Add files using upload-large-folder tool
Browse filesThis view is limited to 50 files because it contains too many changes. See raw diff
- lm-quant-toolkit/.deps/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/implicatures.yaml +4 -0
- lm-quant-toolkit/.deps/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/international_phonetic_alphabet_nli.yaml +4 -0
- lm-quant-toolkit/.deps/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/kanji_ascii.yaml +4 -0
- lm-quant-toolkit/.deps/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/language_identification.yaml +4 -0
- lm-quant-toolkit/.deps/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/logical_deduction.yaml +4 -0
- lm-quant-toolkit/.deps/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/logical_fallacy_detection.yaml +4 -0
- lm-quant-toolkit/.deps/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/mathematical_induction.yaml +4 -0
- lm-quant-toolkit/.deps/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/metaphor_boolean.yaml +4 -0
- lm-quant-toolkit/.deps/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/metaphor_understanding.yaml +4 -0
- lm-quant-toolkit/.deps/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/misconceptions.yaml +4 -0
- lm-quant-toolkit/.deps/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/misconceptions_russian.yaml +4 -0
- lm-quant-toolkit/.deps/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/mnist_ascii.yaml +4 -0
- lm-quant-toolkit/.deps/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/moral_permissibility.yaml +4 -0
- lm-quant-toolkit/.deps/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/movie_dialog_same_or_different.yaml +4 -0
- lm-quant-toolkit/.deps/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/movie_recommendation.yaml +4 -0
- lm-quant-toolkit/.deps/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/multiemo.yaml +4 -0
- lm-quant-toolkit/.deps/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/navigate.yaml +4 -0
- lm-quant-toolkit/.deps/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/nonsense_words_grammar.yaml +4 -0
- lm-quant-toolkit/.deps/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/novel_concepts.yaml +4 -0
- lm-quant-toolkit/.deps/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/odd_one_out.yaml +4 -0
- lm-quant-toolkit/.deps/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/parsinlu_qa.yaml +4 -0
- lm-quant-toolkit/.deps/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/penguins_in_a_table.yaml +4 -0
- lm-quant-toolkit/.deps/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/periodic_elements.yaml +4 -0
- lm-quant-toolkit/.deps/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/persian_idioms.yaml +4 -0
- lm-quant-toolkit/.deps/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/phrase_relatedness.yaml +4 -0
- lm-quant-toolkit/.deps/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/physical_intuition.yaml +4 -0
- lm-quant-toolkit/.deps/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/physics.yaml +4 -0
- lm-quant-toolkit/.deps/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/play_dialog_same_or_different.yaml +4 -0
- lm-quant-toolkit/.deps/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/presuppositions_as_nli.yaml +4 -0
- lm-quant-toolkit/.deps/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/question_selection.yaml +4 -0
- lm-quant-toolkit/.deps/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/real_or_fake_text.yaml +4 -0
- lm-quant-toolkit/.deps/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/reasoning_about_colored_objects.yaml +4 -0
- lm-quant-toolkit/.deps/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/riddle_sense.yaml +4 -0
- lm-quant-toolkit/.deps/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/ruin_names.yaml +4 -0
- lm-quant-toolkit/.deps/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/salient_translation_error_detection.yaml +4 -0
- lm-quant-toolkit/.deps/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/sentence_ambiguity.yaml +4 -0
- lm-quant-toolkit/.deps/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/similarities_abstraction.yaml +4 -0
- lm-quant-toolkit/.deps/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/simple_ethical_questions.yaml +4 -0
- lm-quant-toolkit/.deps/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/snarks.yaml +4 -0
- lm-quant-toolkit/.deps/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/social_iqa.yaml +4 -0
- lm-quant-toolkit/.deps/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/social_support.yaml +4 -0
- lm-quant-toolkit/.deps/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/sports_understanding.yaml +4 -0
