Commit History

MC1 column had 8 rows with a value of 1. It didn't make sense given the next highest value was 0.47 . Assuming they were data errors, they were removed
e03b231

Corey Morris commited on

truthfulqa data added to dataframe
abac22e

Corey Morris commited on

Refactor to make later code changes easier
6d41115

Corey Morris commited on

Added test for removal of undesired columns. fixed code error in column removal
9549fcc

Corey Morris commited on

Added initial tests. test_columns and test_rows will be updated or removed later as they test for the exact number of columns and rows. the number of rows will change as more models are added
85667d0

Corey Morris commited on

Updated the last updated date to 18Aug
42ff7b9

Corey Morris commited on

updated with new hugging face results
8ccc242

Corey Morris commited on

Updated description with more models
7f24726

Corey Morris commited on

updated results
80c79bd

Corey Morris commited on

fixed error
d7b89ce

Corey Morris commited on

Added google analytics snippet
9444cd2

Corey Morris commited on

Increased size of scatter plot
2b16774

Corey Morris commited on

Made the radar plot larger
f52387e

Corey Morris commited on

Moved radar plots to higher in the page
12a9766

Corey Morris commited on

Modified title and explanation to better reflect what the site is
18ec1ba

Corey Morris commited on

Moved radar chart to after analysis
fb25b1e

Corey Morris commited on

Added a default model to compare
7b77065

Corey Morris commited on

Improved clarity of explanation for Radar charts
a450af5

Corey Morris commited on

Fixed some of the diplicate model issue
618dcce

Corey Morris commited on

Table now displays the columns that have the top differences
dc21a69

Corey Morris commited on

removed charts with hardcoded tasks. removed hardcoding of model for other charts
a125eb8

Corey Morris commited on

Finding top differences between tasks from the target model
627e0f9

Corey Morris commited on

Added explanation for the plot and a dataframe of the models
2db58a0

Corey Morris commited on

Added radar chart. Compares a model to the 5 models that have the closest performance on MMLU_average
9695a47

Corey Morris commited on

added new results from hugging face
b9b6115

Corey Morris commited on

Added header back for the table
2a7f691

Corey Morris commited on

Added citation for the site
ea8703d

Corey Morris commited on

Changed streamlit to wide layout to see more of the table
1e6b767

Corey Morris commited on

Updated updated date
28d4d6a

Corey Morris commited on

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

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

Added search for Model name and Task name
3abc48f

Corey Morris commited on

Added reasoning for having scatter plots
cb21769

Corey Morris commited on

Updated title now that there are over 700 open source models in the dataset
a9f9804

Corey Morris commited on

Updated with new results from hugging face
c173f6a

Corey Morris commited on

Added statement and hypothesis about moral scenarios
d97426f

Corey Morris commited on

Plots have a default title
f9a0f38

Corey Morris commited on

updated requirements.txt
bb08057

Corey Morris commited on

Refactor of create_plot
bdad6e6

Corey Morris commited on

Added finding from moral scenarios about threshold
1f8cc2a

Corey Morris commited on

Added bar chart for abstract algebra data.
a79afe8

Corey Morris commited on

updated hugging face results
c823b6d

Corey Morris commited on

Added introduction, links, and reduced the number of plots displayed
a5fb364

Corey Morris commited on

Updated with new data from hugging face
c10db67

Corey Morris commited on

Modified download CSV feature so that the index column now has a title of model name
6a7ad7c

Corey Morris commited on

Added citation
4fbdb10

Corey Morris commited on

Added new hugging face results
6d0ce25

Corey Morris commited on

updated with new hugging face results
8384e2b

Corey Morris commited on

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

Moved rank data into a separate method and dataframe
31bed1a

Corey Morris commited on