LICENSE.md
README.md
setup.py
lm_eval/__init__.py
lm_eval/base.py
lm_eval/evaluator.py
lm_eval/metrics.py
lm_eval/utils.py
lm_eval.egg-info/PKG-INFO
lm_eval.egg-info/SOURCES.txt
lm_eval.egg-info/dependency_links.txt
lm_eval.egg-info/requires.txt
lm_eval.egg-info/top_level.txt
lm_eval/models/__init__.py
lm_eval/models/dummy.py
lm_eval/models/gpt2.py
lm_eval/models/gpt3.py
lm_eval/tasks/__init__.py
lm_eval/tasks/anli.py
lm_eval/tasks/arc.py
lm_eval/tasks/arithmetic.py
lm_eval/tasks/blimp.py
lm_eval/tasks/cbt.py
lm_eval/tasks/common.py
lm_eval/tasks/coqa.py
lm_eval/tasks/drop.py
lm_eval/tasks/glue.py
lm_eval/tasks/headqa.py
lm_eval/tasks/hellaswag.py
lm_eval/tasks/hendrycks_ethics.py
lm_eval/tasks/hendrycks_math.py
lm_eval/tasks/hendrycks_test.py
lm_eval/tasks/lambada.py
lm_eval/tasks/lambada_cloze.py
lm_eval/tasks/lambada_multilingual.py
lm_eval/tasks/logiqa.py
lm_eval/tasks/mathqa.py
lm_eval/tasks/mc_taco.py
lm_eval/tasks/mutual.py
lm_eval/tasks/naturalqs.py
lm_eval/tasks/openbookqa.py
lm_eval/tasks/pile.py
lm_eval/tasks/piqa.py
lm_eval/tasks/prost.py
lm_eval/tasks/pubmedqa.py
lm_eval/tasks/qa4mre.py
lm_eval/tasks/quac.py
lm_eval/tasks/race.py
lm_eval/tasks/sat.py
lm_eval/tasks/sciq.py
lm_eval/tasks/squad.py
lm_eval/tasks/storycloze.py
lm_eval/tasks/superglue.py
lm_eval/tasks/translation.py
lm_eval/tasks/triviaqa.py
lm_eval/tasks/truthfulqa.py
lm_eval/tasks/unscramble.py
lm_eval/tasks/webqs.py
lm_eval/tasks/wikitext.py
lm_eval/tasks/winogrande.py
lm_eval/tasks/wsc273.py
scripts/__init__.py
scripts/cost_estimate.py
scripts/fewshot_description_experiment.py
scripts/get_prompts.py
scripts/make_gpt2_test_cases.py
scripts/make_table_tasks.py
scripts/write_out.py
scripts/clean_training_data/__init__.py
scripts/clean_training_data/archiver.py
scripts/clean_training_data/generate_13_grams.py
scripts/clean_training_data/janitor.py
scripts/clean_training_data/process_sorted_buckets.py
scripts/clean_training_data/sort_13_gram_buckets.py