Spaces:

fair-forward
/

evals-for-every-language

Running

App Files Files Community

evals-for-every-language / evals /tasks.py

Commit History

Upload from GitHub Actions: Ugly fix for CI errors

adc94d7
verified

davidpomerenke commited on about 11 hours ago

Upload from GitHub Actions: Try moving `cache` calls that cause CI issues

bc4afa0
verified

davidpomerenke commited on about 12 hours ago

Temporarily disable classification task

a48ff53

David Pomerenke commited on 7 days ago

Only run tasks for which there is no result yet

2f9dee1

David Pomerenke commited on 8 days ago

Run on 40 languages, additional models

260c1a3

David Pomerenke commited on 15 days ago

Shorter classification prompt + error handling

0384b92

David Pomerenke commited on 15 days ago

Implement MMLU task

a683732

David Pomerenke commited on 24 days ago

MMLU data loader for 3 parallel datasets

47170a5

David Pomerenke commited on 24 days ago

Add Global MMLU benchmark

ce2acb0

David Pomerenke commited on 25 days ago

Translation both from and to

731eddd

David Pomerenke commited on 29 days ago

Run on 100 languages, adjust display

8274634

David Pomerenke commited on Apr 6

spBLEU tokenizer, run on more languages

eaf2d97

David Pomerenke commited on Mar 25

Refactor eval code into files

da6e1bc

David Pomerenke commited on Mar 15

Commit History

Upload from GitHub Actions: Ugly fix for CI errors adc94d7 verified

Upload from GitHub Actions: Try moving `cache` calls that cause CI issues bc4afa0 verified

Temporarily disable classification task a48ff53

Only run tasks for which there is no result yet 2f9dee1

Run on 40 languages, additional models 260c1a3

Shorter classification prompt + error handling 0384b92

Implement MMLU task a683732

MMLU data loader for 3 parallel datasets 47170a5

Add Global MMLU benchmark ce2acb0

Translation both from and to 731eddd

Run on 100 languages, adjust display 8274634

spBLEU tokenizer, run on more languages eaf2d97

Refactor eval code into files da6e1bc