Commit History
added introduction
3a6dcfd
added introduction
6f46f59
added all the metrics
74baf0e
added third statistic
f2ccb21
added own requests
81cd678
added own requests
ffbbfd6
added own requests
d697a82
Try'ng w'th other dataset
4e23ba0
Try'ng w'th other dataset
f719d95
Try'ng w'th other dataset
caec8fc
Try'ng w'th other dataset
7bfa588
Try'ng w'th other dataset
4702c37
First duplicate push§
e68d4bb
update read
943f952
Clémentine
commited on
fixs
314f91a
Clémentine
commited on
fix
1257fc3
Clémentine
commited on
updated leaderboard
efeee6d
Clémentine
commited on
Simplified leaderboard v0
9833cdb
Clémentine
commited on
adding pull back
d084b26
Clémentine
commited on
simplified some parts of the code + updated requirements
9d22eee
Clémentine
commited on
Added check on tokenizer to prevent submissions which won't run
7302987
Clémentine
commited on
Update benchmark count and fix typo (`inetuning->finetuning`) (#395)
7abc6a7
Update README.md
96d111a
make faster thanks to no concurrency limit
d4aa996
Clémentine
commited on
fix order of request file vs request file list, to avoid resubmitting issues
976f398
Clémentine
commited on
cache
4ff9eef
Clémentine
commited on
update for caching
395eff6
Clémentine
commited on
simplify launcher + remove dataframe warning on boolean columns
ab6f548
Clémentine
commited on
add model architecture as column
3dfaf22
Clémentine
commited on
Simplify About
eaace79
Clémentine
commited on
Try concurrency management
bb149ba
Clémentine
commited on
up sdk
d45f810
Clémentine
commited on
fix
be0d7e4
Clémentine
commited on
Refactor 2 - added plotting back
b1a1395
Clémentine
commited on
fix value error in param size
ccefec9
Clémentine
commited on
Fix requirements for mistral models - to change once transformers gets updated.
002172c
Clémentine
commited on
Update app.py
a163e5c
req
c5938bb
Clémentine
commited on
fix
9f11b58
Clémentine
commited on
req
5b347f5
Clémentine
commited on
fix col width
fc1e99b
Clémentine
commited on
refacto style + rate limit
df66f6e
Clémentine
commited on
Fix TruthfulQA NaN scores to 0
bb17be3
Clémentine
commited on
adding collections back
ae85651
Clémentine
commited on
refacto part 1
2a5f9fb
Clémentine
commited on
add new evals to the leaderboard
e3aaf53
Nathan Habib
commited on
add safefail for when we cannot download datasets, will simply restart the space
26286b2
Nathan Habib
commited on
token for checking gated base models
f3cda22
Clémentine
commited on
simplify deps for pip
f69c85c
Clémentine
commited on