **High-Quality Annotations**: Reliable benchmark with meticulous hu"},{"ref":"P25","kind":"page","title":"zai-org/z-ai-sdk-python repository metadata","date":"2026-06-11T01:45:57.554667+00:00","date_source":null,"source_url":"https://github.com/zai-org/z-ai-sdk-python","signal_url":null,"signal_json_url":null,"text":"# zai-org/z-ai-sdk-python\n\nDescription: The official Python SDK for Z.ai's large model open interface, making it easier for developers to call Z.ai's open APIs.\n\nLanguage: Python\n\nLicense: MIT\n\nStars: 110\n\nForks: 28\n\nOpen issues: 8\n\nCreated: 2025-07-01T11:15:24Z\n\nPushed: 2026-06-03T09:59:27Z\n\nDefault branch: main\n\nFork: no\n\nArchived: no\n\nREADME:\n# Z.ai Open Platform Python SDK\n\n[](https://pypi.org/project/zai-sdk/)\n[](https://opensource.org/licenses/MIT)\n[](https://www.python.org/downloads/)\n\n[中文文档](README_CN.md) | English\n\n[Z.ai Open Platform](https://docs.z.ai/) The official Python SDK for Z.ai's large model open interface, making it easier for developers to call Z.ai's open APIs.\n\n## ✨ Core Features\n\n### 🤖 **Chat Completions**\n- **Standard Chat**: Create chat completions with various models including `glm-5.1`\n- **Streaming Support**: Real-time streaming responses for interactive applications\n- **Tool Calling**: Function calling capabilities for enhanced AI interactions\n- **Multimodal Chat**: Image understanding capabilities with vision models\n\n### 🧠 **Embeddings**\n- **Text Embeddings**: Generate high-quality vector embeddings for text\n- **Configurable Dimensions**: Customizable embedding dimensions\n- **Batch Processing**: Support for multiple inputs in a single request\n\n### 🎥 **Video Generation**\n- **Text-to-Video**: Generate videos from text prompts\n- **Image-to-Video**: Create videos from image inputs\n- **Customizable Parameters**: Control quality, duration, FPS, and size\n- **Audio Support**: Optional audio generation for videos\n\n### 🎵 **Audio Processing**\n- **Speech Transcription**: Convert audio files to text\n- **Multiple Formats**: Support for various audio file formats\n\n### 🤝 **Assistant API**\n- **Conversation Management**: Structured conversation handling\n- **Streaming Conversations**: Real-time assistant interactions\n- **Metadata Support**: Rich conversation context and user information\n\n### 🔧 **Advanced Tools**\n- **Web Search**: Integrated web search capabiliti"},{"ref":"P26","kind":"page","title":"zai-org/GLM-V repository metadata","date":"2026-06-11T01:45:57.533775+00:00","date_source":null,"source_url":"https://github.com/zai-org/GLM-V","signal_url":null,"signal_json_url":null,"text":"# zai-org/GLM-V\n\nDescription: GLM-4.6V/4.5V/4.1V-Thinking: Towards Versatile Multimodal Reasoning with Scalable Reinforcement Learning\n\nLanguage: Python\n\nLicense: Apache-2.0\n\nStars: 2326\n\nForks: 171\n\nOpen issues: 12\n\nCreated: 2025-06-28T08:44:06Z\n\nPushed: 2026-05-16T05:42:14Z\n\nDefault branch: main\n\nFork: no\n\nArchived: no\n\nREADME:\n# GLM-V\n\n[中文阅读.](./README_zh.md)\n\n\n \n \n👋 Join our WeChat and Discord communities.\n
\n📖 Check out the GLM-4.6V blog and GLM-4.5V & GLM-4.1V paper.\n
\n📍 Try online or use the API.\n \n\n## Introduction\n\nVision-language models (VLMs) have become a key cornerstone of intelligent systems. As real-world AI tasks grow\nincreasingly complex, VLMs urgently need to enhance reasoning capabilities beyond basic multimodal perception —\nimproving accuracy, comprehensiveness, and intelligence — to enable complex problem solving, long-context understanding,\nand multimodal agents.\n\nThrough our open-source work, we aim to explore the technological frontier together with the community while empowering\nmore developers to create exciting and innovative applications.\n\n**This open-source repository contains our `GLM-4.6V`, `GLM-4.5V` and `GLM-4.1V` series models.** For performance and\ndetails, see [Model Overview](#model-overview). For known issues,\nsee [Fixed and Remaining Issues](#fixed-and-remaining-issues).\n\n## Project Updates\n\n- **News**: `2026/04/02`: We released [GLM-5V-Turbo](https://docs.z.ai/guides/vlm/glm-5v-turbo) \nand [GLM-skills](https://github.com/zai-org/GLM-skills).\n- **News**: `2026/03/28`: We have released multiple GLM-V related Skills, covering several specialized areas\nsuch as GLM-V-Grounding and GLM-V-Prompt-Gen. You are welcome to try them [here](skills).\n- **News**: `2025/11/10`: We released **UI2Code^N**, a"},{"ref":"P27","kind":"page","title":"zai-org/VisionReward repository metadata","date":"2026-06-11T01:45:57.439451+00:00","date_source":null,"source_url":"https://github.com/zai-org/VisionReward","signal_url":null,"signal_json_url":null,"text":"# zai-org/VisionReward\n\nDescription: [AAAI 2026] VisionReward: Fine-Grained Multi-Dimensional Human Preference Learning for Image and Video Generation\n\nLanguage: Python\n\nLicense: Apache-2.0\n\nStars: 407\n\nForks: 14\n\nOpen issues: 19\n\nCreated: 2024-12-12T11:20:46Z\n\nPushed: 2025-03-26T10:07:04Z\n\nDefault branch: main\n\nFork: no\n\nArchived: no\n\nREADME:\n# **VisionReward: Fine-Grained Multi-Dimensional Human Preference Learning for Image and Video Generation**\n\n\n📃 Paper • 🖼 Dataset • 🤗 HF Repo • 🌐 中文博客
