You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
|[**Browse adapter functions**](https://generative-computing.github.io/granite-switch/adapter_catalog.html)|[Pre-composed Models on HF](https://huggingface.co/ibm-granite/granite-switch-4.1-8b-preview)|[Tutorials](tutorials/README.md)|
9
+
|[**Browse adapter functions**](https://generative-computing.github.io/granite-switch/adapter_catalog.html)|[Pre-composed Models on HF](https://huggingface.co/ibm-granite/granite-switch-4.1-8b-preview)|[Tutorials](https://github.com/generative-computing/granite-switch/blob/main/tutorials/README.md)|
10
10
11
11
Software is built from libraries — you pick the ones you need, compose them, and ship. Granite Switch brings this to AI models: choose **adapter functions** for RAG, safety, factuality, and more, compose them into a single model, and deploy with one command. Swap or upgrade any component independently, just like updating a dependency.
12
12
@@ -135,7 +135,7 @@ New here? Start with a 5-minute notebook and work your way up:
135
135
|[RAG Flow](https://colab.research.google.com/github/generative-computing/granite-switch/blob/main/tutorials/notebooks/rag_flow.ipynb)| Query rewrite + answerability + citations in one model | 30 min |[](https://colab.research.google.com/github/generative-computing/granite-switch/blob/main/tutorials/notebooks/rag_flow.ipynb)|
136
136
|[Compose Your Own](https://colab.research.google.com/github/generative-computing/granite-switch/blob/main/tutorials/notebooks/compose_granite_switch.ipynb)| Build a custom checkpoint from adapter function libraries | 15 min |[](https://colab.research.google.com/github/generative-computing/granite-switch/blob/main/tutorials/notebooks/compose_granite_switch.ipynb)|
137
137
138
-
All notebooks run on Colab. See [tutorials/README.md](tutorials/README.md) for the full list and guided learning paths.
138
+
All notebooks run on Colab. See [tutorials/README.md](https://github.com/generative-computing/granite-switch/blob/main/tutorials/README.md) for the full list and guided learning paths.
139
139
140
140
## Ecosystem
141
141
@@ -148,8 +148,8 @@ Granite Switch is part of a coordinated stack:
148
148
149
149
## Contributing
150
150
151
-
Granite Switch was started by IBM Research and is developed in the open. We welcome bug reports, feature requests, and pull requests — see [CONTRIBUTING.md](CONTRIBUTING.md) for guidelines or open an [issue](https://github.com/generative-computing/granite-switch/issues).
151
+
Granite Switch was started by IBM Research and is developed in the open. We welcome bug reports, feature requests, and pull requests — see [CONTRIBUTING.md](https://github.com/generative-computing/granite-switch/blob/main/CONTRIBUTING.md) for guidelines or open an [issue](https://github.com/generative-computing/granite-switch/issues).
152
152
153
153
## License
154
154
155
-
Apache-2.0 — see [LICENSE](LICENSE).
155
+
Apache-2.0 — see [LICENSE](https://github.com/generative-computing/granite-switch/blob/main/LICENSE).
0 commit comments