diff --git a/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/generate_until/analogical_similarity.yaml b/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/generate_until/analogical_similarity.yaml new file mode 100644 index 0000000000000000000000000000000000000000..5cc6550a6075a991bce4826c95188e0c7b3d2a94 --- /dev/null +++ b/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/generate_until/analogical_similarity.yaml @@ -0,0 +1,4 @@ +# Generated by utils.py +dataset_name: analogical_similarity_zero_shot +include: ../generate_until_template_yaml +task: bigbench_analogical_similarity_generate_until diff --git a/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/generate_until/elementary_math_qa.yaml b/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/generate_until/elementary_math_qa.yaml new file mode 100644 index 0000000000000000000000000000000000000000..9fe807bc645a88d7f2e87da1d094a2ec1bb51805 --- /dev/null +++ b/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/generate_until/elementary_math_qa.yaml @@ -0,0 +1,4 @@ +# Generated by utils.py +dataset_name: elementary_math_qa_zero_shot +include: ../generate_until_template_yaml +task: bigbench_elementary_math_qa_generate_until diff --git a/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/generate_until/evaluating_information_essentiality.yaml b/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/generate_until/evaluating_information_essentiality.yaml new file mode 100644 index 0000000000000000000000000000000000000000..b640b9430ad8a11758152c63ad0c77497fd16d50 --- /dev/null +++ b/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/generate_until/evaluating_information_essentiality.yaml @@ -0,0 +1,4 @@ +# Generated by utils.py +dataset_name: evaluating_information_essentiality_zero_shot +include: ../generate_until_template_yaml +task: bigbench_evaluating_information_essentiality_generate_until diff --git a/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/generate_until/gre_reading_comprehension.yaml b/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/generate_until/gre_reading_comprehension.yaml new file mode 100644 index 0000000000000000000000000000000000000000..449b09c47ed4638e2773772b0ce27264cd694be0 --- /dev/null +++ b/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/generate_until/gre_reading_comprehension.yaml @@ -0,0 +1,4 @@ +# Generated by utils.py +dataset_name: gre_reading_comprehension_zero_shot +include: ../generate_until_template_yaml +task: bigbench_gre_reading_comprehension_generate_until diff --git a/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/generate_until/key_value_maps.yaml b/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/generate_until/key_value_maps.yaml new file mode 100644 index 0000000000000000000000000000000000000000..3ea697d1f7664866050ecbd0615ea3e957a13602 --- /dev/null +++ b/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/generate_until/key_value_maps.yaml @@ -0,0 +1,4 @@ +# Generated by utils.py +dataset_name: key_value_maps_zero_shot +include: ../generate_until_template_yaml +task: bigbench_key_value_maps_generate_until diff --git a/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/generate_until/language_identification.yaml b/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/generate_until/language_identification.yaml new file mode 100644 index 0000000000000000000000000000000000000000..9cb7b27408b9a82c308ebac33b89e799df0763a0 --- /dev/null +++ b/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/generate_until/language_identification.yaml @@ -0,0 +1,4 @@ +# Generated by utils.py +dataset_name: language_identification_zero_shot +include: ../generate_until_template_yaml +task: bigbench_language_identification_generate_until diff --git a/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/generate_until/moral_permissibility.yaml b/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/generate_until/moral_permissibility.yaml new file mode 100644 index 0000000000000000000000000000000000000000..277bf69feff29559672655e47ce037df3c42c454 --- /dev/null +++ b/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/generate_until/moral_permissibility.yaml @@ -0,0 +1,4 @@ +# Generated by utils.py +dataset_name: moral_permissibility_zero_shot +include: ../generate_until_template_yaml +task: bigbench_moral_permissibility_generate_until diff --git a/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/generate_until/periodic_elements.yaml b/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/generate_until/periodic_elements.yaml new file mode 100644 index 0000000000000000000000000000000000000000..c5c96cec606f6ba3e749c970b20f71d9ed200799 --- /dev/null +++ b/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/generate_until/periodic_elements.yaml @@ -0,0 +1,4 @@ +# Generated by utils.py +dataset_name: periodic_elements_zero_shot +include: ../generate_until_template_yaml +task: bigbench_periodic_elements_generate_until diff --git a/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/generate_until/reasoning_about_colored_objects.yaml b/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/generate_until/reasoning_about_colored_objects.yaml new file mode 100644 index 0000000000000000000000000000000000000000..0b371d6e37baabaadb7a7e7424a12cd9dd7b81b9 --- /dev/null +++ b/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/generate_until/reasoning_about_colored_objects.yaml @@ -0,0 +1,4 @@ +# Generated by utils.py +dataset_name: reasoning_about_colored_objects_zero_shot +include: ../generate_until_template_yaml +task: bigbench_reasoning_about_colored_objects_generate_until diff --git a/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/analytic_entailment.yaml b/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/analytic_entailment.yaml new file mode 100644 index 0000000000000000000000000000000000000000..ee278f54ac976908075cce87a695dcf4910128f0 --- /dev/null +++ b/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/analytic_entailment.yaml @@ -0,0 +1,4 @@ +# Generated by utils.py +dataset_name: analytic_entailment_zero_shot +include: ../multiple_choice_template_a_yaml +task: bigbench_analytic_entailment_multiple_choice diff --git a/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/arithmetic.yaml b/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/arithmetic.yaml new file mode 100644 index 0000000000000000000000000000000000000000..877268c6d87f6c6d2cdfe6adb721a72f16dabb0b --- /dev/null +++ b/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/arithmetic.yaml @@ -0,0 +1,4 @@ +# Generated by utils.py +dataset_name: arithmetic_zero_shot +include: ../multiple_choice_template_a_yaml +task: bigbench_arithmetic_multiple_choice diff --git a/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/authorship_verification.yaml b/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/authorship_verification.yaml new file mode 100644 index 0000000000000000000000000000000000000000..3e43911cee107276eebff0c36fa88df99290aca2 --- /dev/null +++ b/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/authorship_verification.yaml @@ -0,0 +1,4 @@ +# Generated by utils.py +dataset_name: authorship_verification_zero_shot +include: ../multiple_choice_template_a_yaml +task: bigbench_authorship_verification_multiple_choice diff --git a/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/bbq_lite_json.yaml b/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/bbq_lite_json.yaml new file mode 100644 index 0000000000000000000000000000000000000000..ab248ee29465ac13834efc46017cef414d30f32e --- /dev/null +++ b/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/bbq_lite_json.yaml @@ -0,0 +1,4 @@ +# Generated by utils.py +dataset_name: bbq_lite_json_zero_shot +include: ../multiple_choice_template_a_yaml +task: bigbench_bbq_lite_json_multiple_choice diff --git a/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/causal_judgment.yaml b/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/causal_judgment.yaml new file mode 100644 index 0000000000000000000000000000000000000000..ce3894c88e1f49d9c85e5eadce5b317849571fea --- /dev/null +++ b/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/causal_judgment.yaml @@ -0,0 +1,4 @@ +# Generated by utils.py +dataset_name: causal_judgment_zero_shot +include: ../multiple_choice_template_a_yaml +task: bigbench_causal_judgment_multiple_choice diff --git a/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/checkmate_in_one.yaml b/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/checkmate_in_one.yaml new file mode 100644 index 0000000000000000000000000000000000000000..3729168542d9f52c05b4350172335c29c31a9f5b --- /dev/null +++ b/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/checkmate_in_one.yaml @@ -0,0 +1,4 @@ +# Generated by utils.py +dataset_name: checkmate_in_one_zero_shot +include: ../multiple_choice_template_a_yaml +task: bigbench_checkmate_in_one_multiple_choice diff --git a/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/code_line_description.yaml b/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/code_line_description.yaml new file mode 100644 index 0000000000000000000000000000000000000000..3e579579f76b9f3f057339da9748f28aa7e45104 --- /dev/null +++ b/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/code_line_description.yaml @@ -0,0 +1,4 @@ +# Generated by utils.py +dataset_name: code_line_description_zero_shot +include: ../multiple_choice_template_a_yaml +task: bigbench_code_line_description_multiple_choice diff --git a/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/conceptual_combinations.yaml b/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/conceptual_combinations.yaml new file mode 100644 index 0000000000000000000000000000000000000000..41177eee8e2ffafc5f7bec55fc67e1c861cb7223 --- /dev/null +++ b/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/conceptual_combinations.yaml @@ -0,0 +1,4 @@ +# Generated by utils.py +dataset_name: conceptual_combinations_zero_shot +include: ../multiple_choice_template_a_yaml +task: bigbench_conceptual_combinations_multiple_choice diff --git a/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/contextual_parametric_knowledge_conflicts.yaml b/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/contextual_parametric_knowledge_conflicts.yaml new file mode 100644 index 0000000000000000000000000000000000000000..b63ab9229913494b67d99aab3d81d96a97e29a89 --- /dev/null +++ b/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/contextual_parametric_knowledge_conflicts.yaml @@ -0,0 +1,4 @@ +# Generated by utils.py +dataset_name: contextual_parametric_knowledge_conflicts_zero_shot +include: ../multiple_choice_template_a_yaml +task: bigbench_contextual_parametric_knowledge_conflicts_multiple_choice diff --git a/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/cs_algorithms.yaml b/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/cs_algorithms.yaml new file mode 100644 index 0000000000000000000000000000000000000000..b5e3b94e0f179b01c0b09b8b93ab7a1fd333dfce --- /dev/null +++ b/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/cs_algorithms.yaml @@ -0,0 +1,4 @@ +# Generated by utils.py +dataset_name: cs_algorithms_zero_shot +include: ../multiple_choice_template_a_yaml +task: bigbench_cs_algorithms_multiple_choice diff --git a/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/dark_humor_detection.yaml b/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/dark_humor_detection.yaml new file mode 100644 index 0000000000000000000000000000000000000000..b1851f164db028c1ac3eee21404e9cea24b39bb2 --- /dev/null +++ b/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/dark_humor_detection.yaml @@ -0,0 +1,4 @@ +# Generated by utils.py +dataset_name: dark_humor_detection_zero_shot +include: ../multiple_choice_template_a_yaml +task: bigbench_dark_humor_detection_multiple_choice diff --git a/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/disambiguation_qa.yaml b/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/disambiguation_qa.yaml new file mode 100644 index 0000000000000000000000000000000000000000..80ad2aa2671ca8b66c431519a87d17ea7bc8fff1 --- /dev/null +++ b/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/disambiguation_qa.yaml @@ -0,0 +1,4 @@ +# Generated by utils.py +dataset_name: disambiguation_qa_zero_shot +include: ../multiple_choice_template_a_yaml +task: bigbench_disambiguation_qa_multiple_choice diff --git a/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/discourse_marker_prediction.yaml b/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/discourse_marker_prediction.yaml new file mode 100644 index 0000000000000000000000000000000000000000..01089de84069b093978b07515fbe91318d28748a --- /dev/null +++ b/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/discourse_marker_prediction.yaml @@ -0,0 +1,4 @@ +# Generated by utils.py +dataset_name: discourse_marker_prediction_zero_shot +include: ../multiple_choice_template_a_yaml +task: bigbench_discourse_marker_prediction_multiple_choice diff --git a/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/emoji_movie.yaml b/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/emoji_movie.yaml new file mode 100644 index 0000000000000000000000000000000000000000..4fc57aa269b49be21a307605a7a3fa841545f098 --- /dev/null +++ b/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/emoji_movie.yaml @@ -0,0 +1,4 @@ +# Generated by utils.py +dataset_name: emoji_movie_zero_shot +include: ../multiple_choice_template_a_yaml +task: bigbench_emoji_movie_multiple_choice diff --git a/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/emojis_emotion_prediction.yaml b/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/emojis_emotion_prediction.yaml new file mode 100644 index 0000000000000000000000000000000000000000..c117b3041e7fff9ac7fea51f578825d2320122e6 --- /dev/null +++ b/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/emojis_emotion_prediction.yaml @@ -0,0 +1,4 @@ +# Generated by utils.py +dataset_name: emojis_emotion_prediction_zero_shot +include: ../multiple_choice_template_a_yaml +task: bigbench_emojis_emotion_prediction_multiple_choice diff --git a/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/empirical_judgments.yaml b/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/empirical_judgments.yaml new file mode 100644 index 0000000000000000000000000000000000000000..10fcfaaa4138c0860cd438124ea57e1b8c51508c --- /dev/null +++ b/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/empirical_judgments.yaml @@ -0,0 +1,4 @@ +# Generated by utils.py +dataset_name: empirical_judgments_zero_shot +include: ../multiple_choice_template_a_yaml +task: bigbench_empirical_judgments_multiple_choice diff --git a/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/entailed_polarity.yaml b/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/entailed_polarity.yaml new file mode 100644 index 0000000000000000000000000000000000000000..5e298a34b46dc9ae26133a2c0bb4c1f7a706d281 --- /dev/null +++ b/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/entailed_polarity.yaml @@ -0,0 +1,4 @@ +# Generated by utils.py +dataset_name: entailed_polarity_zero_shot +include: ../multiple_choice_template_a_yaml +task: bigbench_entailed_polarity_multiple_choice diff --git a/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/entailed_polarity_hindi.yaml b/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/entailed_polarity_hindi.yaml new file mode 100644 index 0000000000000000000000000000000000000000..c41565dd63ac583d82cef82911db5c8643ad0919 --- /dev/null +++ b/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/entailed_polarity_hindi.yaml @@ -0,0 +1,4 @@ +# Generated by utils.py +dataset_name: entailed_polarity_hindi_zero_shot +include: ../multiple_choice_template_a_yaml +task: bigbench_entailed_polarity_hindi_multiple_choice diff --git a/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/epistemic_reasoning.yaml b/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/epistemic_reasoning.yaml