- lm-quant-toolkit/.deps/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/strange_stories.yaml +4 -0
- lm-quant-toolkit/.deps/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/strategyqa.yaml +4 -0
- lm-quant-toolkit/.deps/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/suicide_risk.yaml +4 -0
- lm-quant-toolkit/.deps/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/swahili_english_proverbs.yaml +4 -0
- lm-quant-toolkit/.deps/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/swedish_to_german_proverbs.yaml +4 -0
- lm-quant-toolkit/.deps/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/symbol_interpretation.yaml +4 -0
- lm-quant-toolkit/.deps/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/temporal_sequences.yaml +4 -0
- lm-quant-toolkit/.deps/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/timedial.yaml +4 -0
lm-quant-toolkit/.deps/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/implicatures.yaml
ADDED
|
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
# Generated by utils.py
|
| 2 |
+
dataset_name: implicatures_zero_shot
|
| 3 |
+
include: ../multiple_choice_template_a_yaml
|
| 4 |
+
task: bigbench_implicatures_multiple_choice
|
lm-quant-toolkit/.deps/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/international_phonetic_alphabet_nli.yaml
ADDED
|
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
# Generated by utils.py
|
| 2 |
+
dataset_name: international_phonetic_alphabet_nli_zero_shot
|
| 3 |
+
include: ../multiple_choice_template_a_yaml
|
| 4 |
+
task: bigbench_international_phonetic_alphabet_nli_multiple_choice
|
lm-quant-toolkit/.deps/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/kanji_ascii.yaml
ADDED
|
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
# Generated by utils.py
|
| 2 |
+
dataset_name: kanji_ascii_zero_shot
|
| 3 |
+
include: ../multiple_choice_template_a_yaml
|
| 4 |
+
task: bigbench_kanji_ascii_multiple_choice
|
lm-quant-toolkit/.deps/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/language_identification.yaml
ADDED
|
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
# Generated by utils.py
|
| 2 |
+
dataset_name: language_identification_zero_shot
|
| 3 |
+
include: ../multiple_choice_template_a_yaml
|
| 4 |
+
task: bigbench_language_identification_multiple_choice
|
lm-quant-toolkit/.deps/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/logical_deduction.yaml
ADDED
|
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
# Generated by utils.py
|
| 2 |
+
dataset_name: logical_deduction_zero_shot
|
| 3 |
+
include: ../multiple_choice_template_a_yaml
|
| 4 |
+
task: bigbench_logical_deduction_multiple_choice
|
lm-quant-toolkit/.deps/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/logical_fallacy_detection.yaml
ADDED
|
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
# Generated by utils.py
|
| 2 |
+
dataset_name: logical_fallacy_detection_zero_shot
|
| 3 |
+
include: ../multiple_choice_template_a_yaml
|
| 4 |
+
task: bigbench_logical_fallacy_detection_multiple_choice
|
lm-quant-toolkit/.deps/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/mathematical_induction.yaml
ADDED
|
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
# Generated by utils.py
|
| 2 |
+
dataset_name: mathematical_induction_zero_shot
|
| 3 |
+
include: ../multiple_choice_template_a_yaml
|
| 4 |
+
task: bigbench_mathematical_induction_multiple_choice
|
lm-quant-toolkit/.deps/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/metaphor_boolean.yaml
ADDED
|
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
# Generated by utils.py
|
| 2 |
+
dataset_name: metaphor_boolean_zero_shot
|
| 3 |
+
include: ../multiple_choice_template_a_yaml
|
| 4 |
+
task: bigbench_metaphor_boolean_multiple_choice
|
lm-quant-toolkit/.deps/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/metaphor_understanding.yaml
ADDED
|
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
# Generated by utils.py
|
| 2 |
+
dataset_name: metaphor_understanding_zero_shot
|
| 3 |
+
include: ../multiple_choice_template_a_yaml
|
| 4 |
+
task: bigbench_metaphor_understanding_multiple_choice
|
lm-quant-toolkit/.deps/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/misconceptions.yaml
ADDED
|
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
# Generated by utils.py
|
| 2 |
+
dataset_name: misconceptions_zero_shot
|
| 3 |
+
include: ../multiple_choice_template_a_yaml
|
| 4 |
+
task: bigbench_misconceptions_multiple_choice
|
lm-quant-toolkit/.deps/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/misconceptions_russian.yaml
ADDED
|
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
