mungert/autoglm-phone-9b-multilingual-gguf overview

{
  "metadata": {},
  "card_data": {
    "license": "mit",
    "language": [
      "zh"
    ],
    "base_model": [
      "zai-org/GLM-4.1V-9B-Base"
    ],
    "pipeline_tag": "image-text-to-text",
    "tags": [
      "agent"
    ],
    "library_name": "transformers",
    "frontmatter": {
      "license": "mit",
      "language": [
        "zh"
      ],
      "base_model": [
        "zai-org/GLM-4.1V-9B-Base"
      ],
      "pipeline_tag": "image-text-to-text",
      "tags": [
        "agent"
      ],
      "library_name": "transformers"
    },
    "hero_image_url": "https://raw.githubusercontent.com/zai-org/Open-AutoGLM/refs/heads/main/resources/logo.svg",
    "summary": "",
    "quick_links": [],
    "benchmark_table_html": "",
    "readme_markdown": "---\nlicense: mit\nlanguage:\n- zh\nbase_model:\n- zai-org/GLM-4.1V-9B-Base\npipeline_tag: image-text-to-text\ntags:\n- agent\nlibrary_name: transformers\n---\n\n# <span style=\"color: #7FFF7F;\">AutoGLM-Phone-9B-Multilingual GGUF Models</span>\n\n\n## <span style=\"color: #7F7FFF;\">Model Generation Details</span>\n\nThis model was generated using [llama.cpp](https://github.com/ggerganov/llama.cpp) at commit [`e1f15b454`](https://github.com/ggerganov/llama.cpp/commit/e1f15b454fbadfddf8f1ec450bf6d390d9db7adb).\n\n\n\n\n\n---\n\n## <span style=\"color: #7FFF7F;\">Quantization Beyond the IMatrix</span>\n\nI've been experimenting with a new quantization approach that selectively elevates the precision of key layers beyond what the default IMatrix configuration provides.\n\nIn my testing, standard IMatrix quantization underperforms at lower bit depths, especially with Mixture of Experts (MoE) models. To address this, I'm using the `--tensor-type` option in `llama.cpp` to manually \"bump\" important layers to higher precision. You can see the implementation here:  \n👉 [Layer bumping with llama.cpp](https://github.com/Mungert69/GGUFModelBuilder/blob/main/model-converter/tensor_list_builder.py)\n\nWhile this does increase model file size, it significantly improves precision for a given quantization level.\n\n### **I'd love your feedback—have you tried this? How does it perform for you?**\n\n\n\n\n---\n\n<a href=\"https://readyforquantum.com/huggingface_gguf_selection_guide.html\" style=\"color: #7FFF7F;\">\n  Click here to get info on choosing the right GGUF model format\n</a>\n\n---\n\n\n\n<!--Begin Original Model Card-->\n\n\n# AutoGLM-Phone-9B-Multilingual\n\n<div align=\"center\">\n<img src=\"https://raw.githubusercontent.com/zai-org/Open-AutoGLM/refs/heads/main/resources/logo.svg\" width=\"20%\"/>\n</div>\n\n<p align=\"center\">\n    👋 Join our <a href=\"https://raw.githubusercontent.com/zai-org/Open-AutoGLM/refs/heads/main/resources/WECHAT.md\" target=\"_blank\">WeChat</a> community\n</p>\n\n> ⚠️ This project is intended **for research and educational purposes only**.  \n> Any use for illegal data access, system interference, or unlawful activities is strictly prohibited.  \n> Please review our [Terms of Use](https://raw.githubusercontent.com/zai-org/Open-AutoGLM/refs/heads/main/resources/privacy_policy.txt) carefully.\n\n## Project Overview\n\n**Phone Agent** is a mobile intelligent assistant framework built on **AutoGLM**, capable of understanding smartphone screens through multimodal perception and executing automated operations to complete tasks.  \nThe system controls devices via **ADB (Android Debug Bridge)**, uses a **vision-language model** for screen understanding, and leverages **intelligent planning** to generate and execute action sequences.\n\nUsers can simply describe tasks in natural language—for example, *“Open Xiaohongshu and search for food recommendations.”*  \nPhone Agent will automatically parse the intent, understand the current UI, plan the next steps, and carry out the entire workflow.\n\nThe system also includes:\n- **Sensitive action confirmation mechanisms**\n- **Human-in-the-loop fallback** for login or verification code scenarios\n- **Remote ADB debugging**, allowing device connection via WiFi or network for flexible remote control and development\n\n## Model Usage\n\nWe provide an open-source model usage guide to help you quickly download and deploy the model.  \nPlease visit our **[GitHub](https://github.com/zai-org/Open-AutoGLM)** for detailed instructions.\n\n- The model architecture is identical to **`GLM-4.1V-9B-Thinking`**.  \n  For deployment details, see the **[GLM-V](https://github.com/zai-org/GLM-V)** repository.