https://github.com/developer239/llama-chat-cmake-example

https://github.com/developer239/llama-chat-cmake-example

Last synced: 11 days ago
JSON representation

• Host: GitHub
• URL: https://github.com/developer239/llama-chat-cmake-example
• Owner: developer239
• Created: 2024-07-27T14:54:43.000Z (4 months ago)
• Default Branch: master
• Last Pushed: 2024-09-26T22:22:05.000Z (about 2 months ago)
• Last Synced: 2024-11-09T15:16:55.485Z (11 days ago)
• Language: C++
• Size: 8.79 KB
• Stars: 0
• Watchers: 1
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

        
# LlamaChat CMake Example

This project demonstrates how to use the [LlamaChat](https://github.com/developer239/llama-chat) library in a C++ application. It shows how to initialize the model, set up the context, and run multiple queries using the LlamaChat interface.

## Project Structure

```

llamachat-example/

│

├── CMakeLists.txt

├── src/

│   └── main.cpp

├── models/

│   └── Meta-Llama-3.1-8B-Instruct-Q3_K_S.gguf

└── externals/

    └── llama-chat/

```

## Setup

1. Clone this repository:

   ```

   git clone https://github.com/your-username/llamachat-example.git

   cd llamachat-example

   ```

2. Initialize and update the LlamaChat submodule:

   ```

   git submodule update --init --recursive

   ```

3. Place your language model file (e.g., Meta-Llama-3.1-8B-Instruct-Q3_K_S.gguf) in the `models/` directory.

4. Create a build directory and run CMake:

   ```

   mkdir build

   cd build

   cmake ..

   ```

5. Build the project:

   ```

   cmake --build .

   ```

## Usage

After building the project, you can run the example application:

```

./llamachat_example

```

The application will initialize the LlamaChat model, set a system prompt, and then ask a series of predefined questions. The responses will be printed to the console.