\n \n\n**VisionReward** is a fine-grained, multi-dimensional reward model designed to capture human preferences in images and videos. By breaking down subjective judgments into interpretable dimensions with weighted scoring, it delivers precise and comprehensive evaluations. Excelling in video quality prediction, VisionReward sets a new benchmark by thoroughly analyzing dynamic video features. \n\n\n![](\"asset/resource/TopDemo.jpg\") \n \n\n✨ **Key Highlights**:\n- **New reward model& SOTA Performance:** VisionReward, a fine-grained, multi-dimensional, interpretable reward model, achieves **64.0 (Tau)** / **72.1 (Diff)** on **[Video Preference Test Set](https://huggingface.co/datasets/THUDM/VisionRewardDB-Video/viewer/test)**, surpassing **VideoScore** by 17.2% and setting a new **state-of-the-art**! \n- **Fine-Grained Multidimensional Dataset**: A rich, high-quality dataset with detailed annotations drives VisionReward’s precise understanding of human preferences across images and videos.\n- **Multi-objective preference optimization(MPO):** Achives stable and controllable RLHF, enabling the generate model to consider and balance multiple dimensions of human preferences simultaneously.\n\n\n ![](\"asset/resource/OverView.png\") \n \n📄 Arxiv Paper • 🤗 HF Paper • 📊 Dataset\n\n\n## Table of Contents\n\n- [Introduction](#introduction)\n- [Leaderboard](#Leaderboard)\n- [Method](#Method)\n- [How to evaluate on ComplexFuncBench](#how-to-evaluate-on-complexfuncbench)\n- [Citation](#citation)\n\n## Introduction\n\nComplex Function Calling Benchmark (`ComplexFuncBench`) is specillly designed for complex function calling evaluation. The ComplexFuncBench dataset encompass 1,000 complex function calling samples from five aspects: (1) Function calling with **multi-step** in single turn; (2) Function calling with user-provided **constraints**; (3) Function calling that requires **parameter value reasoning** from implicit information; (4) Function calling with **long parameter values** that exceed 500 tokens; and (5) Function calling with **128k long-context** length.\n\n\n\nThe difference between `ComplexFuncBench` and other function calling benchmarks is shown in the following table.\n\n| | Real API Response | Multi-Step | Constraints | Parameter Value Reasoning | Long Parameter Reasoning | Long-Context |\n| :----------------: | :---------------: | :--------: | :---------: | :-----------------------: | :----------------------: | :----------: |\n| API-Bench | ❌ | ❌ | ❌ | ❌ | ❌ | ❌ |\n| ToolBench | ✅ | ✅ | ❌ | ❌ | ❌ | ❌ |\n| T-Eval | ✅ | ✅ | ❌ | ❌ | ❌ | ❌ |\n| BFCL | ❌ | ✅ | ❌ | ❌ | ✅ | ✅ |\n| Tool Sandbox | ❌ | ✅ | ❌ | ❌ | ❌ | ❌ |\n| `ComplexFuncBench` | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ |\n\n## Leaderboard\n\n| Model | Overall Success Rate | Overall Call Acc. | Completeness | Correctness |\n| :--------------------------- | :------------------: | :-------"},{"ref":"E1","kind":"event","title":"zai-org/GLM-5","date":"2026-02-11T04:55:46+00:00","date_source":"source","source_url":"https://huggingface.co/zai-org/GLM-5","signal_url":"https://onlylabs.fyi/signals/72ee3bf6-586a-49e7-8f29-133f219c9fb7","signal_json_url":"https://onlylabs.fyi/signals/72ee3bf6-586a-49e7-8f29-133f219c9fb7/signal.json","text":"model_released · zai-org/GLM-5 · signal_desk=releases · occurred_at=2026-02-11T04:55:46+00:00 · url=https://huggingface.co/zai-org/GLM-5 · hf_downloads=102786 · hf_likes=2093 · hf_params=753864139008 · pipeline=text-generation · license=mit"},{"ref":"E2","kind":"event","title":"zai-org/GLM-4.7","date":"2025-12-22T07:45:52+00:00","date_source":"source","source_url":"https://huggingface.co/zai-org/GLM-4.7","signal_url":"https://onlylabs.fyi/signals/04722f66-05e2-4ba8-862c-2ba6fba5b149","signal_json_url":"https://onlylabs.fyi/signals/04722f66-05e2-4ba8-862c-2ba6fba5b149/signal.json","text":"model_released · zai-org/GLM-4.7 · signal_desk=releases · occurred_at=2025-12-22T07:45:52+00:00 · url=https://huggingface.co/zai-org/GLM-4.7 · hf_downloads=66288 · hf_likes=2041 · hf_params=358337791296 · pipeline=text-generation · license=mit"},{"ref":"E3","kind":"event","title":"zai-org/GLM-OCR","date":"2026-01-30T04:24:21+00:00","date_source":"source","source_url":"https://huggingface.co/zai-org/GLM-OCR","signal_url":"https://onlylabs.fyi/signals/8ed36a7c-374b-4509-9f39-7362837a795c","signal_json_url":"https://onlylabs.fyi/signals/8ed36a7c-374b-4509-9f39-7362837a795c/signal.json","text":"model_released · zai-org/GLM-OCR · signal_desk=releases · occurred_at=2026-01-30T04:24:21+00:00 · url=https://huggingface.co/zai-org/GLM-OCR · hf_downloads=3607869 · hf_likes=1820 · hf_params=1325258240 · pipeline=image-text-to-text · license=mit"},{"ref":"E4","kind":"event","title":"zai-org/GLM-4.7-Flash","date":"2026-01-19T06:28:10+00:00","date_source":"source","source_url":"https://huggingface.co/zai-org/GLM-4.7-Flash","signal_url":"https://onlylabs.fyi/signals/4df2cc6a-f8f6-4197-9766-c8ede6451b82","signal_json_url":"https://onlylabs.fyi/signals/4df2cc6a-f8f6-4197-9766-c8ede6451b82/signal.json","text":"model_released · zai-org/GLM-4.7-Flash · signal_desk=releases · occurred_at=2026-01-19T06:28:10+00:00 · url=https://huggingface.co/zai-org/GLM-4.7-Flash · hf_downloads=1100933 · hf_likes=1745 · hf_params=31221488576 · pipeline=text-generation · license=mit"},{"ref":"E5","kind":"event","title":"zai-org/GLM-5.1","date":"2026-04-03T09:28:47+00:00","date_source":"source","source_url":"https://huggingface.co/zai-org/GLM-5.1","signal_url":"https://onlylabs.fyi/signals/f4fb4df8-c759-44a5-bc98-bac22072971f","signal_json_url":"https://onlylabs.fyi/signals/f4fb4df8-c759-44a5-bc98-bac22072971f/signal.json","text":"model_released · zai-org/GLM-5.1 · signal_desk=releases · occurred_at=2026-04-03T09:28:47+00:00 · url=https://huggingface.co/zai-org/GLM-5.1 · hf_downloads=123470 · hf_likes=1754 · hf_params=753864139008 · pipeline=text-generation · license=mit"},{"ref":"E6","kind":"event","title":"zai-org/GLM-OCR","date":"2026-02-02T12:59:43+00:00","date_source":"source","source_url":"https://github.com/zai-org/GLM-OCR","signal_url":"https://onlylabs.fyi/signals/96b785f6-e53f-411c-8db5-de694472d179","signal_json_url":"https://onlylabs.fyi/signals/96b785f6-e53f-411c-8db5-de694472d179/signal.json","text":"repo_new · zai-org/GLM-OCR · signal_desk=repos · occurred_at=2026-02-02T12:59:43+00:00 · url=https://github.com/zai-org/GLM-OCR · stars=6935 · hn=302 points/75 comments · raw={\"repo\":\"zai-org/GLM-OCR\",\"description\":\"GLM-OCR: Accurate × Fast × Comprehensive\",\"language\":\"Python\"}"},{"ref":"E7","kind":"event","title":"zai-org/GLM-4.5","date":"2025-07-20T03:25:36+00:00","date_source":"source","source_url":"https://huggingface.co/zai-org/GLM-4.5","signal_url":"https://onlylabs.fyi/signals/215ba15c-649f-49a6-b687-455309a9c640","signal_json_url":"https://onlylabs.fyi/signals/215ba15c-649f-49a6-b687-455309a9c640/signal.json","text":"model_released · zai-org/GLM-4.5 · signal_desk=releases · occurred_at=2025-07-20T03:25:36+00:00 · url=https://huggingface.co/zai-org/GLM-4.5 · hf_downloads=176737 · hf_likes=1402 · hf_params=358337791296 · pipeline=text-generation · license=mit"},{"ref":"E8","kind":"event","title":"zai-org/GLM-4.6","date":"2025-09-29T18:22:51+00:00","date_source":"source","source_url":"https://huggingface.co/zai-org/GLM-4.6","signal_url":"https://onlylabs.fyi/signals/fddefdbd-9857-4445-accd-5de1c68743bc","signal_json_url":"https://onlylabs.fyi/signals/fddefdbd-9857-4445-accd-5de1c68743bc/signal.json","text":"model_released · zai-org/GLM-4.6 · signal_desk=releases · occurred_at=2025-09-29T18:22:51+00:00 · url=https://huggingface.co/zai-org/GLM-4.6 · hf_downloads=13553 · hf_likes=1227 · hf_params=356785898816 · pipeline=text-generation · license=mit"},{"ref":"E9","kind":"event","title":"zai-org/GLM-Image","date":"2026-01-08T09:39:56+00:00","date_source":"source","source_url":"https://huggingface.co/zai-org/GLM-Image","signal_url":"https://onlylabs.fyi/signals/63a74604-38af-4f72-a107-9ed3b5efa558","signal_json_url":"https://onlylabs.fyi/signals/63a74604-38af-4f72-a107-9ed3b5efa558/signal.json","text":"model_released · zai-org/GLM-Image · signal_desk=releases · occurred_at=2026-01-08T09:39:56+00:00 · url=https://huggingface.co/zai-org/GLM-Image · hf_downloads=7925 · hf_likes=1073 · pipeline=text-to-image · license=mit"},{"ref":"E10","kind":"event","title":"zai-org/GLM-4.1V-9B-Thinking","date":"2025-06-28T14:24:10+00:00","date_source":"source","source_url":"https://huggingface.co/zai-org/GLM-4.1V-9B-Thinking","signal_url":"https://onlylabs.fyi/signals/bc302628-a073-47dc-9f70-7a3305ca9f56","signal_json_url":"https://onlylabs.fyi/signals/bc302628-a073-47dc-9f70-7a3305ca9f56/signal.json","text":"model_released · zai-org/GLM-4.1V-9B-Thinking · signal_desk=releases · occurred_at=2025-06-28T14:24:10+00:00 · url=https://huggingface.co/zai-org/GLM-4.1V-9B-Thinking · hf_downloads=461239 · hf_likes=776 · hf_params=10292777472 · pipeline=image-text-to-text · license=mit · raw={\"derived_reason\":\"first-party-finetune\"}"},{"ref":"E11","kind":"event","title":"zai-org/GLM-4.5V","date":"2025-08-10T13:55:30+00:00","date_source":"source","source_url":"https://huggingface.co/zai-org/GLM-4.5V","signal_url":"https://onlylabs.fyi/signals/662ae0ee-c232-4ca0-91e3-2b36d37fb07d","signal_json_url":"https://onlylabs.fyi/signals/662ae0ee-c232-4ca0-91e3-2b36d37fb07d/signal.json","text":"model_released · zai-org/GLM-4.5V · signal_desk=releases · occurred_at=2025-08-10T13:55:30+00:00 · url=https://huggingface.co/zai-org/GLM-4.5V · hf_downloads=167014 · hf_likes=718 · hf_params=107710933120 · pipeline=image-text-to-text · license=mit · raw={\"derived_reason\":\"first-party-finetune\"}"},{"ref":"E12","kind":"event","title":"zai-org/GLM-4.5-Air","date":"2025-07-20T03:25:55+00:00","date_source":"source","source_url":"https://huggingface.co/zai-org/GLM-4.5-Air","signal_url":"https://onlylabs.fyi/signals/8a24013c-90c7-4b04-98c7-fd4c65cef757","signal_json_url":"https://onlylabs.fyi/signals/8a24013c-90c7-4b04-98c7-fd4c65cef757/signal.json","text":"model_released · zai-org/GLM-4.5-Air · signal_desk=releases · occurred_at=2025-07-20T03:25:55+00:00 · url=https://huggingface.co/zai-org/GLM-4.5-Air · hf_downloads=319702 · hf_likes=608 · hf_params=110468824832 · pipeline=text-generation · license=mit"},{"ref":"E13","kind":"event","title":"zai-org/GLM-4.6V-Flash","date":"2025-12-07T06:30:04+00:00","date_source":"source","source_url":"https://huggingface.co/zai-org/GLM-4.6V-Flash","signal_url":"https://onlylabs.fyi/signals/7d186301-8e5c-44c2-89e3-647fe696d67a","signal_json_url":"https://onlylabs.fyi/signals/7d186301-8e5c-44c2-89e3-647fe696d67a/signal.json","text":"model_released · zai-org/GLM-4.6V-Flash · signal_desk=releases · occurred_at=2025-12-07T06:30:04+00:00 · url=https://huggingface.co/zai-org/GLM-4.6V-Flash · hf_downloads=57876 · hf_likes=609 · hf_params=10292777472 · pipeline=image-text-to-text · license=mit"},{"ref":"E14","kind":"event","title":"zai-org/AutoGLM-Phone-9B","date":"2025-12-08T08:20:34+00:00","date_source":"source","source_url":"https://huggingface.co/zai-org/AutoGLM-Phone-9B","signal_url":"https://onlylabs.fyi/signals/80c71616-6238-4b7c-b172-7e11b7474c53","signal_json_url":"https://onlylabs.fyi/signals/80c71616-6238-4b7c-b172-7e11b7474c53/signal.json","text":"model_released · zai-org/AutoGLM-Phone-9B · signal_desk=releases · occurred_at=2025-12-08T08:20:34+00:00 · url=https://huggingface.co/zai-org/AutoGLM-Phone-9B · hf_downloads=677 · hf_likes=437 · hf_params=934400 · pipeline=image-text-to-text · license=mit · raw={\"derived_reason\":\"first-party-finetune\"}"},{"ref":"E15","kind":"event","title":"zai-org/GLM-4.6V","date":"2025-12-07T07:20:45+00:00","date_source":"source","source_url":"https://huggingface.co/zai-org/GLM-4.6V","signal_url":"https://onlylabs.fyi/signals/002914ac-5247-47e5-90c0-3d99a4be657b","signal_json_url":"https://onlylabs.fyi/signals/002914ac-5247-47e5-90c0-3d99a4be657b/signal.json","text":"model_released · zai-org/GLM-4.6V · signal_desk=releases · occurred_at=2025-12-07T07:20:45+00:00 · url=https://huggingface.co/zai-org/GLM-4.6V · hf_downloads=2987 · hf_likes=392 · hf_params=107710933120 · pipeline=image-text-to-text · license=mit"},{"ref":"E16","kind":"event","title":"zai-org/GLM-ASR-Nano-2512","date":"2025-12-09T09:07:41+00:00","date_source":"source","source_url":"https://huggingface.co/zai-org/GLM-ASR-Nano-2512","signal_url":"https://onlylabs.fyi/signals/2addea5d-e5ad-4400-9692-6dcb25cade09","signal_json_url":"https://onlylabs.fyi/signals/2addea5d-e5ad-4400-9692-6dcb25cade09/signal.json","text":"model_released · zai-org/GLM-ASR-Nano-2512 · signal_desk=releases · occurred_at=2025-12-09T09:07:41+00:00 · url=https://huggingface.co/zai-org/GLM-ASR-Nano-2512 · hf_downloads=118352 · hf_likes=370 · hf_params=2257843200 · pipeline=automatic-speech-recognition · license=mit"},{"ref":"E17","kind":"event","title":"zai-org/GLM-TTS","date":"2025-12-10T09:59:48+00:00","date_source":"source","source_url":"https://huggingface.co/zai-org/GLM-TTS","signal_url":"https://onlylabs.fyi/signals/1550a4df-6582-44e0-846d-c01934c649f9","signal_json_url":"https://onlylabs.fyi/signals/1550a4df-6582-44e0-846d-c01934c649f9/signal.json","text":"model_released · zai-org/GLM-TTS · signal_desk=releases · occurred_at=2025-12-10T09:59:48+00:00 · url=https://huggingface.co/zai-org/GLM-TTS · hf_downloads=314 · hf_likes=338 · pipeline=text-to-speech · license=mit"},{"ref":"E18","kind":"event","title":"zai-org/AutoGLM-Phone-9B-Multilingual","date":"2025-12-09T04:16:21+00:00","date_source":"source","source_url":"https://huggingface.co/zai-org/AutoGLM-Phone-9B-Multilingual","signal_url":"https://onlylabs.fyi/signals/886bc9f2-dc7b-4935-ae5e-aa1ce2bbe3b1","signal_json_url":"https://onlylabs.fyi/signals/886bc9f2-dc7b-4935-ae5e-aa1ce2bbe3b1/signal.json","text":"model_released · zai-org/AutoGLM-Phone-9B-Multilingual · signal_desk=releases · occurred_at=2025-12-09T04:16:21+00:00 · url=https://huggingface.co/zai-org/AutoGLM-Phone-9B-Multilingual · hf_downloads=658 · hf_likes=234 · hf_params=934400 · pipeline=image-text-to-text · license=mit · raw={\"derived_reason\":\"first-party-finetune\"}"},{"ref":"E19","kind":"event","title":"zai-org/ChatGLM-6B","date":"2023-03-13T12:00:18+00:00","date_source":"source","source_url":"https://github.com/zai-org/ChatGLM-6B","signal_url":"https://onlylabs.fyi/signals/d48bf6d2-05da-4c99-b02b-ba379621db54","signal_json_url":"https://onlylabs.fyi/signals/d48bf6d2-05da-4c99-b02b-ba379621db54/signal.json","text":"repo_new · zai-org/ChatGLM-6B · signal_desk=repos · occurred_at=2023-03-13T12:00:18+00:00 · url=https://github.com/zai-org/ChatGLM-6B · stars=41047 · raw={\"repo\":\"zai-org/ChatGLM-6B\",\"description\":\"ChatGLM-6B: An Open Bilingual Dialogue Language Model | 开源双语对话语言模型\",\"language\":\"Python\"}"},{"ref":"E20","kind":"event","title":"zai-org/Open-AutoGLM","date":"2025-12-08T09:23:44+00:00","date_source":"source","source_url":"https://github.com/zai-org/Open-AutoGLM","signal_url":"https://onlylabs.fyi/signals/fe7d57d8-d5cf-461e-9a73-256085f50a1c","signal_json_url":"https://onlylabs.fyi/signals/fe7d57d8-d5cf-461e-9a73-256085f50a1c/signal.json","text":"repo_new · zai-org/Open-AutoGLM · signal_desk=repos · occurred_at=2025-12-08T09:23:44+00:00 · url=https://github.com/zai-org/Open-AutoGLM · stars=25486 · hn=2 points/0 comments · raw={\"repo\":\"zai-org/Open-AutoGLM\",\"description\":\"An Open Phone Agent Model & Framework. Unlocking the AI Phone for Everyone\",\"language\":\"Python\"}"},{"ref":"E21","kind":"event","title":"zai-org/SCAIL-2","date":"2026-06-09T07:18:27+00:00","date_source":"source","source_url":"https://huggingface.co/zai-org/SCAIL-2","signal_url":"https://onlylabs.fyi/signals/868269e7-f86e-47ba-bdf0-df7043ea921b","signal_json_url":"https://onlylabs.fyi/signals/868269e7-f86e-47ba-bdf0-df7043ea921b/signal.json","text":"model_released · zai-org/SCAIL-2 · signal_desk=releases · occurred_at=2026-06-09T07:18:27+00:00 · url=https://huggingface.co/zai-org/SCAIL-2 · hf_likes=90 · pipeline=image-to-video · license=mit"},{"ref":"E22","kind":"event","title":"zai-org/GLM-Z1-Rumination-32B-0414","date":"2025-04-13T12:06:04+00:00","date_source":"source","source_url":"https://huggingface.co/zai-org/GLM-Z1-Rumination-32B-0414","signal_url":"https://onlylabs.fyi/signals/578a3d75-074b-4a32-bf9e-a88dd6001710","signal_json_url":"https://onlylabs.fyi/signals/578a3d75-074b-4a32-bf9e-a88dd6001710/signal.json","text":"model_released · zai-org/GLM-Z1-Rumination-32B-0414 · signal_desk=releases · occurred_at=2025-04-13T12:06:04+00:00 · url=https://huggingface.co/zai-org/GLM-Z1-Rumination-32B-0414 · hf_downloads=181 · hf_likes=118 · hf_params=33141749760 · pipeline=text-generation · license=mit"},{"ref":"E23","kind":"event","title":"zai-org/SCAIL-Preview","date":"2025-12-08T12:40:27+00:00","date_source":"source","source_url":"https://huggingface.co/zai-org/SCAIL-Preview","signal_url":"https://onlylabs.fyi/signals/79dd192e-4c67-474d-b7f1-9d1ea8c12950","signal_json_url":"https://onlylabs.fyi/signals/79dd192e-4c67-474d-b7f1-9d1ea8c12950/signal.json","text":"model_released · zai-org/SCAIL-Preview · signal_desk=releases · occurred_at=2025-12-08T12:40:27+00:00 · url=https://huggingface.co/zai-org/SCAIL-Preview · hf_likes=111 · license=mit"},{"ref":"E24","kind":"event","title":"zai-org/RealVideo","date":"2025-12-11T08:04:35+00:00","date_source":"source","source_url":"https://huggingface.co/zai-org/RealVideo","signal_url":"https://onlylabs.fyi/signals/35a8289c-ba50-433f-8b0b-c9b5be5a4618","signal_json_url":"https://onlylabs.fyi/signals/35a8289c-ba50-433f-8b0b-c9b5be5a4618/signal.json","text":"model_released · zai-org/RealVideo · signal_desk=releases · occurred_at=2025-12-11T08:04:35+00:00 · url=https://huggingface.co/zai-org/RealVideo · hf_likes=104 · pipeline=any-to-any · license=mit · raw={\"derived_reason\":\"first-party-finetune\"}"},{"ref":"E25","kind":"event","title":"zai-org/ChatGLM2-6B","date":"2023-06-24T06:21:34+00:00","date_source":"source","source_url":"https://github.com/zai-org/ChatGLM2-6B","signal_url":"https://onlylabs.fyi/signals/f5c0af47-7ec5-4126-b5cb-b00eb4aa3eb5","signal_json_url":"https://onlylabs.fyi/signals/f5c0af47-7ec5-4126-b5cb-b00eb4aa3eb5/signal.json","text":"repo_new · zai-org/ChatGLM2-6B · signal_desk=repos · occurred_at=2023-06-24T06:21:34+00:00 · url=https://github.com/zai-org/ChatGLM2-6B · stars=15568 · raw={\"repo\":\"zai-org/ChatGLM2-6B\",\"description\":\"ChatGLM2-6B: An Open Bilingual Chat LLM | 开源双语对话语言模型\",\"language\":\"Python\"}"},{"ref":"E26","kind":"event","title":"zai-org/Glyph","date":"2025-10-25T06:19:07+00:00","date_source":"source","source_url":"https://huggingface.co/zai-org/Glyph","signal_url":"https://onlylabs.fyi/signals/6c3899af-9e45-4ca1-b127-b42c4365bccb","signal_json_url":"https://onlylabs.fyi/signals/6c3899af-9e45-4ca1-b127-b42c4365bccb/signal.json","text":"model_released · zai-org/Glyph · signal_desk=releases · occurred_at=2025-10-25T06:19:07+00:00 · url=https://huggingface.co/zai-org/Glyph · hf_downloads=891 · hf_likes=73 · hf_params=10292777472 · pipeline=image-text-to-text · license=mit · raw={\"derived_reason\":\"first-party-finetune\"}"},{"ref":"E27","kind":"event","title":"zai-org/ChatGLM3","date":"2023-10-26T06:22:47+00:00","date_source":"source","source_url":"https://github.com/zai-org/ChatGLM3","signal_url":"https://onlylabs.fyi/signals/b874a054-71e6-48ab-b2e5-f193ec606c57","signal_json_url":"https://onlylabs.fyi/signals/b874a054-71e6-48ab-b2e5-f193ec606c57/signal.json","text":"repo_new · zai-org/ChatGLM3 · signal_desk=repos · occurred_at=2023-10-26T06:22:47+00:00 · url=https://github.com/zai-org/ChatGLM3 · stars=13679 · raw={\"repo\":\"zai-org/ChatGLM3\",\"description\":\"ChatGLM3 series: Open Bilingual Chat LLMs | 开源双语对话语言模型\",\"language\":\"Python\"}"},{"ref":"E28","kind":"event","title":"zai-org/GLM-4.1V-9B-Base","date":"2025-06-28T14:23:46+00:00","date_source":"source","source_url":"https://huggingface.co/zai-org/GLM-4.1V-9B-Base","signal_url":"https://onlylabs.fyi/signals/d6905e2a-b787-4bc3-a827-1f9a08eb0b0c","signal_json_url":"https://onlylabs.fyi/signals/d6905e2a-b787-4bc3-a827-1f9a08eb0b0c/signal.json","text":"model_released · zai-org/GLM-4.1V-9B-Base · signal_desk=releases · occurred_at=2025-06-28T14:23:46+00:00 · url=https://huggingface.co/zai-org/GLM-4.1V-9B-Base · hf_downloads=2085 · hf_likes=66 · hf_params=10292777472 · pipeline=image-text-to-text · license=mit · raw={\"derived_reason\":\"first-party-finetune\"}"},{"ref":"E29","kind":"event","title":"zai-org/CogVideo","date":"2022-05-29T06:46:18+00:00","date_source":"source","source_url":"https://github.com/zai-org/CogVideo","signal_url":"https://onlylabs.fyi/signals/2c95c9bb-86b9-4774-bb11-571611012cd9","signal_json_url":"https://onlylabs.fyi/signals/2c95c9bb-86b9-4774-bb11-571611012cd9/signal.json","text":"repo_new · zai-org/CogVideo · signal_desk=repos · occurred_at=2022-05-29T06:46:18+00:00 · url=https://github.com/zai-org/CogVideo · stars=12775 · raw={\"repo\":\"zai-org/CogVideo\",\"description\":\"text and image to video generation: CogVideoX (2024) and CogVideo (ICLR 2023)\",\"language\":\"Python\"}"},{"ref":"E30","kind":"event","title":"zai-org/GLM-4.5-Base","date":"2025-07-20T05:14:19+00:00","date_source":"source","source_url":"https://huggingface.co/zai-org/GLM-4.5-Base","signal_url":"https://onlylabs.fyi/signals/1220b8c8-3171-4bd4-8ed1-a67d5caad1f4","signal_json_url":"https://onlylabs.fyi/signals/1220b8c8-3171-4bd4-8ed1-a67d5caad1f4/signal.json","text":"model_released · zai-org/GLM-4.5-Base · signal_desk=releases · occurred_at=2025-07-20T05:14:19+00:00 · url=https://huggingface.co/zai-org/GLM-4.5-Base · hf_downloads=312 · hf_likes=60 · hf_params=358337791296 · pipeline=text-generation · license=mit"},{"ref":"E31","kind":"event","title":"zai-org/GLM-4.5-Air-Base","date":"2025-07-20T03:24:43+00:00","date_source":"source","source_url":"https://huggingface.co/zai-org/GLM-4.5-Air-Base","signal_url":"https://onlylabs.fyi/signals/486c9814-f670-4d32-88fc-243fd64d6bbd","signal_json_url":"https://onlylabs.fyi/signals/486c9814-f670-4d32-88fc-243fd64d6bbd/signal.json","text":"model_released · zai-org/GLM-4.5-Air-Base · signal_desk=releases · occurred_at=2025-07-20T03:24:43+00:00 · url=https://huggingface.co/zai-org/GLM-4.5-Air-Base · hf_downloads=1167 · hf_likes=46 · hf_params=110468824832 · pipeline=text-generation · license=mit"},{"ref":"E32","kind":"event","title":"zai-org/CodeGeeX","date":"2022-09-17T14:06:29+00:00","date_source":"source","source_url":"https://github.com/zai-org/CodeGeeX","signal_url":"https://onlylabs.fyi/signals/92b0330d-2543-4a51-ad0c-1b40108650f7","signal_json_url":"https://onlylabs.fyi/signals/92b0330d-2543-4a51-ad0c-1b40108650f7/signal.json","text":"repo_new · zai-org/CodeGeeX · signal_desk=repos · occurred_at=2022-09-17T14:06:29+00:00 · url=https://github.com/zai-org/CodeGeeX · stars=8791 · raw={\"repo\":\"zai-org/CodeGeeX\",\"description\":\"CodeGeeX: An Open Multilingual Code Generation Model (KDD 2023)\",\"language\":\"Python\"}"},{"ref":"E33","kind":"event","title":"zai-org/SCAIL-2","date":"2026-05-28T11:38:02+00:00","date_source":"source","source_url":"https://github.com/zai-org/SCAIL-2","signal_url":"https://onlylabs.fyi/signals/48759bf3-02e0-43d9-83c5-0fbb4f8168aa","signal_json_url":"https://onlylabs.fyi/signals/48759bf3-02e0-43d9-83c5-0fbb4f8168aa/signal.json","text":"repo_new · zai-org/SCAIL-2 · signal_desk=repos · occurred_at=2026-05-28T11:38:02+00:00 · url=https://github.com/zai-org/SCAIL-2 · stars=191 · raw={\"repo\":\"zai-org/SCAIL-2\",\"description\":\"Official Implementation of SCAIL-2: Unifying Controlled Character Animation with End-to-end In-Context Conditioning\",\"language\":\"Python\"}"},{"ref":"E34","kind":"event","title":"zai-org/GLM-130B","date":"2022-08-03T20:21:58+00:00","date_source":"source","source_url":"https://github.com/zai-org/GLM-130B","signal_url":"https://onlylabs.fyi/signals/43f65f4a-b053-46b0-a0e6-dc64ff400a6d","signal_json_url":"https://onlylabs.fyi/signals/43f65f4a-b053-46b0-a0e6-dc64ff400a6d/signal.json","text":"repo_new · zai-org/GLM-130B · signal_desk=repos · occurred_at=2022-08-03T20:21:58+00:00 · url=https://github.com/zai-org/GLM-130B · stars=7651 · raw={\"repo\":\"zai-org/GLM-130B\",\"description\":\"GLM-130B: An Open Bilingual Pre-Trained Model (ICLR 2023)\",\"language\":\"Python\"}"},{"ref":"E35","kind":"event","title":"zai-org/CodeGeeX2","date":"2023-07-23T18:26:53+00:00","date_source":"source","source_url":"https://github.com/zai-org/CodeGeeX2","signal_url":"https://onlylabs.fyi/signals/5fff96c1-bdc7-4b22-a759-2ef7afdcf0e4","signal_json_url":"https://onlylabs.fyi/signals/5fff96c1-bdc7-4b22-a759-2ef7afdcf0e4/signal.json","text":"repo_new · zai-org/CodeGeeX2 · signal_desk=repos · occurred_at=2023-07-23T18:26:53+00:00 · url=https://github.com/zai-org/CodeGeeX2 · stars=7552 · raw={\"repo\":\"zai-org/CodeGeeX2\",\"description\":\"CodeGeeX2: A More Powerful Multilingual Code Generation Model\",\"language\":\"Python\"}"},{"ref":"E36","kind":"event","title":"zai-org/GLM-4","date":"2024-05-15T05:17:08+00:00","date_source":"source","source_url":"https://github.com/zai-org/GLM-4","signal_url":"https://onlylabs.fyi/signals/e27f1ae7-4209-4932-8a8c-262c50be3dc9","signal_json_url":"https://onlylabs.fyi/signals/e27f1ae7-4209-4932-8a8c-262c50be3dc9/signal.json","text":"repo_new · zai-org/GLM-4 · signal_desk=repos · occurred_at=2024-05-15T05:17:08+00:00 · url=https://github.com/zai-org/GLM-4 · stars=7064 · raw={\"repo\":\"zai-org/GLM-4\",\"description\":\"GLM-4 series: Open Multilingual Multimodal Chat LMs | 开源多语言多模态对话模型\",\"language\":\"Python\"}"},{"ref":"E37","kind":"event","title":"zai-org/CogVLM","date":"2023-09-18T02:12:50+00:00","date_source":"source","source_url":"https://github.com/zai-org/CogVLM","signal_url":"https://onlylabs.fyi/signals/78f58efd-8ac8-4996-aba3-723cfef3dbc7","signal_json_url":"https://onlylabs.fyi/signals/78f58efd-8ac8-4996-aba3-723cfef3dbc7/signal.json","text":"repo_new · zai-org/CogVLM · signal_desk=repos · occurred_at=2023-09-18T02:12:50+00:00 · url=https://github.com/zai-org/CogVLM · stars=6739 · raw={\"repo\":\"zai-org/CogVLM\",\"description\":\"a state-of-the-art-level open visual language model | 多模态预训练模型\",\"language\":\"Python\"}"},{"ref":"E38","kind":"event","title":"zai-org/Synapse","date":"2026-05-13T11:06:53+00:00","date_source":"source","source_url":"https://github.com/zai-org/Synapse","signal_url":"https://onlylabs.fyi/signals/d6c9e002-b775-427b-ad28-972e3ab76500","signal_json_url":"https://onlylabs.fyi/signals/d6c9e002-b775-427b-ad28-972e3ab76500/signal.json","text":"repo_new · zai-org/Synapse · signal_desk=repos · occurred_at=2026-05-13T11:06:53+00:00 · url=https://github.com/zai-org/Synapse · stars=46 · raw={\"repo\":\"zai-org/Synapse\",\"description\":\"Self-hosted AI workspace with shareable AI teammates, shared conversations, memory, and governed access to plugins, MCP tools, and local devices.\",\"language\":\"TypeScript\"}"},{"ref":"E39","kind":"event","title":"zai-org/UI2Code_N","date":"2025-11-11T11:18:32+00:00","date_source":"source","source_url":"https://huggingface.co/zai-org/UI2Code_N","signal_url":"https://onlylabs.fyi/signals/84f04b6d-f76c-406e-a02a-0a5932c824a7","signal_json_url":"https://onlylabs.fyi/signals/84f04b6d-f76c-406e-a02a-0a5932c824a7/signal.json","text":"model_released · zai-org/UI2Code_N · signal_desk=releases · occurred_at=2025-11-11T11:18:32+00:00 · url=https://huggingface.co/zai-org/UI2Code_N · hf_downloads=225 · hf_likes=23 · pipeline=image-text-to-text · license=mit · raw={\"derived_reason\":\"first-party-finetune\"}"},{"ref":"E40","kind":"event","title":"zai-org/ImageMining","date":"2026-04-28T10:33:43+00:00","date_source":"source","source_url":"https://github.com/zai-org/ImageMining","signal_url":"https://onlylabs.fyi/signals/1bc1e9fc-2c53-4c6f-8c88-f46d8ae7f504","signal_json_url":"https://onlylabs.fyi/signals/1bc1e9fc-2c53-4c6f-8c88-f46d8ae7f504/signal.json","text":"repo_new · zai-org/ImageMining · signal_desk=repos · occurred_at=2026-04-28T10:33:43+00:00 · url=https://github.com/zai-org/ImageMining · stars=10 · raw={\"repo\":\"zai-org/ImageMining\"}"},{"ref":"E41","kind":"event","title":"zai-org/GLM-4.5","date":"2025-07-20T09:24:09+00:00","date_source":"source","source_url":"https://github.com/zai-org/GLM-4.5","signal_url":"https://onlylabs.fyi/signals/a4d678b4-e41d-48ac-9bd1-2bcbac3a88be","signal_json_url":"https://onlylabs.fyi/signals/a4d678b4-e41d-48ac-9bd1-2bcbac3a88be/signal.json","text":"repo_new · zai-org/GLM-4.5 · signal_desk=repos · occurred_at=2025-07-20T09:24:09+00:00 · url=https://github.com/zai-org/GLM-4.5 · stars=4353 · raw={\"repo\":\"zai-org/GLM-4.5\",\"description\":\"GLM-4.5: Agentic, Reasoning, and Coding (ARC) Foundation Models\",\"language\":\"Python\"}"},{"ref":"E42","kind":"event","title":"zai-org/VisualGLM-6B","date":"2023-04-23T09:36:56+00:00","date_source":"source","source_url":"https://github.com/zai-org/VisualGLM-6B","signal_url":"https://onlylabs.fyi/signals/ffaab0c1-97c6-4bd7-9254-a16229c22eb5","signal_json_url":"https://onlylabs.fyi/signals/ffaab0c1-97c6-4bd7-9254-a16229c22eb5/signal.json","text":"repo_new · zai-org/VisualGLM-6B · signal_desk=repos · occurred_at=2023-04-23T09:36:56+00:00 · url=https://github.com/zai-org/VisualGLM-6B · stars=4159 · raw={\"repo\":\"zai-org/VisualGLM-6B\",\"description\":\"Chinese and English multimodal conversational language model | 多模态中英双语对话语言模型\",\"language\":\"Python\"}"},{"ref":"E43","kind":"event","title":"zai-org/WebVIA-Agent","date":"2025-11-12T04:39:14+00:00","date_source":"source","source_url":"https://huggingface.co/zai-org/WebVIA-Agent","signal_url":"https://onlylabs.fyi/signals/8c77f8d3-0796-4cbd-9363-14cd0e1a7c64","signal_json_url":"https://onlylabs.fyi/signals/8c77f8d3-0796-4cbd-9363-14cd0e1a7c64/signal.json","text":"model_released · zai-org/WebVIA-Agent · signal_desk=releases · occurred_at=2025-11-12T04:39:14+00:00 · url=https://huggingface.co/zai-org/WebVIA-Agent · hf_downloads=92 · hf_likes=20 · hf_params=10292777472 · pipeline=image-text-to-text · license=mit · raw={\"derived_reason\":\"first-party-finetune\"}"},{"ref":"E44","kind":"event","title":"zai-org/Kaleido-14B-S2V","date":"2025-10-27T08:31:26+00:00","date_source":"source","source_url":"https://huggingface.co/zai-org/Kaleido-14B-S2V","signal_url":"https://onlylabs.fyi/signals/aacda9a0-d80c-4f4f-9e5d-48471039f783","signal_json_url":"https://onlylabs.fyi/signals/aacda9a0-d80c-4f4f-9e5d-48471039f783/signal.json","text":"model_released · zai-org/Kaleido-14B-S2V · signal_desk=releases · occurred_at=2025-10-27T08:31:26+00:00 · url=https://huggingface.co/zai-org/Kaleido-14B-S2V · hf_likes=19 · license=mit · raw={\"derived_reason\":\"first-party-finetune\"}"},{"ref":"E45","kind":"event","title":"zai-org/GLM-5","date":"2026-02-09T08:17:02+00:00","date_source":"source","source_url":"https://github.com/zai-org/GLM-5","signal_url":"https://onlylabs.fyi/signals/24fe5750-0998-45fd-b227-3e58096c2732","signal_json_url":"https://onlylabs.fyi/signals/24fe5750-0998-45fd-b227-3e58096c2732/signal.json","text":"repo_new · zai-org/GLM-5 · signal_desk=repos · occurred_at=2026-02-09T08:17:02+00:00 · url=https://github.com/zai-org/GLM-5 · stars=3388 · raw={\"repo\":\"zai-org/GLM-5\",\"description\":\"GLM-5: From Vibe Coding to Agentic Engineering\"}"},{"ref":"E46","kind":"event","title":"zai-org/GLM-4-Voice","date":"2024-10-24T12:12:32+00:00","date_source":"source","source_url":"https://github.com/zai-org/GLM-4-Voice","signal_url":"https://onlylabs.fyi/signals/178c8a76-8c99-4863-b696-07d577ade208","signal_json_url":"https://onlylabs.fyi/signals/178c8a76-8c99-4863-b696-07d577ade208/signal.json","text":"repo_new · zai-org/GLM-4-Voice · signal_desk=repos · occurred_at=2024-10-24T12:12:32+00:00 · url=https://github.com/zai-org/GLM-4-Voice · stars=3187 · raw={\"repo\":\"zai-org/GLM-4-Voice\",\"description\":\"GLM-4-Voice | 端到端中英语音对话模型\",\"language\":\"Python\"}"},{"ref":"E47","kind":"event","title":"zai-org/GLM-OCR v0.1.5","date":"2026-04-08T06:22:18+00:00","date_source":"source","source_url":"https://github.com/zai-org/GLM-OCR/releases/tag/v0.1.5","signal_url":"https://onlylabs.fyi/signals/75e7ffd2-51ae-4e6d-a779-0b41c373bc86","signal_json_url":"https://onlylabs.fyi/signals/75e7ffd2-51ae-4e6d-a779-0b41c373bc86/signal.json","text":"release · zai-org/GLM-OCR v0.1.5 · signal_desk=releases · occurred_at=2026-04-08T06:22:18+00:00 · url=https://github.com/zai-org/GLM-OCR/releases/tag/v0.1.5 · raw={\"repo\":\"zai-org/GLM-OCR\"}"},{"ref":"E48","kind":"event","title":"zai-org/CodeGeeX4","date":"2024-07-03T11:01:55+00:00","date_source":"source","source_url":"https://github.com/zai-org/CodeGeeX4","signal_url":"https://onlylabs.fyi/signals/c219c2fe-67be-4e16-bd84-e016323a5a41","signal_json_url":"https://onlylabs.fyi/signals/c219c2fe-67be-4e16-bd84-e016323a5a41/signal.json","text":"repo_new · zai-org/CodeGeeX4 · signal_desk=repos · occurred_at=2024-07-03T11:01:55+00:00 · url=https://github.com/zai-org/CodeGeeX4 · stars=2531 · raw={\"repo\":\"zai-org/CodeGeeX4\",\"description\":\"CodeGeeX4-ALL-9B, a versatile model for all AI software development scenarios, including code completion, code interpreter, web search, function calling, repository-level Q&A and much more.\",\"language\":\"Python\"}"},{"ref":"E49","kind":"event","title":"zai-org/CogVLM2","date":"2024-05-10T09:07:11+00:00","date_source":"source","source_url":"https://github.com/zai-org/CogVLM2","signal_url":"https://onlylabs.fyi/signals/06e5d19c-c441-429a-a1d5-1d1ed89fd029","signal_json_url":"https://onlylabs.fyi/signals/06e5d19c-c441-429a-a1d5-1d1ed89fd029/signal.json","text":"repo_new · zai-org/CogVLM2 · signal_desk=repos · occurred_at=2024-05-10T09:07:11+00:00 · url=https://github.com/zai-org/CogVLM2 · stars=2438 · raw={\"repo\":\"zai-org/CogVLM2\",\"description\":\"GPT4V-level open-source multi-modal model based on Llama3-8B\",\"language\":\"Python\"}"},{"ref":"E50","kind":"event","title":"zai-org/SSVAE","date":"2025-12-04T06:22:58+00:00","date_source":"source","source_url":"https://huggingface.co/zai-org/SSVAE","signal_url":"https://onlylabs.fyi/signals/90530351-c08d-4a44-a0dc-083dff68f9a0","signal_json_url":"https://onlylabs.fyi/signals/90530351-c08d-4a44-a0dc-083dff68f9a0/signal.json","text":"model_released · zai-org/SSVAE · signal_desk=releases · occurred_at=2025-12-04T06:22:58+00:00 · url=https://huggingface.co/zai-org/SSVAE · hf_likes=12 · license=mit"},{"ref":"E51","kind":"event","title":"zai-org/GLM-V","date":"2025-06-28T08:44:06+00:00","date_source":"source","source_url":"https://github.com/zai-org/GLM-V","signal_url":"https://onlylabs.fyi/signals/fd80c955-0d17-41f4-8cd0-3dffb54f8776","signal_json_url":"https://onlylabs.fyi/signals/fd80c955-0d17-41f4-8cd0-3dffb54f8776/signal.json","text":"repo_new · zai-org/GLM-V · signal_desk=repos · occurred_at=2025-06-28T08:44:06+00:00 · url=https://github.com/zai-org/GLM-V · stars=2327 · raw={\"repo\":\"zai-org/GLM-V\",\"description\":\"GLM-4.6V/4.5V/4.1V-Thinking: Towards Versatile Multimodal Reasoning with Scalable Reinforcement Learning\",\"language\":\"Python\"}"},{"ref":"E52","kind":"event","title":"zai-org/GLM-skills","date":"2026-03-30T08:34:04+00:00","date_source":"source","source_url":"https://github.com/zai-org/GLM-skills","signal_url":"https://onlylabs.fyi/signals/0530d1b0-8293-4e6b-9f76-f1a059b43c41","signal_json_url":"https://onlylabs.fyi/signals/0530d1b0-8293-4e6b-9f76-f1a059b43c41/signal.json","text":"repo_new · zai-org/GLM-skills · signal_desk=repos · occurred_at=2026-03-30T08:34:04+00:00 · url=https://github.com/zai-org/GLM-skills · stars=410 · raw={\"repo\":\"zai-org/GLM-skills\",\"description\":\"Official skills for the GLM family of models.