Moved CSV download to just below the table
a34a60b
Corey Morris
commited on
Commit History
Added download CSV button
c90b29a
Corey Morris
commited on
Added updated results from hugging face evaluation runs
51a128e
Corey Morris
commited on
Rename
e854cb9
Corey Morris
commited on
Added custom scatterplot creation
ca8d4b9
Corey Morris
commited on
Improving clarity. Moved MMLU average column to a more appropriate spot
5129f48
Corey Morris
commited on
Hiding filters unless box is selected. Removed model name column because it is the index of the table
8488477
Corey Morris
commited on
Added a scatter plot with just the top 50 performing models on MMLU average
ca8e784
Corey Morris
commited on
added MMLU overall average column. added a few charts comparing more moral reasoning and comparing MMLU overall to other data
c671de9
Corey Morris
commited on
Added statsmodels to be able to use a trendline in plotly
ed019c6
Corey Morris
commited on
Updated data cleanup so that column names are cleaned up appropriatly with regex=True
c1a84da
Corey Morris
commited on
added a few charts
ac931c6
Corey Morris
commited on
fixed reversed plot. extracted making chart into a method
337b761
Corey Morris
commited on
Update app.py and requirements.txt so that it will work with huggingface streamlit with the pandas 1.x version
ba99486
Corey Morris
commited on
updated requirments.txt
cf28458
Corey Morris
commited on
updated requirments.txt with exact spaces
e468b5f
Corey Morris
commited on
updated requirments.txt
65d5105
Corey Morris
commited on
updated requirements.txt
544ab80
Corey Morris
commited on
updated requirements.txt
f0012a7
Corey Morris
commited on
updated requirements.txt with versions being used locally
7ae46ce
Corey Morris
commited on
added requirements file
a33e674
Corey Morris
commited on
Fixed plot
dfa14a8
Corey Morris
commited on
WIP commit. Troubleshoot chart display. Add behavior of filter
43b4e29
Corey Morris
commited on
Revert "Moved dataframe to above the multiselect"
e3642ff
Corey Morris
commited on
Moved dataframe to above the multiselect
24e7049
Corey Morris
commited on
streamlit initial app
c12bd84
Corey Morris
commited on
added hugging face evaluation harness results submodule
4dcdfc8
Corey Morris
commited on