Commits · tunis-ai/TunisianEncoderModelsLeaderboard

feat: enhance evaluation system and space management

cec147a

hamzabouajila commited on Aug 5

remove signal from evaluator runner , because it runs only on main thread

f73020a

hamzabouajila commited on Aug 5

remove dockerfile because it is not running both files ,

e92e200

hamzabouajila commited on Aug 5

feat: enhance evaluation queue reliability and add stale job recovery

2f1e30c

hamzabouajila commited on Aug 5

feat: enhance evaluation pipeline and error handling

34052ff

hamzabouajila commited on Aug 4

fix: Correct evaluation result mapping and display

ead2260

hamzabouajila commited on Jul 11

Added traceback import to handle error traces

f12b6ec

hamzabouajila commited on Jul 11

add RESULT_REPO to evaluate file

f54d576

hamzabouajila commited on Jul 8

update evaluator to start if pending models were found

29e54f1

hamzabouajila commited on Jul 8

implement scripts for checking , add logging and update submission and integrate evaluation

742dfc3

hamzabouajila commited on Jul 8

implement evaluation and fix bugs

28e88f2

hamzabouajila commited on Jul 7

add evaluator integration

9d7aae7

hamzabouajila commited on Jul 7

Improve DataFrame handling in leaderboard functions; add debug print for empty DataFrame case

cd16e55

hamzabouajila commited on Jul 7

Refactor AutoEvalColumn usage for consistency and clarity; add debug prints for NaN checks in formatting functions

ed90aae

hamzabouajila commited on Jul 7

Add dependencies for Jupyter support and enhance leaderboard data processing

04dab39

hamzabouajila commited on Jul 6

Refactor leaderboard column definitions to use field defaults for better clarity and maintainability

180ffb5

hamzabouajila commited on Jul 6

Update project configuration and add main entry point

e44a1e5

hamzabouajila commited on Jul 6

Duplicate from demo-leaderboard-backend/leaderboard

a04b287
verified

hamzabouajila

clefourrier HF Staff commited on Jul 6

Spaces:

tunis-ai
/

TunisianEncoderModelsLeaderboard

Sleeping

Commit History

feat: enhance evaluation system and space management

cec147a

remove signal from evaluator runner , because it runs only on main thread

f73020a

remove dockerfile because it is not running both files ,

e92e200

feat: enhance evaluation queue reliability and add stale job recovery

2f1e30c

feat: enhance evaluation pipeline and error handling

34052ff

fix: Correct evaluation result mapping and display

ead2260

Added traceback import to handle error traces

f12b6ec

add RESULT_REPO to evaluate file

f54d576

update evaluator to start if pending models were found

29e54f1

implement scripts for checking , add logging and update submission and integrate evaluation

742dfc3

implement evaluation and fix bugs

28e88f2

add evaluator integration

9d7aae7

Improve DataFrame handling in leaderboard functions; add debug print for empty DataFrame case

cd16e55

Refactor AutoEvalColumn usage for consistency and clarity; add debug prints for NaN checks in formatting functions

ed90aae

Add dependencies for Jupyter support and enhance leaderboard data processing

04dab39

Refactor leaderboard column definitions to use field defaults for better clarity and maintainability

180ffb5

Update project configuration and add main entry point

e44a1e5

Duplicate from demo-leaderboard-backend/leaderboard

a04b287
verified

Commit History

feat: enhance evaluation system and space management cec147a

remove signal from evaluator runner , because it runs only on main thread f73020a

remove dockerfile because it is not running both files , e92e200

feat: enhance evaluation queue reliability and add stale job recovery 2f1e30c

feat: enhance evaluation pipeline and error handling 34052ff

fix: Correct evaluation result mapping and display ead2260

Added traceback import to handle error traces f12b6ec

add RESULT_REPO to evaluate file f54d576

update evaluator to start if pending models were found 29e54f1

implement scripts for checking , add logging and update submission and integrate evaluation 742dfc3

implement evaluation and fix bugs 28e88f2

add evaluator integration 9d7aae7

Improve DataFrame handling in leaderboard functions; add debug print for empty DataFrame case cd16e55

Refactor AutoEvalColumn usage for consistency and clarity; add debug prints for NaN checks in formatting functions ed90aae

Add dependencies for Jupyter support and enhance leaderboard data processing 04dab39

Refactor leaderboard column definitions to use field defaults for better clarity and maintainability 180ffb5

Update project configuration and add main entry point e44a1e5

Duplicate from demo-leaderboard-backend/leaderboard a04b287 verified

feat: enhance evaluation system and space management

cec147a

remove signal from evaluator runner , because it runs only on main thread

f73020a

remove dockerfile because it is not running both files ,

e92e200

feat: enhance evaluation queue reliability and add stale job recovery

2f1e30c

feat: enhance evaluation pipeline and error handling

34052ff

fix: Correct evaluation result mapping and display

ead2260

Added traceback import to handle error traces

f12b6ec

add RESULT_REPO to evaluate file

f54d576

update evaluator to start if pending models were found

29e54f1

implement scripts for checking , add logging and update submission and integrate evaluation

742dfc3

implement evaluation and fix bugs

28e88f2

add evaluator integration

9d7aae7

Improve DataFrame handling in leaderboard functions; add debug print for empty DataFrame case

cd16e55

Refactor AutoEvalColumn usage for consistency and clarity; add debug prints for NaN checks in formatting functions

ed90aae

Add dependencies for Jupyter support and enhance leaderboard data processing

04dab39

Refactor leaderboard column definitions to use field defaults for better clarity and maintainability

180ffb5

Update project configuration and add main entry point

e44a1e5

Duplicate from demo-leaderboard-backend/leaderboard

a04b287
verified