Commit History

Update app.py
fd7fab5
Running
verified

saattrupdan commited on

Update app.py
5c9ed9a
verified

saattrupdan commited on

Update README.md (#1)
c24aee4
verified

saattrupdan commited on

fix: Lower case model sorting
6e9ab8e

saattrupdan commited on

feat: Change UPDATE_FREQUENCY_MINUTES to 5
9e3c3cd

saattrupdan commited on

feat: Update app with log rank scores
5f70754

saattrupdan commited on

fix: Update win ratios to take ranks into account
734648f

saattrupdan commited on

feat: Add update colours button
c34e772

saattrupdan commited on

feat: Update datasets used in ScandEval
8157f53

saattrupdan commited on

feat: Sorting is case-independent
f04c64c

saattrupdan commited on

fix: Sort models and languages in the beginning
995f0f4

saattrupdan commited on

feat: Sort dropdown list of model IDs
27bc6fa

saattrupdan commited on

feat: Change order of tasks, to avoid hiding INFORMATION_EXTRACTION
437ac86

saattrupdan commited on

feat: Fix colour for each model (up to retakes), reduce logging
a73e53c

saattrupdan commited on

chore: Revert last change
576340d

saattrupdan commited on

feat: Use experimental nested t-test to determine statistical significance
ada1f6c

saattrupdan commited on

style: Kwargs and type hints
4bf4abc

saattrupdan commited on

feat: Select 2 models if possible
0360399

saattrupdan commited on

fix: Ensure different colours, remove Faroese
81fc601

saattrupdan commited on

feat: Use t-tests to determine win ratios
9a46da5

saattrupdan commited on

feat: Add scaling sliders of plot
65f7993

saattrupdan commited on

feat: Fix the stacking order of the models
e5b38af

saattrupdan commited on

feat: Add `show_scale`, default False
a4a8904

saattrupdan commited on

feat: Change layout, fix task order, fix colours for models, fix range
76e4363

saattrupdan commited on

feat: Set GPT-4 as default
3e57038

saattrupdan commited on

fix: Default dropdown choices of models
c878c57

saattrupdan commited on

chore: Update logging message
7b43a09

saattrupdan commited on

fix: Allow languages that do not have all tasks
9b382e3

saattrupdan commited on

fix: Keep the selected models if they're valid. Add more logging
bd0b666

saattrupdan commited on

chore: Change logging format
b1d592c

saattrupdan commited on

Merge branch 'main' of https://huggingface.co/spaces/alexandrainst/radial-plot
6e9f4fc

saattrupdan commited on

feat: Update with new results every 30 mins
3baf99a

saattrupdan commited on

Update README.md
949e1de
verified

saattrupdan commited on

Update README.md
681e4e0
verified

saattrupdan commited on

fix: Bug when `model_id` isnt in `results_dfs_filtered`
8b5abf6

saattrupdan commited on

fix: Bugs related to filtering, change theme, add descriptions
d05d9d8

saattrupdan commited on

feat: Initial commit
1ef58ee

saattrupdan commited on

initial commit
1c2b5d0
verified

saattrupdan commited on