\",\"language\":\"Python\"}"},{"ref":"E53","kind":"event","title":"zai-org/CogView","date":"2021-05-25T14:48:31+00:00","date_source":"source","source_url":"https://github.com/zai-org/CogView","signal_url":"https://onlylabs.fyi/signals/83495e63-0f09-4704-8ceb-93045d729ca6","signal_json_url":"https://onlylabs.fyi/signals/83495e63-0f09-4704-8ceb-93045d729ca6/signal.json","text":"repo_new · zai-org/CogView · signal_desk=repos · occurred_at=2021-05-25T14:48:31+00:00 · url=https://github.com/zai-org/CogView · stars=1797 · raw={\"repo\":\"zai-org/CogView\",\"description\":\"Text-to-Image generation. The repo for NeurIPS 2021 paper \\\"CogView: Mastering Text-to-Image Generation via Transformers\\\".\",\"language\":\"Python\"}"},{"ref":"E54","kind":"event","title":"zai-org/ImageReward","date":"2023-04-01T09:04:17+00:00","date_source":"source","source_url":"https://github.com/zai-org/ImageReward","signal_url":"https://onlylabs.fyi/signals/9d46b90f-3ef6-427c-a54c-a1877590beb7","signal_json_url":"https://onlylabs.fyi/signals/9d46b90f-3ef6-427c-a54c-a1877590beb7/signal.json","text":"repo_new · zai-org/ImageReward · signal_desk=repos · occurred_at=2023-04-01T09:04:17+00:00 · url=https://github.com/zai-org/ImageReward · stars=1681 · data_radar_lanes=Evals and quality · data_radar_terms=eval · data_radar_reason=Zhipu AI (GLM) has a repo signal matching evals and quality. · raw={\"repo\":\"zai-org/ImageReward\",\"description\":\"[NeurIPS 2023] ImageReward: Learning and Evaluating Human Preferences for Text-to-image Generation\",\"language\":\"Python\"}"},{"ref":"E55","kind":"event","title":"zai-org/Vision2Web","date":"2026-03-29T15:31:33+00:00","date_source":"source","source_url":"https://github.com/zai-org/Vision2Web","signal_url":"https://onlylabs.fyi/signals/7d1f43fb-6ff0-47a5-86c4-7222cb22ad17","signal_json_url":"https://onlylabs.fyi/signals/7d1f43fb-6ff0-47a5-86c4-7222cb22ad17/signal.json","text":"repo_new · zai-org/Vision2Web · signal_desk=repos · occurred_at=2026-03-29T15:31:33+00:00 · url=https://github.com/zai-org/Vision2Web · stars=48 · raw={\"repo\":\"zai-org/Vision2Web\",\"language\":\"Python\"}"},{"ref":"E56","kind":"event","title":"zai-org/CogAgent","date":"2023-11-28T09:28:08+00:00","date_source":"source","source_url":"https://github.com/zai-org/CogAgent","signal_url":"https://onlylabs.fyi/signals/ebdb2c69-1053-4be0-a0a7-121965b47fe0","signal_json_url":"https://onlylabs.fyi/signals/ebdb2c69-1053-4be0-a0a7-121965b47fe0/signal.json","text":"repo_new · zai-org/CogAgent · signal_desk=repos · occurred_at=2023-11-28T09:28:08+00:00 · url=https://github.com/zai-org/CogAgent · stars=1183 · raw={\"repo\":\"zai-org/CogAgent\",\"description\":\"An open-sourced end-to-end VLM-based GUI Agent\",\"language\":\"Python\"}"},{"ref":"E57","kind":"event","title":"zai-org/CogView4","date":"2024-09-23T06:38:31+00:00","date_source":"source","source_url":"https://github.com/zai-org/CogView4","signal_url":"https://onlylabs.fyi/signals/e52eab96-5dec-4ddb-af70-f13e518425c4","signal_json_url":"https://onlylabs.fyi/signals/e52eab96-5dec-4ddb-af70-f13e518425c4/signal.json","text":"repo_new · zai-org/CogView4 · signal_desk=repos · occurred_at=2024-09-23T06:38:31+00:00 · url=https://github.com/zai-org/CogView4 · stars=1103 · raw={\"repo\":\"zai-org/CogView4\",\"description\":\"CogView4, CogView3-Plus and CogView3(ECCV 2024)\",\"language\":\"Python\"}"},{"ref":"E58","kind":"event","title":"zai-org/GLM-TTS","date":"2025-12-06T04:50:56+00:00","date_source":"source","source_url":"https://github.com/zai-org/GLM-TTS","signal_url":"https://onlylabs.fyi/signals/7589a3bf-b65a-4ac9-bd26-c296fa2d0d09","signal_json_url":"https://onlylabs.fyi/signals/7589a3bf-b65a-4ac9-bd26-c296fa2d0d09/signal.json","text":"repo_new · zai-org/GLM-TTS · signal_desk=repos · occurred_at=2025-12-06T04:50:56+00:00 · url=https://github.com/zai-org/GLM-TTS · stars=1021 · raw={\"repo\":\"zai-org/GLM-TTS\",\"description\":\"GLM-TTS: Controllable & Emotion-Expressive Zero-shot TTS with Multi-Reward Reinforcement Learning\",\"language\":\"Python\"}"},{"ref":"E59","kind":"event","title":"zai-org/SCAIL","date":"2025-12-01T06:42:54+00:00","date_source":"source","source_url":"https://github.com/zai-org/SCAIL","signal_url":"https://onlylabs.fyi/signals/1609b84d-bfd5-4243-909a-5b3ffc6f0f3c","signal_json_url":"https://onlylabs.fyi/signals/1609b84d-bfd5-4243-909a-5b3ffc6f0f3c/signal.json","text":"repo_new · zai-org/SCAIL · signal_desk=repos · occurred_at=2025-12-01T06:42:54+00:00 · url=https://github.com/zai-org/SCAIL · stars=986 · raw={\"repo\":\"zai-org/SCAIL\",\"description\":\"SCAIL: Towards Studio-Grade Character Animation via In-Context Learning of 3D-Consistent Pose Representations (CVPR 2026 Findings)\",\"language\":\"Python\"}"},{"ref":"E60","kind":"event","title":"zai-org/CogView2","date":"2022-04-25T10:15:47+00:00","date_source":"source","source_url":"https://github.com/zai-org/CogView2","signal_url":"https://onlylabs.fyi/signals/65508c76-4a5f-4d64-8c97-219b2d917847","signal_json_url":"https://onlylabs.fyi/signals/65508c76-4a5f-4d64-8c97-219b2d917847/signal.json","text":"repo_new · zai-org/CogView2 · signal_desk=repos · occurred_at=2022-04-25T10:15:47+00:00 · url=https://github.com/zai-org/CogView2 · stars=955 · raw={\"repo\":\"zai-org/CogView2\",\"description\":\"official code repo for paper \\\"CogView2: Faster and Better Text-to-Image Generation via Hierarchical Transformers\\\"\",\"language\":\"Python\"}"}]} |
![](\"assets/logo2.png\"/){kind=logo}
\n![](\"assets/logo.png\"/){kind=logo}
\n![](\"resources/7D6433A42D189E2E6FBC62BE066BCE91.png\")
\n\n![](\"resources/logo/codegeex_logo.png\"){kind=logo}
\n\n