Path Lines of Code LICENSE.md 17 README.md 350 examples/lm-eval-overview.ipynb 1230 examples/visualize-wandb.ipynb 170 examples/visualize-zeno.ipynb 115 ignore.txt 8 lm_eval/tasks/README.md 115 lm_eval/tasks/aclue/README.md 36 lm_eval/tasks/aexams/README.md 35 lm_eval/tasks/afrimgsm/README.md 39 lm_eval/tasks/afrimmlu/README.md 37 lm_eval/tasks/afrixnli/README.md 44 lm_eval/tasks/agieval/README.md 95 lm_eval/tasks/alghafa/copa_ar/README.md 22 lm_eval/tasks/alghafa/piqa_ar/README.md 26 lm_eval/tasks/anli/README.md 40 lm_eval/tasks/arc/README.md 39 lm_eval/tasks/arc_mt/README.md 9 lm_eval/tasks/arithmetic/README.md 44 lm_eval/tasks/asdiv/README.md 38 lm_eval/tasks/babi/README.md 31 lm_eval/tasks/basqueglue/README.md 53 lm_eval/tasks/bbh/README.md 37 lm_eval/tasks/belebele/README.md 33 lm_eval/tasks/benchmarks/multimedqa/README.md 34 lm_eval/tasks/blimp/README.md 39 lm_eval/tasks/ceval/README.md 103 lm_eval/tasks/cmmlu/README.md 33 lm_eval/tasks/commonsense_qa/README.md 43 lm_eval/tasks/copal_id/README.md 30 lm_eval/tasks/coqa/README.md 27 lm_eval/tasks/drop/README.md 36 lm_eval/tasks/eq_bench/README.md 35 lm_eval/tasks/eus_exams/README.md 32 lm_eval/tasks/eus_proficiency/README.md 31 lm_eval/tasks/eus_reading/README.md 31 lm_eval/tasks/eus_trivia/README.md 36 lm_eval/tasks/fda/README.md 57 lm_eval/tasks/fld/README.md 47 lm_eval/tasks/french_bench/README.md 72 lm_eval/tasks/glianorex/README.md 11 lm_eval/tasks/gsm8k/README.md 44 lm_eval/tasks/headqa/README.md 41 lm_eval/tasks/hellaswag/README.md 31 lm_eval/tasks/hendrycks_ethics/README.md 39 lm_eval/tasks/hendrycks_math/README.md 38 lm_eval/tasks/ifeval/README.md 29 lm_eval/tasks/kobest/README.md 24 lm_eval/tasks/kormedmcqa/README.md 30 lm_eval/tasks/lambada/README.md 27 lm_eval/tasks/lambada_cloze/README.md 39 lm_eval/tasks/lambada_multilingual/README.md 35 lm_eval/tasks/lambada_multilingual_stablelm/README.md 41 lm_eval/tasks/leaderboard/README.md 254 lm_eval/tasks/logiqa/README.md 35 lm_eval/tasks/logiqa2/README.md 35 lm_eval/tasks/mathqa/README.md 35 lm_eval/tasks/mc_taco/README.md 35 lm_eval/tasks/med_concepts_qa/README.md 27 lm_eval/tasks/mgsm/README.md 75 lm_eval/tasks/minerva_math/README.md 47 lm_eval/tasks/mmlusr/README.md 42 lm_eval/tasks/mutual/README.md 32 lm_eval/tasks/noticia/README.md 35 lm_eval/tasks/nq_open/README.md 16 lm_eval/tasks/openbookqa/README.md 37 lm_eval/tasks/paloma/README.md 50 lm_eval/tasks/paws-x/README.md 54 lm_eval/tasks/pile/README.md 54 lm_eval/tasks/pile_10k/README.md 28 lm_eval/tasks/piqa/README.md 36 lm_eval/tasks/polemo2/README.md 40 lm_eval/tasks/prost/README.md 44 lm_eval/tasks/pubmedqa/README.md 39 lm_eval/tasks/qa4mre/README.md 38 lm_eval/tasks/qasper/README.md 47 lm_eval/tasks/race/README.md 45 lm_eval/tasks/sciq/README.md 32 lm_eval/tasks/scrolls/README.md 24 lm_eval/tasks/squad_completion/README.md 36 lm_eval/tasks/squadv2/README.md 38 lm_eval/tasks/storycloze/README.md 39 lm_eval/tasks/super_glue/README.md 60 lm_eval/tasks/swag/README.md 35 lm_eval/tasks/tinyBenchmarks/README.md 91 lm_eval/tasks/tmmluplus/README.md 29 lm_eval/tasks/toxigen/README.md 29 lm_eval/tasks/translation/README.md 24 lm_eval/tasks/triviaqa/README.md 35 lm_eval/tasks/truthfulqa/README.md 38 lm_eval/tasks/unitxt/README.md 52 lm_eval/tasks/unscramble/README.md 41 lm_eval/tasks/webqs/README.md 40 lm_eval/tasks/wikitext/README.md 32 lm_eval/tasks/winogrande/README.md 36 lm_eval/tasks/wmt2016/README.md 33 lm_eval/tasks/wsc273/README.md 42 lm_eval/tasks/xcopa/README.md 43 lm_eval/tasks/xnli/README.md 57 lm_eval/tasks/xstorycloze/README.md 66 lm_eval/tasks/xwinograd/README.md 45 mypy.ini 22 pile_statistics.json 37 requirements.txt 1 scripts/clean_training_data/README.md 30 templates/new_yaml_task/README.md 27