README.md
setup.cfg
setup.py
bigbench/__init__.py
bigbench/evaluate_task.py
bigbench.egg-info/PKG-INFO
bigbench.egg-info/SOURCES.txt
bigbench.egg-info/dependency_links.txt
bigbench.egg-info/requires.txt
bigbench.egg-info/top_level.txt
bigbench/api/__init__.py
bigbench/api/analysis.py
bigbench/api/conftest.py
bigbench/api/json_task.py
bigbench/api/json_utils.py
bigbench/api/model.py
bigbench/api/results.py
bigbench/api/task.py
bigbench/api/task_metrics.py
bigbench/api/test_json_utils.py
bigbench/api/test_task_metrics.py
bigbench/api/test_tasks.py
bigbench/api/test_util.py
bigbench/api/util.py
bigbench/bbseqio/__init__.py
bigbench/bbseqio/bigbench_bridge.py
bigbench/bbseqio/bigbench_bridge_test.py
bigbench/bbseqio/bigbench_json_paths.py
bigbench/bbseqio/bigbench_json_paths_test.py
bigbench/bbseqio/bigbench_lite.py
bigbench/bbseqio/compatibility_test.py
bigbench/bbseqio/run_example.py
bigbench/bbseqio/task_api.py
bigbench/bbseqio/task_api_test.py
bigbench/bbseqio/tasks.py
bigbench/bbseqio/test_utils.py
bigbench/bbseqio/utils.py
bigbench/bbseqio/utils_test.py
bigbench/bbseqio/vocabs.py
bigbench/bbseqio/tools/__init__.py
bigbench/bbseqio/tools/seqio_task_catalog_generator_main.py
bigbench/bbseqio/tools/utils.py
bigbench/benchmark_tasks/__init__.py
bigbench/benchmark_tasks/generate_benchmark_stat_figures.py
bigbench/benchmark_tasks/generate_task_headers.py
bigbench/benchmark_tasks/generate_task_summaries.py
bigbench/benchmark_tasks/parse_author_emails.py
bigbench/benchmark_tasks/abstract_narrative_understanding/utils.py
bigbench/benchmark_tasks/abstraction_and_reasoning_corpus/task.py
bigbench/benchmark_tasks/arithmetic/generate_examples.py
bigbench/benchmark_tasks/bbq_lite/task.py
bigbench/benchmark_tasks/bias_from_probabilities/task.py
bigbench/benchmark_tasks/boolean_expressions/task.py
bigbench/benchmark_tasks/cause_and_effect/convert_to_because_sentences.py
bigbench/benchmark_tasks/chess_state_tracking/scripts/generate_synthetic_games.py
bigbench/benchmark_tasks/chess_state_tracking/scripts/generate_tasks.py
bigbench/benchmark_tasks/chess_state_tracking/scripts/parse_lichess.py
bigbench/benchmark_tasks/com2sense/task.py
bigbench/benchmark_tasks/context_definition_alignment/task.py
bigbench/benchmark_tasks/context_definition_alignment/test.py
bigbench/benchmark_tasks/convinceme/task.py
bigbench/benchmark_tasks/coqa_conversational_question_answering/coqa_official_evaluation_script.py
bigbench/benchmark_tasks/coqa_conversational_question_answering/task.py
bigbench/benchmark_tasks/cycled_letters/generate_word_list.py
bigbench/benchmark_tasks/cycled_letters/task.py
bigbench/benchmark_tasks/cycled_letters/valid_cycle_words.py
bigbench/benchmark_tasks/diverse_social_bias/task.py
bigbench/benchmark_tasks/dynamic_counting/task.py
bigbench/benchmark_tasks/factuality_of_summary/task.py
bigbench/benchmark_tasks/forecasting_subquestions/make_prompt.py
bigbench/benchmark_tasks/forecasting_subquestions/task.py
bigbench/benchmark_tasks/gender_sensitivity_chinese/task.py
bigbench/benchmark_tasks/gender_sensitivity_english/task.py
bigbench/benchmark_tasks/high_low_game/task.py
bigbench/benchmark_tasks/intersect_geometry/generate_data.py
bigbench/benchmark_tasks/intersect_geometry/generate_one_example_point.py
bigbench/benchmark_tasks/linguistic_mappings/de_past_tense/task.py
bigbench/benchmark_tasks/linguistic_mappings/past_tense/task.py
bigbench/benchmark_tasks/linguistic_mappings/plural/task.py
bigbench/benchmark_tasks/linguistic_mappings/pronoun_replacement/task.py
