7494f1f6e8
ctranslate2-bindings@0.4.0-rc.0 http-api-bindings@0.4.0-rc.0 llama-cpp-bindings@0.4.0-rc.0 rust-cxx-cmake-bridge@0.4.0-rc.0 tabby@0.4.0-rc.0 tabby-common@0.4.0-rc.0 tabby-download@0.4.0-rc.0 tabby-inference@0.4.0-rc.0 tabby-scheduler@0.4.0-rc.0 Generated by cargo-workspaces |
||
|---|---|---|
| .github | ||
| ci | ||
| clients | ||
| crates | ||
| experimental | ||
| python/tabby | ||
| tests | ||
| website | ||
| .dockerignore | ||
| .gitattributes | ||
| .gitignore | ||
| .gitmodules | ||
| .rustfmt.toml | ||
| CHANGELOG.md | ||
| Cargo.lock | ||
| Cargo.toml | ||
| Dockerfile | ||
| LICENSE | ||
| MODEL_SPEC.md | ||
| Makefile | ||
| README.md | ||
| package.json | ||
| yarn.lock | ||
README.md
🐾 Tabby
Tabby is a self-hosted AI coding assistant, offering an open-source and on-premises alternative to GitHub Copilot. It boasts several key features:
- Self-contained, with no need for a DBMS or cloud service.
- OpenAPI interface, easy to integrate with existing infrastructure (e.g Cloud IDE).
- Supports consumer-grade GPUs.
🔥 What's New
- 10/15/2023 RAG-based code completion is enabled by detail in v0.3.0🎉! Check out the blogpost explaining how Tabby utilizes repo-level context to get even smarter!
- 10/04/2023 Check out the model directory for the latest models supported by Tabby.
- 09/21/2023 We've hit 10K stars 🌟 on GitHub! 🚀🎉👏
Archived
* **09/18/2023** Apple's M1/M2 Metal inference support has landed in [v0.1.1](https://github.com/TabbyML/tabby/releases/tag/v0.1.1)! * **08/31/2023** Tabby's first stable release [v0.0.1](https://github.com/TabbyML/tabby/releases/tag/v0.0.1) 🥳. * **08/28/2023** Experimental support for the [CodeLlama 7B](https://github.com/TabbyML/tabby/issues/370). * **08/24/2023** Tabby is now on [JetBrains Marketplace](https://plugins.jetbrains.com/plugin/22379-tabby)!👋 Getting Started
You can find our documentation here.
Run Tabby in 1 Minute
The easiest way to start a Tabby server is by using the following Docker command:
docker run -it \
--gpus all -p 8080:8080 -v $HOME/.tabby:/data \
tabbyml/tabby \
serve --model TabbyML/SantaCoder-1B --device cuda
For additional options (e.g inference type, parallelism), please refer to the documentation page.
🤝 Contributing
Get the Code
git clone --recurse-submodules https://github.com/TabbyML/tabby
cd tabby
If you have already cloned the repository, you could run the git submodule update --recursive --init command to fetch all submodules.
Build
-
Set up the Rust environment by following this tutorial.
-
Install the required dependencies:
# For MacOS
brew install protobuf
# For Ubuntu / Debian
apt-get install protobuf-compiler libopenblas-dev
- Now, you can build Tabby by running the command
cargo build.
Start Hacking!
... and don't forget to submit a Pull Request
🌍 Community
- #️⃣ Slack - connect with the TabbyML community
- 🎤 Twitter / X - engage with TabbyML for all things possible
- 📚 LinkedIn - follow for the latest from the community
- 💌 Newsletter - subscribe to unlock Tabby insights and secrets