new file mode 100644 index 0000000000000000000000000000000000000000..22fa9ed80691bdc55752bb585eafa951fd5636a5 --- /dev/null +++ b/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/epistemic_reasoning.yaml @@ -0,0 +1,4 @@ +# Generated by utils.py +dataset_name: epistemic_reasoning_zero_shot +include: ../multiple_choice_template_a_yaml +task: bigbench_epistemic_reasoning_multiple_choice diff --git a/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/figure_of_speech_detection.yaml b/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/figure_of_speech_detection.yaml new file mode 100644 index 0000000000000000000000000000000000000000..84a88054de00a6d5a65669a1d0755620c570b3f5 --- /dev/null +++ b/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/figure_of_speech_detection.yaml @@ -0,0 +1,4 @@ +# Generated by utils.py +dataset_name: figure_of_speech_detection_zero_shot +include: ../multiple_choice_template_a_yaml +task: bigbench_figure_of_speech_detection_multiple_choice diff --git a/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/formal_fallacies_syllogisms_negation.yaml b/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/formal_fallacies_syllogisms_negation.yaml new file mode 100644 index 0000000000000000000000000000000000000000..38f9f9c9da940875520f0c4c91b73f3bf03db4c9 --- /dev/null +++ b/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/formal_fallacies_syllogisms_negation.yaml @@ -0,0 +1,4 @@ +# Generated by utils.py +dataset_name: formal_fallacies_syllogisms_negation_zero_shot +include: ../multiple_choice_template_a_yaml +task: bigbench_formal_fallacies_syllogisms_negation_multiple_choice diff --git a/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/general_knowledge.yaml b/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/general_knowledge.yaml new file mode 100644 index 0000000000000000000000000000000000000000..f1922e434ba70383bf390058585cff70ca1da721 --- /dev/null +++ b/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/general_knowledge.yaml @@ -0,0 +1,4 @@ +# Generated by utils.py +dataset_name: general_knowledge_zero_shot +include: ../multiple_choice_template_a_yaml +task: bigbench_general_knowledge_multiple_choice diff --git a/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/hhh_alignment.yaml b/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/hhh_alignment.yaml new file mode 100644 index 0000000000000000000000000000000000000000..aae1ecb429f5b22178952dc5ba94ea1a2776dadb --- /dev/null +++ b/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/hhh_alignment.yaml @@ -0,0 +1,4 @@ +# Generated by utils.py +dataset_name: hhh_alignment_zero_shot +include: ../multiple_choice_template_a_yaml +task: bigbench_hhh_alignment_multiple_choice diff --git a/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/human_organs_senses.yaml b/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/human_organs_senses.yaml new file mode 100644 index 0000000000000000000000000000000000000000..d95bbf9dbb5ce330c85886d026e6d08848497928 --- /dev/null +++ b/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/human_organs_senses.yaml @@ -0,0 +1,4 @@ +# Generated by utils.py +dataset_name: human_organs_senses_zero_shot +include: ../multiple_choice_template_a_yaml +task: bigbench_human_organs_senses_multiple_choice diff --git a/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/implicatures.yaml b/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/implicatures.yaml new file mode 100644 index 0000000000000000000000000000000000000000..9e71d8b50c831db4682d995291fb4f5050d1b404 --- /dev/null +++ b/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/implicatures.yaml @@ -0,0 +1,4 @@ +# Generated by utils.py +dataset_name: implicatures_zero_shot +include: ../multiple_choice_template_a_yaml +task: bigbench_implicatures_multiple_choice diff --git a/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/international_phonetic_alphabet_nli.yaml b/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/international_phonetic_alphabet_nli.yaml new file mode 100644 index 0000000000000000000000000000000000000000..1a6b0d52d567db19cf12d9506f3cabec92d4a871 --- /dev/null +++ b/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/international_phonetic_alphabet_nli.yaml @@ -0,0 +1,4 @@ +# Generated by utils.py +dataset_name: international_phonetic_alphabet_nli_zero_shot +include: ../multiple_choice_template_a_yaml +task: bigbench_international_phonetic_alphabet_nli_multiple_choice diff --git a/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/intersect_geometry.yaml b/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/intersect_geometry.yaml new file mode 100644 index 0000000000000000000000000000000000000000..2477ad3bfb53759f9ad510cc44ac1ec32315c7df --- /dev/null +++ b/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/intersect_geometry.yaml @@ -0,0 +1,4 @@ +# Generated by utils.py +dataset_name: intersect_geometry_zero_shot +include: ../multiple_choice_template_a_yaml +task: bigbench_intersect_geometry_multiple_choice diff --git a/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/kanji_ascii.yaml b/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/kanji_ascii.yaml new file mode 100644 index 0000000000000000000000000000000000000000..97cc4aac6136ff8a75ea74c39e59f62bd3a2a447 --- /dev/null +++ b/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/kanji_ascii.yaml @@ -0,0 +1,4 @@ +# Generated by utils.py +dataset_name: kanji_ascii_zero_shot +include: ../multiple_choice_template_a_yaml +task: bigbench_kanji_ascii_multiple_choice diff --git a/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/known_unknowns.yaml b/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/known_unknowns.yaml new file mode 100644 index 0000000000000000000000000000000000000000..90012e6a3dceffbe3cb4f9aab3fbbb3a3414e672 --- /dev/null +++ b/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/known_unknowns.yaml @@ -0,0 +1,4 @@ +# Generated by utils.py +dataset_name: known_unknowns_zero_shot +include: ../multiple_choice_template_a_yaml +task: bigbench_known_unknowns_multiple_choice diff --git a/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/logical_args.yaml b/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/logical_args.yaml new file mode 100644 index 0000000000000000000000000000000000000000..3bc8b59310cd44e482e03e271e33f9e1ae44dffe --- /dev/null +++ b/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/logical_args.yaml @@ -0,0 +1,4 @@ +# Generated by utils.py +dataset_name: logical_args_zero_shot +include: ../multiple_choice_template_a_yaml +task: bigbench_logical_args_multiple_choice diff --git a/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/logical_deduction.yaml b/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/logical_deduction.yaml new file mode 100644 index 0000000000000000000000000000000000000000..2b41e9b25692c01845f8529f9598dc333e971442 --- /dev/null +++ b/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/logical_deduction.yaml @@ -0,0 +1,4 @@ +# Generated by utils.py +dataset_name: logical_deduction_zero_shot +include: ../multiple_choice_template_a_yaml +task: bigbench_logical_deduction_multiple_choice diff --git a/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/logical_sequence.yaml b/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/logical_sequence.yaml new file mode 100644 index 0000000000000000000000000000000000000000..e03574c113731da4f23c6d63b772b9d0a804eff1 --- /dev/null +++ b/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/logical_sequence.yaml @@ -0,0 +1,4 @@ +# Generated by utils.py +dataset_name: logical_sequence_zero_shot +include: ../multiple_choice_template_a_yaml +task: bigbench_logical_sequence_multiple_choice diff --git a/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/metaphor_boolean.yaml b/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/metaphor_boolean.yaml new file mode 100644 index 0000000000000000000000000000000000000000..e2669ee075ab19a0170fe062f0c0d70d51810d21 --- /dev/null +++ b/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/metaphor_boolean.yaml @@ -0,0 +1,4 @@ +# Generated by utils.py +dataset_name: metaphor_boolean_zero_shot +include: ../multiple_choice_template_a_yaml +task: bigbench_metaphor_boolean_multiple_choice diff --git a/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/metaphor_understanding.yaml b/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/metaphor_understanding.yaml new file mode 100644 index 0000000000000000000000000000000000000000..58dfee1ee1fe6b7d56ef283caa8e809875763d64 --- /dev/null +++ b/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/metaphor_understanding.yaml @@ -0,0 +1,4 @@ +# Generated by utils.py +dataset_name: metaphor_understanding_zero_shot +include: ../multiple_choice_template_a_yaml +task: bigbench_metaphor_understanding_multiple_choice diff --git a/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/misconceptions.yaml b/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/misconceptions.yaml new file mode 100644 index 0000000000000000000000000000000000000000..de7c546b1b0457fc4a5ca3aa88af4242b2d936c2 --- /dev/null +++ b/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/misconceptions.yaml @@ -0,0 +1,4 @@ +# Generated by utils.py +dataset_name: misconceptions_zero_shot +include: ../multiple_choice_template_a_yaml +task: bigbench_misconceptions_multiple_choice diff --git a/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/misconceptions_russian.yaml b/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/misconceptions_russian.yaml new file mode 100644 index 0000000000000000000000000000000000000000..139266f269a038f1a50d5e1b957e37c64820a7a5 --- /dev/null +++ b/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/misconceptions_russian.yaml @@ -0,0 +1,4 @@ +# Generated by utils.py +dataset_name: misconceptions_russian_zero_shot +include: ../multiple_choice_template_a_yaml +task: bigbench_misconceptions_russian_multiple_choice diff --git a/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/mnist_ascii.yaml b/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/mnist_ascii.yaml new file mode 100644 index 0000000000000000000000000000000000000000..d2808bfc3ea863bccface977dcd84a9436491ae2 --- /dev/null +++ b/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/mnist_ascii.yaml @@ -0,0 +1,4 @@ +# Generated by utils.py +dataset_name: mnist_ascii_zero_shot +include: ../multiple_choice_template_a_yaml +task: bigbench_mnist_ascii_multiple_choice diff --git a/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/movie_dialog_same_or_different.yaml