bigbench/benchmark_tasks/linguistic_mappings/question_formation/task.py
bigbench/benchmark_tasks/linguistic_mappings/question_formation_json/make_json.py
bigbench/benchmark_tasks/linguistic_mappings/sentence_negation/task.py
bigbench/benchmark_tasks/long_context_integration/task.py
bigbench/benchmark_tasks/multistep_arithmetic/task.py
bigbench/benchmark_tasks/muslim_violence_bias/task.py
bigbench/benchmark_tasks/object_counting/generate_task.py
bigbench/benchmark_tasks/program_synthesis/task.py
bigbench/benchmark_tasks/program_synthesis/test.py
bigbench/benchmark_tasks/protein_interacting_sites/task.py
bigbench/benchmark_tasks/python_programming_challenge/challenge.py
bigbench/benchmark_tasks/python_programming_challenge/challenge_definitions.py
bigbench/benchmark_tasks/python_programming_challenge/print_challenges.py
bigbench/benchmark_tasks/python_programming_challenge/restricted_builtins.py
bigbench/benchmark_tasks/python_programming_challenge/sandbox.py
bigbench/benchmark_tasks/python_programming_challenge/task.py
bigbench/benchmark_tasks/python_programming_challenge/test.py
bigbench/benchmark_tasks/python_programming_challenge/test_solutions.py
bigbench/benchmark_tasks/question_answer_creation/qa_creation_class.py
bigbench/benchmark_tasks/question_answer_creation/task.py
bigbench/benchmark_tasks/roots_optimization_and_games/task.py
bigbench/benchmark_tasks/self_awareness/task.py
bigbench/benchmark_tasks/self_awareness/test.py
bigbench/benchmark_tasks/self_evaluation_courtroom/cases.py
bigbench/benchmark_tasks/self_evaluation_courtroom/task.py
bigbench/benchmark_tasks/self_evaluation_tutoring/task.py
bigbench/benchmark_tasks/simple_arithmetic/task.py
bigbench/benchmark_tasks/simple_arithmetic/test.py
bigbench/benchmark_tasks/spelling_bee/spelling_bee_game.py
bigbench/benchmark_tasks/spelling_bee/task.py
bigbench/benchmark_tasks/spelling_bee/test.py
bigbench/benchmark_tasks/sports_understanding/generate_tasks.py
bigbench/benchmark_tasks/squad_shifts/task.py
bigbench/benchmark_tasks/subject_verb_agreement/task.py
bigbench/benchmark_tasks/sudoku/sudoku.py
bigbench/benchmark_tasks/sudoku/task.py
bigbench/benchmark_tasks/sudoku/test.py
bigbench/benchmark_tasks/taboo/task.py
bigbench/benchmark_tasks/talkdown/task.py
bigbench/benchmark_tasks/text_navigation_game/task.py
bigbench/benchmark_tasks/training_on_test_set/task.py
bigbench/benchmark_tasks/truthful_qa/task.py
bigbench/benchmark_tasks/twenty_questions/task.py
bigbench/benchmark_tasks/unit_conversion/task_generation/unit_math_tasks.py
bigbench/benchmark_tasks/unqover/analysis.py
bigbench/benchmark_tasks/unqover/lists.py
bigbench/benchmark_tasks/unqover/task.py
bigbench/benchmark_tasks/unqover/underspecified_templates.py
bigbench/benchmark_tasks/vitaminc_fact_verification/convert_to_lm_format.py
bigbench/benchmark_tasks/web_of_lies/task.py
bigbench/benchmark_tasks/word_problems_on_sets_and_graphs/__init__.py
bigbench/benchmark_tasks/word_problems_on_sets_and_graphs/acquaintances.py
bigbench/benchmark_tasks/word_problems_on_sets_and_graphs/fruitbasket.py
bigbench/benchmark_tasks/word_problems_on_sets_and_graphs/studentclasses.py
bigbench/benchmark_tasks/word_problems_on_sets_and_graphs/task.py
bigbench/benchmark_tasks/yes_no_black_white/task.py
bigbench/benchmark_tasks/yes_no_black_white/test.py
bigbench/models/__init__.py
bigbench/models/dummy_model.py
bigbench/models/huggingface_models.py
bigbench/models/human_model.py
bigbench/models/json_rpc_model.py
bigbench/models/test_hf_models.py
bigbench/models/turing_text_generator.py