Add evaluation results
#8
by SaylorTwift HF Staff - opened
Add .eval_results/A.X-K1.yaml with benchmark results from the model card
Thanks for the contribution! The eval results YAML matches the numbers on our model card, so merging this in. Appreciated!
singleheart changed pull request status to merged
No issues!! This is actually part of a new feature named community evals. Your models now appears on the leaderboards on the hub. Here are the docs about it. It would be lovely to have those eval-results in the models for your next model releases 💟