Commits · CZLC/BenCzechMark

Rename the submission date column from Release to Submitted

5928b80

idolezal commited on 16 days ago

Joining the "Historical" category of tasks into the "Reading Comprehension" category

5038cd9

idolezal commited on Nov 13

Update content.py

ba40e06
verified

mfajcik commited on Nov 7

Merge branch 'main' of hf.co:spaces/CZLC/BenCzechMark

2c4907f

idolezal commited on Nov 4

Reduced processing in the critical section

cfb07ff

idolezal commited on Nov 4

Update content.py

feb5abd
verified

mfajcik commited on Oct 24

Update content.py

da8b87f
verified

mfajcik commited on Oct 24

Tuning the duration of some notifications

73f436c

idolezal commited on Oct 24

Upload only when it could be changed

e2d6d6c

idolezal commited on Oct 24

Do not read big JSON file twice

0e8ff48

idolezal commited on Oct 24

More info notifications

9d3d879

idolezal commited on Oct 23

Default sorting of leaderboard is by "average_score"

81fdab8

idolezal commited on Oct 23

Erase the pre-submission after confirmation

8f5c6eb

idolezal commited on Oct 23

For testing purpose improved fake tournament

54b531c

idolezal commited on Oct 23

Locks only on confirmation of submission

2e42a59

idolezal commited on Oct 23

Now only executes the duels that are missing

dfdc202

idolezal commited on Oct 21

Upload to the dataset the map from "submission_id" to "model_title"

8ae0f62

idolezal commited on Oct 15

Packages freezed on the versions in "requirements.txt"

fe41e81

idolezal commited on Oct 15

For debug purpose list pip installed packages

c6b8af5

idolezal commited on Oct 10

Update content.py

d7e0c9e
verified

mfajcik commited on Oct 9

Update content.py

a899f05
verified

mfajcik commited on Oct 7

Update content.py

5d4717f
verified

mfajcik commited on Oct 2

Update content.py

11f7f74
verified

mfajcik commited on Oct 2

Update content.py

889e149
verified

mfajcik commited on Oct 1

Update content.py

dab68b3
verified

mfajcik commited on Oct 1

Update content.py

7d29744
verified

mfajcik commited on Oct 1

More specific task categories

ef3bb57

idolezal commited on Sep 28

More specific task categories

bb503c2

idolezal commited on Sep 27

Removed contaminated tasks from "tasks_metadata.json"

01c6f6b

idolezal commited on Sep 27

Get task names only from "tasks_metadata.json"

387e6ad

idolezal commited on Sep 27

Fix some "source_url" in "tasks_metadata.json"

72a6a07

idolezal commited on Sep 27

Use specified metric for every task

9225102

idolezal commited on Sep 27

Added specified metric for every task in "tasks_metadata.json"

37d296d

idolezal commited on Sep 27

Update sorted list of models in README.md

a658d09

idolezal commited on Sep 20

Prepare to pandas 3.0

c3d760a

idolezal commited on Sep 20

Repeat when connection to check significance server is timed out

7d453b5

idolezal commited on Sep 20

Better check significance server reachable test

1405ed9

idolezal commited on Sep 20

Removed `delete_on_close` parameter, because it's since Python 3.12

c164d65

idolezal commited on Sep 19

Restart space if check significance server is not reachable

34bacde

idolezal commited on Sep 19

Added delimiter between download button and submit button

34e486a

idolezal commited on Sep 19

Added better validation of link to the model

d361e71

idolezal commited on Sep 19

Added category "Overall with details" to dropdown menu

b5d384e

idolezal commited on Sep 17

Show pre-submit leaderboard and model tournament table and buttons for CSV

272c73f

idolezal commited on Sep 17

Reduced loading of pre-submited model JSON file

6762695

idolezal commited on Sep 17

Enabled getting leaderboard and model tournament table and CSV for pre-submit

3b8382c

idolezal commited on Sep 17

For CSV export added "n-shot" attribute

c6d7faa

idolezal commited on Sep 17

Enabled Overall with details, mainly for CSV format

690c597

idolezal commited on Sep 17

Enabled to get Overall for make model_tournament_results_table

acca45a

idolezal commited on Sep 17

Update content.py

95a2c0e
verified

mfajcik commited on Sep 16

Upgraded to the version 4.44.0 of the Gradio SDK

fe161da

idolezal commited on Sep 10

Commit History

Rename the submission date column from Release to Submitted 5928b80

Joining the "Historical" category of tasks into the "Reading Comprehension" category 5038cd9

