Ecosyste.ms: Awesome
An open API service indexing awesome lists of open source software.
https://github.com/orfeous/llamacpp.net
C#/.NET binding of llama.cpp
https://github.com/orfeous/llamacpp.net
ai chatbot gpt llama llamacpp llm
Last synced: 2 months ago
JSON representation
C#/.NET binding of llama.cpp
- Host: GitHub
- URL: https://github.com/orfeous/llamacpp.net
- Owner: Orfeous
- License: apache-2.0
- Created: 2023-06-17T11:52:09.000Z (over 1 year ago)
- Default Branch: develop
- Last Pushed: 2023-10-23T09:00:33.000Z (about 1 year ago)
- Last Synced: 2024-10-18T21:15:51.805Z (3 months ago)
- Topics: ai, chatbot, gpt, llama, llamacpp, llm
- Language: C#
- Homepage:
- Size: 830 KB
- Stars: 10
- Watchers: 3
- Forks: 0
- Open Issues: 14
-
Metadata Files:
- Readme: readme.md
- Contributing: .github/CONTRIBUTING.md
- License: LICENSE
- Code of conduct: .github/CODE_OF_CONDUCT.md
Awesome Lists containing this project
README
# LlamaCpp.Net
LlamaCpp.Net is a .NET wrapper for [llama.cpp](https://github.com/ggerganov/llama.cpp), a C++ library for dealing with large language models.
In particular, we try to abstract away the complexity of dealing with the C++ code and provide a simple interface for using the library in .NET applications.
Nobody wants to deal with pointers and memory management in C#.
## Features
- **Fast** - LlamaCpp.Net is a thin wrapper around llama.cpp, which is written in C++ and is very fast
- **Idiomatic** - If there's a C# way of doing something, we do it the C# way.
- **Cross-platform** - LlamaCpp.Net is written in C# and can be used on Windows, Linux and macOS
- **Open-source** - LlamaCpp.Net is open-source and is licensed under the terms of the Apache 2.0 license
- **Batteries included** - LlamaCpp.Net comes with pre-built runtime binaries for different platforms and architectures
## Installation
LlamaCpp.Net is available as a [NuGet package](https://www.nuget.org/packages/LlamaCpp.Net/).
Additionally, you'll need to install the runtime binaries for your platform and architecture.
These are, conveniently, also available as [NuGet packages](https://www.nuget.org/packages?q%253DLlamaCpp.Net).
## Getting started
For a quick start, check out the [examples](examples) folder, or check out the Wiki in Github.
## Building from source
We use [Cake](https://cakebuild.net/) as our build system, so our build scripts are written in C#, and can be run on Windows, Linux and macOS.
As the underlying dependencies may be changed, please refer to the [llama.cpp](https://github.com/ggerganov/llama.cpp) repositories for which dependencies are required.
After that, it's as simple as running `.\build.ps1 -t SetupDevelopmentEnvironment` on Windows, or `./build.sh -t SetupDevelopmentEnvironment` on Linux and macOS.
## Llama icon
Llama icon by [Gedeon Maheux](https://www.iconhot.com/icon/the-emperor39s-new-groove/llama-glyph.html)
## Contact
If you have any questions or need help, please contact us on [Discord](https://discord.gg/GtPWFSGbye).
## License
LlamaCpp.Net is licensed under the terms of the Apache 2.0 license.
[llama.cpp](https://github.com/ggerganov/llama.cpp) is licensed under the terms of the MIT license.