Saina Helm 2.0: a small model for workflow decisions

Saina Helm 2.0, a 0.8B-parameter decision model for workflow automation built by the developer run-saina, scored 30.17 on the public Decision Index 0.3 suite using model revision 9903c487a3b1eef45c8cc56c76155b9baccb55f9, a self-run result the developer states is not an official leaderboard score. The developer published a reproducible evaluation at the run-saina/saina-decision-index GitHub repository and is seeking feedback on the evaluation plus suggestions for workflow tests and integrations.

I’ve been building Saina Helm 2.0, a 0.8B decision model for workflow automation. I ran it on the public Decision Index 0.3 suite and got 30.17 using model revision 9903c487a3b1eef45c8cc56c76155b9baccb55f9 https://huggingface.co/run-saina/saina-helm-2-0.8b/tree/9903c487a3b1eef45c8cc56c76155b9baccb55f9 . This is a self-run public result, not an official leaderboard score. - Reproducible evaluation https://github.com/run-saina/saina-decision-index I’d welcome feedback on the evaluation and suggestions for useful workflow tests or integrations.