# Generated by utils.py
|
| 2 |
+
dataset_name: misconceptions_russian_zero_shot
|
| 3 |
+
include: ../multiple_choice_template_a_yaml
|
| 4 |
+
task: bigbench_misconceptions_russian_multiple_choice
|
lm-quant-toolkit/.deps/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/mnist_ascii.yaml
ADDED
|
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
# Generated by utils.py
|
| 2 |
+
dataset_name: mnist_ascii_zero_shot
|
| 3 |
+
include: ../multiple_choice_template_a_yaml
|
| 4 |
+
task: bigbench_mnist_ascii_multiple_choice
|
lm-quant-toolkit/.deps/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/moral_permissibility.yaml
ADDED
|
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
# Generated by utils.py
|
| 2 |
+
dataset_name: moral_permissibility_zero_shot
|
| 3 |
+
include: ../multiple_choice_template_a_yaml
|
| 4 |
+
task: bigbench_moral_permissibility_multiple_choice
|
lm-quant-toolkit/.deps/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/movie_dialog_same_or_different.yaml
ADDED
|
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
# Generated by utils.py
|
| 2 |
+
dataset_name: movie_dialog_same_or_different_zero_shot
|
| 3 |
+
include: ../multiple_choice_template_a_yaml
|
| 4 |
+
task: bigbench_movie_dialog_same_or_different_multiple_choice
|
lm-quant-toolkit/.deps/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/movie_recommendation.yaml
ADDED
|
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
# Generated by utils.py
|
| 2 |
+
dataset_name: movie_recommendation_zero_shot
|
| 3 |
+
include: ../multiple_choice_template_a_yaml
|
| 4 |
+
task: bigbench_movie_recommendation_multiple_choice
|
lm-quant-toolkit/.deps/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/multiemo.yaml
ADDED
|
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
# Generated by utils.py
|
| 2 |
+
dataset_name: multiemo_zero_shot
|
| 3 |
+
include: ../multiple_choice_template_a_yaml
|
| 4 |
+
task: bigbench_multiemo_multiple_choice
|
lm-quant-toolkit/.deps/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/navigate.yaml
ADDED
|
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
# Generated by utils.py
|
| 2 |
+
dataset_name: navigate_zero_shot
|
| 3 |
+
include: ../multiple_choice_template_a_yaml
|
| 4 |
+
task: bigbench_navigate_multiple_choice
|
lm-quant-toolkit/.deps/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/nonsense_words_grammar.yaml
ADDED
|
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
# Generated by utils.py
|
| 2 |
+
dataset_name: nonsense_words_grammar_zero_shot
|
| 3 |
+
include: ../multiple_choice_template_a_yaml
|
| 4 |
+
task: bigbench_nonsense_words_grammar_multiple_choice
|
lm-quant-toolkit/.deps/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/novel_concepts.yaml
ADDED
|
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
# Generated by utils.py
|
| 2 |
+
dataset_name: novel_concepts_zero_shot
|
| 3 |
+
include: ../multiple_choice_template_a_yaml
|
| 4 |
+
task: bigbench_novel_concepts_multiple_choice
|
lm-quant-toolkit/.deps/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/odd_one_out.yaml
ADDED
|
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
# Generated by utils.py
|
| 2 |
+
dataset_name: odd_one_out_zero_shot
|
| 3 |
+
include: ../multiple_choice_template_a_yaml
|
| 4 |
+
task: bigbench_odd_one_out_multiple_choice
|
lm-quant-toolkit/.deps/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/parsinlu_qa.yaml
ADDED
|
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
# Generated by utils.py
|
| 2 |
+
dataset_name: parsinlu_qa_zero_shot
|
| 3 |
+
include: ../multiple_choice_template_a_yaml
|
| 4 |
+
task: bigbench_parsinlu_qa_multiple_choice
|
lm-quant-toolkit/.deps/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/penguins_in_a_table.yaml
ADDED
|
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
# Generated by utils.py
|
| 2 |
+
dataset_name: penguins_in_a_table_zero_shot
|
| 3 |
+
include: ../multiple_choice_template_a_yaml
|
| 4 |
+
task: bigbench_penguins_in_a_table_multiple_choice
|
lm-quant-toolkit/.deps/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/periodic_elements.yaml
ADDED
|
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
# Generated by utils.py
|
| 2 |
+
dataset_name: periodic_elements_zero_shot
|
| 3 |
+
include: ../multiple_choice_template_a_yaml
|
| 4 |
+
task: bigbench_periodic_elements_multiple_choice
|
lm-quant-toolkit/.deps/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/persian_idioms.yaml
ADDED
|
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
# Generated by utils.py
|
| 2 |
+
dataset_name: persian_idioms_zero_shot
|
| 3 |
+
