Commit History

updated model param number reader
1df8383

Clémentine commited on

updated version
788108a

Clémentine commited on

added precision for truthfulqa 6 shot
18916e3

Clémentine commited on

fix view
00358b1

Clémentine commited on

moved the submit to a tab since the results are becoming very long
8dfa543

Clémentine commited on

Small fix - we do not want to display models where the MMLU is old with models where the MMLU is new - however, since version is displayed in the results, we keep the files
97b27da

Clémentine commited on

Add details on the datasets for reproducibility (#107)
256c5d3

clefourrier HF staff thomwolf HF staff commited on

Using the new backend
d16cee2

Linker1907 commited on

small fix link Ilyas leaderboard
e868f35

Clémentine commited on

added harness command
d2e8eca

Clémentine commited on

revamp
6e8f400

Clémentine commited on

column fix
d52179b

Clémentine commited on

merge refactor
460d762

Clémentine commited on

Update Vicuna link
a7cba30

sheonhan commited on

Adjust description for TruthfulQA
5601a63

NimaBoscarino commited on

Copy change
ce824ba

sheonhan commited on

Fix elo ratings model links
e05ec6c

sheonhan commited on

Add custom url for second tab
7644705

sheonhan commited on

Still return tab without query params
6a6e05c

sheonhan commited on

Link to discussion with custom url
8cb7546

sheonhan commited on

Update tab button
b5f5045

sheonhan commited on

Update deps
39cc014

sheonhan commited on

Add GPT-4 & human eval tab
0227006

sheonhan commited on

Upload scale-hf-logo.png
9cea2a5

sheonhan commited on

Delete scale-hf-logo.png
74ff6f5

sheonhan commited on

Upload scale-hf-logo.png
adaa4ee

sheonhan commited on

adding citations
e61a555

thomwolf HF staff commited on

Update CHANGELOG
b3f0642

sheonhan commited on

Add search emoji
92ae76d

sheonhan commited on

Search on ENTER
48c5442

sheonhan commited on

Increase concurrency count
f458f0b

sheonhan commited on

import datetime correctly
d35aee2

sheonhan commited on

Fix bullet point about evaluation
3b93b88

sheonhan commited on

Update CHANGELOG
b29b985

sheonhan commited on

record submitted time
8696209

sheonhan commited on

style clean up
aa7c3f4

sheonhan commited on

implements search bar
ffefe11

sheonhan commited on

format utils.py
2102b66

sheonhan commited on

Fix bibtex
d06dc21

sheonhan commited on

Add citation button
2a73469

sheonhan commited on

Simply layout
c131125

sheonhan commited on

clean up vars
4c8dd3c

sheonhan commited on

sync with the internal version
58733e4

sheonhan commited on

Auto-restart every hour
46f8d78

sheonhan commited on

start every 20 minutes
9567fa6

sheonhan commited on

use the same H4_TOKEN for restart
0a3d32f

sheonhan commited on

use BackgroundScheduler to restart space
10f9b3c

sheonhan commited on

rename block to demo
01233b7

sheonhan commited on

sort imports and import BackgroundScheduler
4596a70

sheonhan commited on