Usama

Results 82 comments of Usama

Adding Indian Women Menstrual Health Chatbot Eval

> Thank you for explaining and suggesting using 'closedqa' modelgraded eval. We have now used the same with the criteria set to checking if the answer was contextualized to India....

Add gpt4facts Eval

Updated version of #255 .

add chinese character and english words generation count evaluation (17% accuracy, 40 samples)

Thank you for opening this PR. We're not accepting evals that have custom code implementations at this moment (but we are accepting custom model-graded evals). If possible, could you rewrite...

add chinese character and english words generation count evaluation (17% accuracy, 40 samples)

Closing this PR, please open another PR with the suggested changes.

Add slope-intercept eval

Closing the PR due to inactivity; please reopen if you get a chance to address comments.

Added eval to predict next number in the series (Accuracy: 0.97, Samples: 100)

Closing the PR due to inactivity; please reopen if you get a chance to address comments.

Added eval to predict next number in the series (Accuracy: 0.97, Samples: 100)

You should see GPT-4 API access enabled in your account in the next few days.

Chess best move

Closing the PR due to inactivity; please reopen if you get a chance to address comments.

Chess draw by insufficient material

Closing the PR due to inactivity; please reopen if you get a chance to address comments.

Add count puzzle for eval logic and math ability

Closing the PR due to inactivity; please reopen if you get a chance to address comments.