Updated to reflect number of models. Previously, I think there were duplicates d396c1e Corey Morris commited on Aug 24, 2023
Show a random question from the moral scenarios evaluation 19c7c67 Corey Morris commited on Aug 24, 2023
Modified title and explanation to better reflect what the site is 18ec1ba Corey Morris commited on Aug 15, 2023
Table now displays the columns that have the top differences dc21a69 Corey Morris commited on Aug 14, 2023
removed charts with hardcoded tasks. removed hardcoding of model for other charts a125eb8 Corey Morris commited on Aug 14, 2023
Finding top differences between tasks from the target model 627e0f9 Corey Morris commited on Aug 14, 2023
Added explanation for the plot and a dataframe of the models 2db58a0 Corey Morris commited on Aug 14, 2023
Added radar chart. Compares a model to the 5 models that have the closest performance on MMLU_average 9695a47 Corey Morris commited on Aug 14, 2023
Changed streamlit to wide layout to see more of the table 1e6b767 Corey Morris commited on Aug 10, 2023
Added filter for parameter count. Fixed model filter so that it only filters on the Model name (index of the table) 8474e43 Corey Morris commited on Aug 10, 2023
Modified the selection of models and evaluations so that most do not show up by default. for a better user experience with 700+ models 0a33874 Corey Morris commited on Aug 10, 2023
Updated title now that there are over 700 open source models in the dataset a9f9804 Corey Morris commited on Aug 10, 2023
Added introduction, links, and reduced the number of plots displayed a5fb364 Corey Morris commited on Aug 8, 2023
Modified download CSV feature so that the index column now has a title of model name 6a7ad7c Corey Morris commited on Aug 3, 2023
Add dashed line at the appropriate scale of the largest and smallest values on the plot so that plotly still zooms in to show that 7ed3839 Corey Morris commited on Jul 30, 2023
Refactoring. Moved ResultDataProcessor class to a separate file to make it easier to use with experimentation in a jupyter notebook 843a5ef Corey Morris commited on Jul 24, 2023