Commit History

keep old Average
96fbe7c

djstrong commited on

normalize scores to majority class baseline
1bea7de

djstrong commited on

polqa in avg
665a818

djstrong commited on

sort results by date
b521fe9

djstrong commited on

enable text select
11f89d3

djstrong commited on

add polqa tasks
9655a7c

djstrong commited on

baseline type
68bbe4a

djstrong commited on

change bele task
b5aa7e1

djstrong commited on

revert to 0
d488d58

djstrong commited on

print missing metadata models
45fa708

djstrong commited on

add perplexity info
6d3b503

djstrong commited on

add perplexity
0d2a785

djstrong commited on

disable requests
b5cbc31

djstrong commited on

add metadata and filters
ed33da8

djstrong commited on

tasks descriptions
36e06b6

djstrong commited on

remove dtype
ccd6234

djstrong commited on

move to speakleash
1602bff

djstrong commited on

remove trust remote code
92530b5

djstrong commited on

speakleash
1be4fc9

djstrong commited on

model name links
e03efff

djstrong commited on

model name width
647e0eb

djstrong commited on

update metrics to f1
11d1872

djstrong commited on

enable scroll
f108808

djstrong commited on

change model name
ea6148c

djstrong commited on

spichlerz org
2a37ba0

djstrong commited on

more info
705e23f

djstrong commited on

disable not working filters
45d02c6

djstrong commited on

metrics description
149e41e

djstrong commited on

more info
3c5ea13

djstrong commited on

clickable condition
1889818

djstrong commited on

n-shot filter
d2d2329

djstrong commited on

n-shot filter
1d87935

djstrong commited on

add n-shot param
3bb301b

djstrong commited on

add 5-shot
1f30b67

djstrong commited on

0-shot description
d6e3be2

djstrong commited on

only 0-shot
a8630b1

djstrong commited on

simplify model names
b15949c

djstrong commited on

simplify task names
f4bd2ee

djstrong commited on

change name
e279549

djstrong commited on