Spaces:

open-llm-leaderboard
/

comparator

Running

App Files Files Community

comparator / src /results.py

Commit History

Fix loading message in case of timeout error

966ae7b

Running
verified

albertvillanova HF staff commited on 9 days ago

Make the code robust against HTTP errors

719c272
verified

albertvillanova HF staff commited on 10 days ago

Support comparing model tree generations

523fad9
verified

albertvillanova HF staff commited on 10 days ago

Fix load_results for None data frames

96f60e1
verified

albertvillanova HF staff commited on 15 days ago

Set result_paths_per_model as State

729af67
verified

albertvillanova HF staff commited on 15 days ago

Minor fix

e7f29e1
verified

albertvillanova HF staff commited on 15 days ago

Support more than 2 models

bea7063
verified

albertvillanova HF staff commited on 17 days ago

Hide MATH fewshot_config.samples with memory address

22fb9eb
verified

albertvillanova HF staff commited on 17 days ago

Fix style

31903af
verified

albertvillanova HF staff commited on 21 days ago

Add Download button

b1b50fb
verified

albertvillanova HF staff commited on 22 days ago

Avoid bug with radar plot

9ade1c2
verified

albertvillanova HF staff commited on 23 days ago

Plot also radar

a56da8a
verified

albertvillanova HF staff commited on 24 days ago

Plot with plotly

2b1d96b
verified

albertvillanova HF staff commited on 24 days ago

Plot Results

07db628
verified

albertvillanova HF staff commited on 24 days ago

Extract concat_results function

ea4c670
verified

albertvillanova HF staff commited on 24 days ago

Refactor glob to use the cache of HfFileSystem

7e32ac7
verified

albertvillanova HF staff commited on 27 days ago

Rename load file functions

fae0e19
verified

albertvillanova HF staff commited on 28 days ago

Change colormap to PiYG

41fbe9f
verified

albertvillanova HF staff commited on 29 days ago

Rename to Hide Standard Errors

585c3fa
verified

albertvillanova HF staff commited on 29 days ago

Use color map for Results metrics values

581682a
verified

albertvillanova HF staff commited on 29 days ago

Add checkbox in Configs to show only differences

f12aa56
verified

albertvillanova HF staff commited on 29 days ago

Add checkbox in Results to hide stderr

54e105e
verified

albertvillanova HF staff commited on 29 days ago

Fix style

611a3ed
verified

albertvillanova HF staff commited on 30 days ago

Escape HTML tags in data

bd64e7a
verified

albertvillanova HF staff commited on about 1 month ago

Display loading message

8f7c83f
verified

albertvillanova HF staff commited on about 1 month ago

Import contants as submodule

30a0c61
verified

albertvillanova HF staff commited on about 1 month ago

Use magenta instead of red color

33d0dfb
verified

albertvillanova HF staff commited on about 1 month ago

Load results asynchronously

d0f55c6
verified

albertvillanova HF staff commited on about 1 month ago

Remove unnecessary iteration

da4a3b1
verified

albertvillanova HF staff commited on about 1 month ago

Remove ARC task by hiding from All

6099782
verified

albertvillanova HF staff commited on Oct 14

Highlight exact_match and change colors

a4b20f4
verified

albertvillanova HF staff commited on Oct 11

Highlight min/max Results accuracy

26e855f
verified

albertvillanova HF staff commited on Oct 11

Fix missing results by reading all files

8e404a5
verified

albertvillanova HF staff commited on Oct 11

Put Results and Configs tabs at top level and sync

9c39267
verified

albertvillanova HF staff commited on Oct 11

Make Results tasks (in)visible

bf6ab81
verified

albertvillanova HF staff commited on Oct 11

Fix latest_result_path_per_model variable and refactor

c2c9efa
verified

albertvillanova HF staff commited on Oct 11

Fix fs variable

460930f
verified

albertvillanova HF staff commited on Oct 11

Create src.results module

15c8167
verified

albertvillanova HF staff commited on Oct 10