include: ../multiple_choice_template_a_yaml
|
| 4 |
+
task: bigbench_persian_idioms_multiple_choice
|
lm-quant-toolkit/.deps/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/phrase_relatedness.yaml
ADDED
|
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
# Generated by utils.py
|
| 2 |
+
dataset_name: phrase_relatedness_zero_shot
|
| 3 |
+
include: ../multiple_choice_template_a_yaml
|
| 4 |
+
task: bigbench_phrase_relatedness_multiple_choice
|
lm-quant-toolkit/.deps/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/physical_intuition.yaml
ADDED
|
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
# Generated by utils.py
|
| 2 |
+
dataset_name: physical_intuition_zero_shot
|
| 3 |
+
include: ../multiple_choice_template_a_yaml
|
| 4 |
+
task: bigbench_physical_intuition_multiple_choice
|
lm-quant-toolkit/.deps/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/physics.yaml
ADDED
|
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
# Generated by utils.py
|
| 2 |
+
dataset_name: physics_zero_shot
|
| 3 |
+
include: ../multiple_choice_template_a_yaml
|
| 4 |
+
task: bigbench_physics_multiple_choice
|
lm-quant-toolkit/.deps/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/play_dialog_same_or_different.yaml
ADDED
|
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
# Generated by utils.py
|
| 2 |
+
dataset_name: play_dialog_same_or_different_zero_shot
|
| 3 |
+
include: ../multiple_choice_template_a_yaml
|
| 4 |
+
task: bigbench_play_dialog_same_or_different_multiple_choice
|
lm-quant-toolkit/.deps/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/presuppositions_as_nli.yaml
ADDED
|
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
# Generated by utils.py
|
| 2 |
+
dataset_name: presuppositions_as_nli_zero_shot
|
| 3 |
+
include: ../multiple_choice_template_a_yaml
|
| 4 |
+
task: bigbench_presuppositions_as_nli_multiple_choice
|
lm-quant-toolkit/.deps/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/question_selection.yaml
ADDED
|
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
# Generated by utils.py
|
| 2 |
+
dataset_name: question_selection_zero_shot
|
| 3 |
+
include: ../multiple_choice_template_a_yaml
|
| 4 |
+
task: bigbench_question_selection_multiple_choice
|
lm-quant-toolkit/.deps/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/real_or_fake_text.yaml
ADDED
|
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
# Generated by utils.py
|
| 2 |
+
dataset_name: real_or_fake_text_zero_shot
|
| 3 |
+
include: ../multiple_choice_template_a_yaml
|
| 4 |
+
task: bigbench_real_or_fake_text_multiple_choice
|
lm-quant-toolkit/.deps/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/reasoning_about_colored_objects.yaml
ADDED
|
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
# Generated by utils.py
|
| 2 |
+
dataset_name: reasoning_about_colored_objects_zero_shot
|
| 3 |
+
include: ../multiple_choice_template_a_yaml
|
| 4 |
+
task: bigbench_reasoning_about_colored_objects_multiple_choice
|
lm-quant-toolkit/.deps/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/riddle_sense.yaml
ADDED
|
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
# Generated by utils.py
|
| 2 |
+
dataset_name: riddle_sense_zero_shot
|
| 3 |
+
include: ../multiple_choice_template_a_yaml
|
| 4 |
+
task: bigbench_riddle_sense_multiple_choice
|
lm-quant-toolkit/.deps/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/ruin_names.yaml
ADDED
|
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
# Generated by utils.py
|
| 2 |
+
dataset_name: ruin_names_zero_shot
|
| 3 |
+
include: ../multiple_choice_template_a_yaml
|
| 4 |
+
task: bigbench_ruin_names_multiple_choice
|
lm-quant-toolkit/.deps/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/salient_translation_error_detection.yaml
ADDED
|
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
# Generated by utils.py
|
| 2 |
+
dataset_name: salient_translation_error_detection_zero_shot
|
| 3 |
+
include: ../multiple_choice_template_a_yaml
|
| 4 |
+
task: bigbench_salient_translation_error_detection_multiple_choice
|
lm-quant-toolkit/.deps/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/sentence_ambiguity.yaml
ADDED
|
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
# Generated by utils.py
|
| 2 |
+
dataset_name: sentence_ambiguity_zero_shot
|
| 3 |
+
include: ../multiple_choice_template_a_yaml
|
| 4 |
+
task: bigbench_sentence_ambiguity_multiple_choice
|
lm-quant-toolkit/.deps/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/similarities_abstraction.yaml
ADDED
|
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
# Generated by utils.py
|
| 2 |
+
dataset_name: similarities_abstraction_zero_shot
