open_pl_llm_leaderboard

Restarting on CPU Upgrade

App Files Files Community

open_pl_llm_leaderboard

Commit History

show perplexity for 5-shot too

91765f5

djstrong commited on Mar 26

update description

39d6a74

djstrong commited on Mar 25

keep old Average

96fbe7c

djstrong commited on Mar 25

normalize scores to majority class baseline

1bea7de

djstrong commited on Mar 25

polqa in avg

665a818

djstrong commited on Mar 25

sort results by date

b521fe9

djstrong commited on Mar 25

enable text select

11f89d3

djstrong commited on Mar 21

add polqa tasks

9655a7c

djstrong commited on Mar 20

baseline type

68bbe4a

djstrong commited on Mar 19

change bele task

b5aa7e1

djstrong commited on Mar 18

revert to 0

d488d58

djstrong commited on Mar 18

print missing metadata models

45fa708

djstrong commited on Mar 18

add perplexity info

6d3b503

djstrong commited on Mar 18

add perplexity

0d2a785

djstrong commited on Mar 18

disable unused code

331e613

djstrong commited on Mar 18

set precision

bddad3e

djstrong commited on Mar 17

lang

918265b

djstrong commited on Mar 10

disable requests

b5cbc31

djstrong commited on Mar 10

add metadata and filters

ed33da8

djstrong commited on Mar 10

tasks descriptions

36e06b6

djstrong commited on Mar 8

remove dtype

ccd6234

djstrong commited on Mar 5

move to speakleash

1602bff

djstrong commited on Mar 5

remove trust remote code

92530b5

djstrong commited on Mar 5

speakleash

1be4fc9

djstrong commited on Mar 4

model name links

e03efff

djstrong commited on Mar 4

gradient working

f7bb3a0

djstrong commited on Mar 3

model name width

647e0eb

djstrong commited on Mar 3

citation

24cd81f

djstrong commited on Mar 3

update metrics to f1

11d1872

djstrong commited on Mar 3

enable scroll

f108808

djstrong commited on Mar 2

tests

07a9845

djstrong commited on Mar 2

tests

c20dc0b

djstrong commited on Mar 2

tests

2bc9ba2

djstrong commited on Mar 2

tests

09af846

djstrong commited on Mar 2

tests

d885a59

djstrong commited on Mar 2

desc

2699972

djstrong commited on Mar 2

change model name

ea6148c

djstrong commited on Mar 2

spichlerz org

2a37ba0

djstrong commited on Mar 2

more info

705e23f

djstrong commited on Mar 1

move filters

59e91d5

djstrong commited on Feb 29

fix search

8a3bdad

djstrong commited on Feb 29

disable not working filters

45d02c6

djstrong commited on Feb 29

metrics description

149e41e

djstrong commited on Feb 27

more info

3c5ea13

djstrong commited on Feb 25

clickable condition

1889818

djstrong commited on Feb 25

n-shot filter

d2d2329

djstrong commited on Feb 24

n-shot filter

59f4209

djstrong commited on Feb 24

n-shot filter

6cd6b86

djstrong commited on Feb 24

n-shot filter

1d87935

djstrong commited on Feb 24

add n-shot param

3bb301b

djstrong commited on Feb 24

Commit History

show perplexity for 5-shot too 91765f5

update description 39d6a74

keep old Average 96fbe7c

normalize scores to majority class baseline 1bea7de

polqa in avg 665a818

sort results by date b521fe9

enable text select 11f89d3

add polqa tasks 9655a7c

baseline type 68bbe4a

change bele task b5aa7e1

revert to 0 d488d58

print missing metadata models 45fa708

add perplexity info 6d3b503

add perplexity 0d2a785

disable unused code 331e613

set precision bddad3e

lang 918265b

disable requests b5cbc31

add metadata and filters ed33da8

tasks descriptions 36e06b6

remove dtype ccd6234

move to speakleash 1602bff

remove trust remote code 92530b5

speakleash 1be4fc9

model name links e03efff

gradient working f7bb3a0

model name width 647e0eb

citation 24cd81f

update metrics to f1 11d1872

enable scroll f108808

tests 07a9845

tests c20dc0b

tests 2bc9ba2

tests 09af846

tests d885a59

desc 2699972

change model name ea6148c

spichlerz org 2a37ba0

more info 705e23f

move filters 59e91d5

fix search 8a3bdad

disable not working filters 45d02c6

metrics description 149e41e

more info 3c5ea13

clickable condition 1889818

n-shot filter d2d2329

n-shot filter 59f4209

n-shot filter 6cd6b86

n-shot filter 1d87935

add n-shot param 3bb301b

show perplexity for 5-shot too

91765f5

update description

39d6a74

keep old Average

96fbe7c

normalize scores to majority class baseline

1bea7de

polqa in avg

665a818

sort results by date

b521fe9

enable text select

11f89d3

add polqa tasks

9655a7c

baseline type

68bbe4a

change bele task

b5aa7e1

revert to 0

d488d58

print missing metadata models

45fa708

add perplexity info

6d3b503

add perplexity

0d2a785

disable unused code

331e613

set precision

bddad3e

lang

918265b

disable requests

b5cbc31

add metadata and filters

ed33da8

tasks descriptions

36e06b6

remove dtype

ccd6234

move to speakleash

1602bff

remove trust remote code

92530b5

speakleash

1be4fc9

model name links

e03efff

gradient working

f7bb3a0

model name width

647e0eb

citation

24cd81f

update metrics to f1

11d1872

enable scroll

f108808

tests

07a9845

tests

c20dc0b

tests

2bc9ba2

tests

09af846

tests

d885a59

desc

2699972

change model name

ea6148c

spichlerz org

2a37ba0

more info

705e23f

move filters

59e91d5

fix search

8a3bdad

disable not working filters

45d02c6

metrics description

149e41e

more info

3c5ea13

clickable condition

1889818

n-shot filter

d2d2329

n-shot filter

59f4209

n-shot filter

6cd6b86

n-shot filter

1d87935

add n-shot param

3bb301b