b/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/movie_dialog_same_or_different.yaml new file mode 100644 index 0000000000000000000000000000000000000000..536e40e9a987f879654351ba8c67334fd43c212b --- /dev/null +++ b/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/movie_dialog_same_or_different.yaml @@ -0,0 +1,4 @@ +# Generated by utils.py +dataset_name: movie_dialog_same_or_different_zero_shot +include: ../multiple_choice_template_a_yaml +task: bigbench_movie_dialog_same_or_different_multiple_choice diff --git a/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/movie_recommendation.yaml b/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/movie_recommendation.yaml new file mode 100644 index 0000000000000000000000000000000000000000..beded58696bd0448b3d5e7153759cc2b9600807d --- /dev/null +++ b/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/movie_recommendation.yaml @@ -0,0 +1,4 @@ +# Generated by utils.py +dataset_name: movie_recommendation_zero_shot +include: ../multiple_choice_template_a_yaml +task: bigbench_movie_recommendation_multiple_choice diff --git a/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/multiemo.yaml b/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/multiemo.yaml new file mode 100644 index 0000000000000000000000000000000000000000..500cac065ecb3c035afa5d525f46ab255a4017f4 --- /dev/null +++ b/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/multiemo.yaml @@ -0,0 +1,4 @@ +# Generated by utils.py +dataset_name: multiemo_zero_shot +include: ../multiple_choice_template_a_yaml +task: bigbench_multiemo_multiple_choice diff --git a/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/novel_concepts.yaml b/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/novel_concepts.yaml new file mode 100644 index 0000000000000000000000000000000000000000..cb2213a750784a9eb9f9b8f48bb683a615d10562 --- /dev/null +++ b/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/novel_concepts.yaml @@ -0,0 +1,4 @@ +# Generated by utils.py +dataset_name: novel_concepts_zero_shot +include: ../multiple_choice_template_a_yaml +task: bigbench_novel_concepts_multiple_choice diff --git a/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/parsinlu_qa.yaml b/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/parsinlu_qa.yaml new file mode 100644 index 0000000000000000000000000000000000000000..20a880d8ffed2b396dc6bdc4ca36cc3a1706859f --- /dev/null +++ b/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/parsinlu_qa.yaml @@ -0,0 +1,4 @@ +# Generated by utils.py +dataset_name: parsinlu_qa_zero_shot +include: ../multiple_choice_template_a_yaml +task: bigbench_parsinlu_qa_multiple_choice diff --git a/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/persian_idioms.yaml b/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/persian_idioms.yaml new file mode 100644 index 0000000000000000000000000000000000000000..9a45e479145c8b708c7799065d6ce71155524cfa --- /dev/null +++ b/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/persian_idioms.yaml @@ -0,0 +1,4 @@ +# Generated by utils.py +dataset_name: persian_idioms_zero_shot +include: ../multiple_choice_template_a_yaml +task: bigbench_persian_idioms_multiple_choice diff --git a/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/physical_intuition.yaml b/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/physical_intuition.yaml new file mode 100644 index 0000000000000000000000000000000000000000..fc54acaf05aaf24c5e665fda0619a298fffa63af --- /dev/null +++ b/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/physical_intuition.yaml @@ -0,0 +1,4 @@ +# Generated by utils.py +dataset_name: physical_intuition_zero_shot +include: ../multiple_choice_template_a_yaml +task: bigbench_physical_intuition_multiple_choice diff --git a/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/physics.yaml b/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/physics.yaml new file mode 100644 index 0000000000000000000000000000000000000000..d4c4ff4baf7019f4a965f30f05dc77b0133a7fa2 --- /dev/null +++ b/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/physics.yaml @@ -0,0 +1,4 @@ +# Generated by utils.py +dataset_name: physics_zero_shot +include: ../multiple_choice_template_a_yaml +task: bigbench_physics_multiple_choice diff --git a/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/presuppositions_as_nli.yaml b/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/presuppositions_as_nli.yaml new file mode 100644 index 0000000000000000000000000000000000000000..5ca6d0f47a874c43359aff3b52c93e3f356a4673 --- /dev/null +++ b/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/presuppositions_as_nli.yaml @@ -0,0 +1,4 @@ +# Generated by utils.py +dataset_name: presuppositions_as_nli_zero_shot +include: ../multiple_choice_template_a_yaml +task: bigbench_presuppositions_as_nli_multiple_choice diff --git a/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/real_or_fake_text.yaml b/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/real_or_fake_text.yaml new file mode 100644 index 0000000000000000000000000000000000000000..2013e5b9c7af28c58b71238066e6755b45efc197 --- /dev/null +++ b/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/real_or_fake_text.yaml @@ -0,0 +1,4 @@ +# Generated by utils.py +dataset_name: real_or_fake_text_zero_shot +include: ../multiple_choice_template_a_yaml +task: bigbench_real_or_fake_text_multiple_choice diff --git a/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/riddle_sense.yaml b/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/riddle_sense.yaml new file mode 100644 index 0000000000000000000000000000000000000000..3a11b6d59917be3a37d8caa3c9284915a99f428f --- /dev/null +++ b/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/riddle_sense.yaml @@ -0,0 +1,4 @@ +# Generated by utils.py +dataset_name: riddle_sense_zero_shot +include: ../multiple_choice_template_a_yaml +task: bigbench_riddle_sense_multiple_choice diff --git a/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/ruin_names.yaml b/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/ruin_names.yaml new file mode 100644 index 0000000000000000000000000000000000000000..4b7cb5e7318fe73422c66e88ed3a64025c65d0e8 --- /dev/null +++ b/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/ruin_names.yaml @@ -0,0 +1,4 @@ +# Generated by utils.py +dataset_name: ruin_names_zero_shot +include: ../multiple_choice_template_a_yaml +task: bigbench_ruin_names_multiple_choice diff --git a/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/salient_translation_error_detection.yaml b/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/salient_translation_error_detection.yaml new file mode 100644 index 0000000000000000000000000000000000000000..fd5765699452d90aa32ead4f4f6742d168c50252 --- /dev/null +++ b/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/salient_translation_error_detection.yaml @@ -0,0 +1,4 @@ +# Generated by utils.py +dataset_name: salient_translation_error_detection_zero_shot +include: ../multiple_choice_template_a_yaml +task: bigbench_salient_translation_error_detection_multiple_choice diff --git a/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/sentence_ambiguity.yaml b/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/sentence_ambiguity.yaml new file mode 100644 index 0000000000000000000000000000000000000000..07282c28825716254ec84468e07ac27872f826ca --- /dev/null +++ b/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/sentence_ambiguity.yaml @@ -0,0 +1,4 @@ +# Generated by utils.py +dataset_name: sentence_ambiguity_zero_shot +include: ../multiple_choice_template_a_yaml +task: bigbench_sentence_ambiguity_multiple_choice diff --git a/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/social_iqa.yaml b/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/social_iqa.yaml new file mode 100644 index 0000000000000000000000000000000000000000..8ec2dd1dd282dba0f7aac80d8a3a9a050598caf0 --- /dev/null +++ b/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/social_iqa.yaml @@ -0,0 +1,4 @@ +# Generated by utils.py +dataset_name: social_iqa_zero_shot +include: ../multiple_choice_template_a_yaml +task: bigbench_social_iqa_multiple_choice diff --git a/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/sports_understanding.yaml b/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/sports_understanding.yaml new file mode 100644 index 0000000000000000000000000000000000000000..ae2ba852ee277e224e20a634545afe1dd3ccebdd --- /dev/null +++ b/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/sports_understanding.yaml @@ -0,0 +1,4 @@ +# Generated by utils.py +dataset_name: sports_understanding_zero_shot +include: ../multiple_choice_template_a_yaml +task: bigbench_sports_understanding_multiple_choice diff --git a/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/strange_stories.yaml b/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/strange_stories.yaml new file mode 100644 index 0000000000000000000000000000000000000000..bed6b55f292ffe31ec7f045be4b73460bd545196 --- /dev/null +++ b/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/strange_stories.yaml @@ -0,0 +1,4 @@ +# Generated by utils.py +dataset_name: strange_stories_zero_shot +include: ../multiple_choice_template_a_yaml +task: bigbench_strange_stories_multiple_choice diff --git a/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/suicide_risk.yaml b/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/suicide_risk.yaml new file mode 100644 index 0000000000000000000000000000000000000000..138c2dff78de1488eea82809692ac45b237195c8 --- /dev/null +++ b/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/suicide_risk.yaml @@ -0,0 +1,4 @@ +# Generated by utils.py +dataset_name: suicide_risk_zero_shot +include: ../multiple_choice_template_a_yaml +task: bigbench_suicide_risk_multiple_choice diff --git a/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/swahili_english_proverbs.yaml b/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/swahili_english_proverbs.yaml new file mode 100644 index 0000000000000000000000000000000000000000..46d66147c44daef4ddf08e311b06397d521fbdae --- /dev/null +++ b/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/swahili_english_proverbs.yaml @@ -0,0 +1,4 @@ +# Generated by utils.py +dataset_name: swahili_english_proverbs_zero_shot +include: ../multiple_choice_template_a_yaml +task: bigbench_swahili_english_proverbs_multiple_choice diff --git a/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/swedish_to_german_proverbs.yaml b/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/swedish_to_german_proverbs.yaml new file mode 100644 index 0000000000000000000000000000000000000000..a08c437e07c6f4f7422cf16e0b4e69c5b92c6952 --- /dev/null +++ b/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/swedish_to_german_proverbs.yaml @@ -0,0 +1,4 @@ +# Generated by utils.py +dataset_name: swedish_to_german_proverbs_zero_shot +include: ../multiple_choice_template_a_yaml +task: bigbench_swedish_to_german_proverbs_multiple_choice diff --git a/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/timedial.yaml b/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/timedial.yaml new file mode 100644 index 0000000000000000000000000000000000000000..ea069173bd43a5d61c5cd7f4a1863a5aeb62c189 --- /dev/null +++ b/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/timedial.yaml @@ -0,0 +1,4 @@ +# Generated by utils.py +dataset_name: timedial_zero_shot +include: ../multiple_choice_template_a_yaml +task: bigbench_timedial_multiple_choice diff --git a/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/tracking_shuffled_objects.yaml b/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/tracking_shuffled_objects.yaml new file mode 100644 index 0000000000000000000000000000000000000000..62ebc5d6101cd62798ffbb950cd44b0e5fef6787 --- /dev/null +++ b/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/tracking_shuffled_objects.yaml @@ -0,0 +1,4 @@ +# Generated by utils.py +dataset_name: tracking_shuffled_objects_zero_shot +include: ../multiple_choice_template_a_yaml +task: bigbench_tracking_shuffled_objects_multiple_choice diff --git a/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/understanding_fables.yaml b/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/understanding_fables.yaml new file mode 100644 index 0000000000000000000000000000000000000000..5cdd779d7bbab2d4294a650bd9ef7fe161a1ecdb --- /dev/null +++ b/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/understanding_fables.yaml @@ -0,0 +1,4 @@ +# Generated by utils.py +dataset_name: understanding_fables_zero_shot +include: ../multiple_choice_template_a_yaml +task: bigbench_understanding_fables_multiple_choice diff --git a/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/undo_permutation.yaml b/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/undo_permutation.yaml new file mode 100644 index 0000000000000000000000000000000000000000..bfe91a2b08da90c48211ec8e93503741f920cb3d --- /dev/null +++ b/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/undo_permutation.yaml @@ -0,0 +1,4 @@ +# Generated by utils.py +dataset_name: undo_permutation_zero_shot +include: ../multiple_choice_template_a_yaml +task: bigbench_undo_permutation_multiple_choice diff --git a/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/unit_conversion.yaml b/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/unit_conversion.yaml new file mode 100644 index 0000000000000000000000000000000000000000..d1c50a6523671032ec0a02315e761650c58f47cd --- /dev/null +++ b/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/unit_conversion.yaml @@ -0,0 +1,4 @@ +# Generated by utils.py +dataset_name: unit_conversion_zero_shot +include: ../multiple_choice_template_a_yaml +task: bigbench_unit_conversion_multiple_choice diff --git a/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/unit_interpretation.yaml b/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/unit_interpretation.yaml new file mode 100644 index 0000000000000000000000000000000000000000..7d87db233aa59431879b806cf8ff4ced6218338f --- /dev/null +++ b/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/unit_interpretation.yaml @@ -0,0 +1,4 @@ +# Generated by utils.py +dataset_name: unit_interpretation_zero_shot +include: ../multiple_choice_template_a_yaml +task: bigbench_unit_interpretation_multiple_choice diff --git a/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/vitaminc_fact_verification.yaml b/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/vitaminc_fact_verification.yaml new file mode 100644 index 0000000000000000000000000000000000000000..42db495738e77624415c04990548f06770c8f1a3 --- /dev/null +++ b/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/vitaminc_fact_verification.yaml @@ -0,0 +1,4 @@ +# Generated by utils.py +dataset_name: vitaminc_fact_verification_zero_shot +include: ../multiple_choice_template_a_yaml +task: bigbench_vitaminc_fact_verification_multiple_choice diff --git a/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/what_is_the_tao.yaml b/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/what_is_the_tao.yaml new file mode 100644 index 0000000000000000000000000000000000000000..8c4e15d3ad6e160dce16db288ab8e1f9c331ca80 --- /dev/null +++ b/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/what_is_the_tao.yaml @@ -0,0 +1,4 @@ +# Generated by utils.py +dataset_name: what_is_the_tao_zero_shot +include: ../multiple_choice_template_a_yaml +task: bigbench_what_is_the_tao_multiple_choice diff --git a/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/winowhy.yaml b/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/winowhy.yaml new file mode 100644 index 0000000000000000000000000000000000000000..23ffc4bdd98f125ae32d466460c2afc0e688f200 --- /dev/null +++ b/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/winowhy.yaml @@ -0,0 +1,4 @@ +# Generated by utils.py +dataset_name: winowhy_zero_shot +include: ../multiple_choice_template_a_yaml +task: bigbench_winowhy_multiple_choice