|
| 3 |
+
include: ../multiple_choice_template_a_yaml
|
| 4 |
+
task: bigbench_similarities_abstraction_multiple_choice
|
lm-quant-toolkit/.deps/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/simple_ethical_questions.yaml
ADDED
|
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
# Generated by utils.py
|
| 2 |
+
dataset_name: simple_ethical_questions_zero_shot
|
| 3 |
+
include: ../multiple_choice_template_a_yaml
|
| 4 |
+
task: bigbench_simple_ethical_questions_multiple_choice
|
lm-quant-toolkit/.deps/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/snarks.yaml
ADDED
|
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
# Generated by utils.py
|
| 2 |
+
dataset_name: snarks_zero_shot
|
| 3 |
+
include: ../multiple_choice_template_a_yaml
|
| 4 |
+
task: bigbench_snarks_multiple_choice
|
lm-quant-toolkit/.deps/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/social_iqa.yaml
ADDED
|
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
# Generated by utils.py
|
| 2 |
+
dataset_name: social_iqa_zero_shot
|
| 3 |
+
include: ../multiple_choice_template_a_yaml
|
| 4 |
+
task: bigbench_social_iqa_multiple_choice
|
lm-quant-toolkit/.deps/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/social_support.yaml
ADDED
|
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
# Generated by utils.py
|
| 2 |
+
dataset_name: social_support_zero_shot
|
| 3 |
+
include: ../multiple_choice_template_a_yaml
|
| 4 |
+
task: bigbench_social_support_multiple_choice
|
lm-quant-toolkit/.deps/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/sports_understanding.yaml
ADDED
|
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
# Generated by utils.py
|
| 2 |
+
dataset_name: sports_understanding_zero_shot
|
| 3 |
+
include: ../multiple_choice_template_a_yaml
|
| 4 |
+
task: bigbench_sports_understanding_multiple_choice
|
lm-quant-toolkit/.deps/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/strange_stories.yaml
ADDED
|
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
# Generated by utils.py
|
| 2 |
+
dataset_name: strange_stories_zero_shot
|
| 3 |
+
include: ../multiple_choice_template_a_yaml
|
| 4 |
+
task: bigbench_strange_stories_multiple_choice
|
lm-quant-toolkit/.deps/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/strategyqa.yaml
ADDED
|
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
# Generated by utils.py
|
| 2 |
+
dataset_name: strategyqa_zero_shot
|
| 3 |
+
include: ../multiple_choice_template_b_yaml
|
| 4 |
+
task: bigbench_strategyqa_multiple_choice
|
lm-quant-toolkit/.deps/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/suicide_risk.yaml
ADDED
|
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
# Generated by utils.py
|
| 2 |
+
dataset_name: suicide_risk_zero_shot
|
| 3 |
+
include: ../multiple_choice_template_a_yaml
|
| 4 |
+
task: bigbench_suicide_risk_multiple_choice
|
lm-quant-toolkit/.deps/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/swahili_english_proverbs.yaml
ADDED
|
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
# Generated by utils.py
|
| 2 |
+
dataset_name: swahili_english_proverbs_zero_shot
|
| 3 |
+
include: ../multiple_choice_template_a_yaml
|
| 4 |
+
task: bigbench_swahili_english_proverbs_multiple_choice
|
lm-quant-toolkit/.deps/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/swedish_to_german_proverbs.yaml
ADDED
|
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
# Generated by utils.py
|
| 2 |
+
dataset_name: swedish_to_german_proverbs_zero_shot
|
| 3 |
+
include: ../multiple_choice_template_a_yaml
|
| 4 |
+
task: bigbench_swedish_to_german_proverbs_multiple_choice
|
lm-quant-toolkit/.deps/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/symbol_interpretation.yaml
ADDED
|
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
# Generated by utils.py
|
| 2 |
+
dataset_name: symbol_interpretation_zero_shot
|
| 3 |
+
include: ../multiple_choice_template_a_yaml
|
| 4 |
+
task: bigbench_symbol_interpretation_multiple_choice
|
lm-quant-toolkit/.deps/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/temporal_sequences.yaml
ADDED
|
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
# Generated by utils.py
|
| 2 |
+
dataset_name: temporal_sequences_zero_shot
|
| 3 |
+
include: ../multiple_choice_template_a_yaml
|
| 4 |
+
task: bigbench_temporal_sequences_multiple_choice
|
lm-quant-toolkit/.deps/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/timedial.yaml
ADDED
|
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
# Generated by utils.py
|
| 2 |
+
dataset_name: timedial_zero_shot
|
| 3 |
+
include: ../multiple_choice_template_a_yaml
|
| 4 |
+
task: bigbench_timedial_multiple_choice
|