[
  {
    "path": "README.md",
    "content": "# Vicuna Installation Guide\n\n\n[![Stargazers][stars-shield]][stars-url]\n[![Forks][forks-shield]][forks-url]\n\nDetailed instructions for installing and configuring Vicuna\n\n<a href=\"#installation\">Installation</a> - <a href=\"#usage\">Usage</a>\n\n\n### latest changes\n- updated the guide to vicuna 1.5 `10.10.23`\n- fixed the guide\n- added instructions for 7B model\n- fixed the `wget` command \n- modified the `chat-with-vicuna-v1.txt` in my llama.cpp fork\n- updated this guide to vicuna version 1.1\n## Requirements\n- The Vicuna 13B model needs ~10GB of CPU RAM, If you don't have enough RAM, you can increase the size of your virtual RAM (swap)\n  A tutorial on how to increase the swapfile on Linux: https://arcolinux.com/how-to-increase-the-size-of-your-swapfile/\n- The git and wget package \n- A Unix based operating system is recommended\n\n## Installation\n### One-line install script for Vicuna-1.1-13B\n```\ngit clone https://github.com/fredi-python/llama.cpp.git && cd llama.cpp && make -j && cd models && wget -c https://huggingface.co/TheBloke/vicuna-13B-v1.5-GGUF/resolve/main/vicuna-13b-v1.5.Q4_K_M.gguf\n```\n### One-line install script for Vicuna-1.1-7B\n```\ngit clone https://github.com/fredi-python/llama.cpp.git && cd llama.cpp && make -j && cd models && wget -c https://huggingface.co/TheBloke/vicuna-7B-v1.5-GGUF/resolve/main/vicuna-7b-v1.5.Q4_K_M.gguf\n```\n\n### Manual Installation\n#### 1. Clone the llama.cpp respository\n```\ngit clone https://github.com/fredi-python/llama.cpp.git\n```\n#### 2. Change directory\n```\ncd llama.cpp\n```\n#### 3. Make it!\n```\nmake -j\n```\n#### 4. Move to the llama.cpp/models folder\n```\ncd models\n```\n#### 5. a) Download the latest Vicuna model (13B) from Huggingface\n```\nwget -c https://huggingface.co/TheBloke/vicuna-13B-v1.5-GGUF/resolve/main/vicuna-13b-v1.5.Q4_K_M.gguf\n```\n#### 5. b) Download the latest Vicuna model (7B) from Huggingface\n```\nwget -c https://huggingface.co/TheBloke/vicuna-7B-v1.5-GGUF/resolve/main/vicuna-7b-v1.5.Q4_K_M.gguf\n```\n## Usage\n#### Navigate back to the llama.cpp folder\n```\ncd ..\n```\n#### Example of how to run the 13b model with llama.cpp's chat-with-vicuna-v1.txt \n```\n./main -m models/vicuna-13b-v1.5.Q4_K_M.gguf --repeat_penalty 1.0 --color -i -r \"User:\" -f prompts/chat-with-vicuna-v1.txt\n```\n\n\n[stars-shield]: https://img.shields.io/github/stars/vicuna-tools/vicuna-installation-guide.svg?style=for-the-badge\n[stars-url]: https://github.com/vicuna-tools/vicuna-installation-guide/stargazers\n[forks-shield]: https://img.shields.io/github/forks/vicuna-tools/vicuna-installation-guide.svg?style=for-the-badge\n[forks-url]: https://github.com/vicuna-tools/vicuna-installation-guide/network/members\n"
  }
]