Update content.py ba40e06 verified

Merge branch 'main' of hf.co:spaces/CZLC/BenCzechMark 2c4907f

Reduced processing in the critical section cfb07ff

Update content.py feb5abd verified

Update content.py da8b87f verified

Tuning the duration of some notifications 73f436c

Upload only when it could be changed e2d6d6c

Do not read big JSON file twice 0e8ff48

More info notifications 9d3d879

Default sorting of leaderboard is by "average_score" 81fdab8

Erase the pre-submission after confirmation 8f5c6eb

For testing purpose improved fake tournament 54b531c

Locks only on confirmation of submission 2e42a59

Now only executes the duels that are missing dfdc202

Upload to the dataset the map from "submission_id" to "model_title" 8ae0f62

Packages freezed on the versions in "requirements.txt" fe41e81

For debug purpose list pip installed packages c6b8af5

Update content.py d7e0c9e verified

Update content.py a899f05 verified

Update content.py 5d4717f verified

Update content.py 11f7f74 verified

Update content.py 889e149 verified

Update content.py dab68b3 verified

Update content.py 7d29744 verified

More specific task categories ef3bb57

More specific task categories bb503c2

Removed contaminated tasks from "tasks_metadata.json" 01c6f6b

Get task names only from "tasks_metadata.json" 387e6ad

Fix some "source_url" in "tasks_metadata.json" 72a6a07

Use specified metric for every task 9225102

Added specified metric for every task in "tasks_metadata.json" 37d296d

Update sorted list of models in README.md a658d09

Prepare to pandas 3.0 c3d760a

Repeat when connection to check significance server is timed out 7d453b5

Better check significance server reachable test 1405ed9

Removed `delete_on_close` parameter, because it's since Python 3.12 c164d65

Restart space if check significance server is not reachable 34bacde

Added delimiter between download button and submit button 34e486a

Added better validation of link to the model d361e71

Added category "Overall with details" to dropdown menu b5d384e

Show pre-submit leaderboard and model tournament table and buttons for CSV 272c73f

Reduced loading of pre-submited model JSON file 6762695

Enabled getting leaderboard and model tournament table and CSV for pre-submit 3b8382c

For CSV export added "n-shot" attribute c6d7faa

Enabled Overall with details, mainly for CSV format 690c597

Enabled to get Overall for make model_tournament_results_table acca45a

Update content.py 95a2c0e verified

Upgraded to the version 4.44.0 of the Gradio SDK fe161da

Rename the submission date column from Release to Submitted

5928b80

Joining the "Historical" category of tasks into the "Reading Comprehension" category

5038cd9

Update content.py

ba40e06
verified

Merge branch 'main' of hf.co:spaces/CZLC/BenCzechMark

2c4907f

Reduced processing in the critical section

cfb07ff

Update content.py

feb5abd
verified

Update content.py

da8b87f
verified

Tuning the duration of some notifications

73f436c

Upload only when it could be changed

e2d6d6c

Do not read big JSON file twice

0e8ff48

More info notifications

9d3d879

Default sorting of leaderboard is by "average_score"

81fdab8

Erase the pre-submission after confirmation

8f5c6eb

For testing purpose improved fake tournament

54b531c

Locks only on confirmation of submission

2e42a59

Now only executes the duels that are missing

dfdc202

Upload to the dataset the map from "submission_id" to "model_title"

8ae0f62

Packages freezed on the versions in "requirements.txt"

fe41e81

For debug purpose list pip installed packages

c6b8af5

Update content.py

d7e0c9e
verified

Update content.py

a899f05
verified

Update content.py

5d4717f
verified

Update content.py

11f7f74
verified

Update content.py

889e149
verified

Update content.py

dab68b3
verified

Update content.py

7d29744
verified

More specific task categories

ef3bb57

More specific task categories

bb503c2

Removed contaminated tasks from "tasks_metadata.json"

01c6f6b

Get task names only from "tasks_metadata.json"

387e6ad

Fix some "source_url" in "tasks_metadata.json"

72a6a07

Use specified metric for every task

9225102

Added specified metric for every task in "tasks_metadata.json"

37d296d

Update sorted list of models in README.md

a658d09

Prepare to pandas 3.0

c3d760a

Repeat when connection to check significance server is timed out

7d453b5

Better check significance server reachable test

1405ed9

Removed `delete_on_close` parameter, because it's since Python 3.12

c164d65

Restart space if check significance server is not reachable

34bacde

Added delimiter between download button and submit button

34e486a

Added better validation of link to the model

d361e71

Added category "Overall with details" to dropdown menu

b5d384e

Show pre-submit leaderboard and model tournament table and buttons for CSV

272c73f

Reduced loading of pre-submited model JSON file

6762695

Enabled getting leaderboard and model tournament table and CSV for pre-submit

3b8382c

For CSV export added "n-shot" attribute

c6d7faa

Enabled Overall with details, mainly for CSV format

690c597

Enabled to get Overall for make model_tournament_results_table

acca45a

Update content.py

95a2c0e
verified

Upgraded to the version 4.44.0 of the Gradio SDK

fe161da