\n\n### Citation\n\nIf you find our work helpful, please cite the following paper:\n```bibtex\n@article{liu2024autoglm,\n  title={Autoglm: Autonomous foundation agents for guis},\n  author={Liu, Xiao and Qin, Bo and Liang, Dongzhu and Dong, Guang and Lai, Hanyu and Zhang, Hanchen and Zhao, Hanlin and Iong, Iat Long and Sun, Jiadai and Wang, Jiaqi and others},\n  journal={arXiv preprint arXiv:2411.00820},\n  year={2024}\n}\n@article{xu2025mobilerl,\n  title={MobileRL: Online Agentic Reinforcement Learning for Mobile GUI Agents},\n  author={Xu, Yifan and Liu, Xiao and Liu, Xinghan and Fu, Jiaqi and Zhang, Hanchen and Jing, Bohao and Zhang, Shudan and Wang, Yuting and Zhao, Wenyi and Dong, Yuxiao},\n  journal={arXiv preprint arXiv:2509.18119},\n  year={2025}\n}\n```\n\n<!--End Original Model Card-->\n\n---\n\n# <span id=\"testllm\" style=\"color: #7F7FFF;\">🚀 If you find these models useful</span>\n\nHelp me test my **AI-Powered Quantum Network Monitor Assistant** with **quantum-ready security checks**:  \n\n👉 [Quantum Network Monitor](https://readyforquantum.com/?assistant=open&utm_source=huggingface&utm_medium=referral&utm_campaign=huggingface_repo_readme)  \n\n\nThe full Open Source Code for the Quantum Network Monitor Service available at my github repos ( repos with NetworkMonitor in the name) : [Source Code Quantum Network Monitor](https://github.com/Mungert69). You will also find the code I use to quantize the models if you want to do it yourself [GGUFModelBuilder](https://github.com/Mungert69/GGUFModelBuilder)\n\n💬 **How to test**:  \n Choose an **AI assistant type**:  \n   - `TurboLLM` (GPT-4.1-mini)  \n   - `HugLLM` (Hugginface Open-source models)  \n   - `TestLLM` (Experimental CPU-only)  \n\n### **What I’m Testing**  \nI’m pushing the limits of **small open-source models for AI network monitoring**, specifically:  \n- **Function calling** against live network services  \n- **How small can a model go** while still handling:  \n  - Automated **Nmap security scans**  \n  - **Quantum-readiness checks**  \n  - **Network Monitoring tasks**  \n\n🟡 **TestLLM** – Current experimental model (llama.cpp on 2 CPU threads on huggingface docker space):  \n- ✅ **Zero-configuration setup**  \n- ⏳ 30s load time (slow inference but **no API costs**) . No token limited as the cost is low.\n- 🔧 **Help wanted!** If you’re into **edge-device AI**, let’s collaborate!  \n\n### **Other Assistants**  \n🟢 **TurboLLM** – Uses **gpt-4.1-mini** :\n- **It performs very well but unfortunatly OpenAI charges per token. For this reason tokens usage is limited. \n- **Create custom cmd processors to run .net code on Quantum Network Monitor Agents**\n- **Real-time network diagnostics and monitoring**\n- **Security Audits**\n- **Penetration testing** (Nmap/Metasploit)  \n\n🔵 **HugLLM** – Latest Open-source models:  \n- 🌐 Runs on Hugging Face Inference API. Performs pretty well using the lastest models hosted on Novita.\n\n### 💡 **Example commands you could test**:  \n1. `\"Give me info on my websites SSL certificate\"`  \n2. `\"Check if my server is using quantum safe encyption for communication\"`  \n3. `\"Run a comprehensive security audit on my server\"`\n4. '\"Create a cmd processor to .. (what ever you want)\" Note you need to install a [Quantum Network Monitor Agent](https://readyforquantum.com/Download/?utm_source=huggingface&utm_medium=referral&utm_campaign=huggingface_repo_readme) to run the .net code on. This is a very flexible and powerful feature. Use with caution!\n\n### Final Word\n\nI fund the servers used to create these model files, run the Quantum Network Monitor service, and pay for inference from Novita and OpenAI—all out of my own pocket. All the code behind the model creation and the Quantum Network Monitor project is [open source](https://github.com/Mungert69). Feel free to use whatever you find helpful.\n\nIf you appreciate the work, please consider [buying me a coffee](https://www.buymeacoffee.com/mahadeva) ☕. Your support helps cover service costs and allows me to raise token limits for everyone.\n\nI'm also open to job opportunities or sponsorship.\n\nThank you! 😊\n",
    "related_quantizations": []
  },
  "tags": [
    "transformers",
    "gguf",
    "agent",
    "image-text-to-text",
    "zh",
    "arxiv:2411.00820",
    "arxiv:2509.18119",
    "base_model:zai-org/GLM-4.1V-9B-Base",
    "base_model:quantized:zai-org/GLM-4.1V-9B-Base",
    "license:mit",
    "endpoints_compatible",
    "region:us",
    "conversational"
  ],
  "likes": 0,
  "downloads": 351,
  "gated": false,
  "private": false,
  "last_modified": "2025-12-23T03:55:03.000Z",
  "created_at": "2025-12-22T23:18:48.000Z",
  "pipeline_tag": "image-text-to-text",
  "library_name": "transformers"
}

{
  "_id": "6949d1d85b54d6322ac726a7",
  "id": "Mungert/AutoGLM-Phone-9B-Multilingual-GGUF",
  "modelId": "Mungert/AutoGLM-Phone-9B-Multilingual-GGUF",
  "sha": "8ded99415e6e53c87d5fc944d614ca515066a2d1",
  "createdAt": "2025-12-22T23:18:48.000Z",
  "lastModified": "2025-12-23T03:55:03.000Z",
  "author": "Mungert",
  "downloads": 351,
  "likes": 0,
  "gated": false,
  "private": false,
  "pipeline_tag": "image-text-to-text",
  "library_name": "transformers",
  "siblings_count": 32
}