Hugging Face's logo

koichi12
/
llm-scripts

Model card Files
xet
Community
koichi12 commited on
Commit
969dcb4
·
verified ·
1 Parent(s): edc79ed

Add files using upload-large-folder tool

Browse files
This view is limited to 50 files because it contains too many changes.   See raw diff
Files changed (50) hide show
  1. scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/generate_until/analogical_similarity.yaml +4 -0
  2. scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/generate_until/elementary_math_qa.yaml +4 -0
  3. scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/generate_until/evaluating_information_essentiality.yaml +4 -0
  4. scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/generate_until/gre_reading_comprehension.yaml +4 -0
  5. scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/generate_until/key_value_maps.yaml +4 -0
  6. scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/generate_until/language_identification.yaml +4 -0
  7. scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/generate_until/moral_permissibility.yaml +4 -0
  8. scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/generate_until/periodic_elements.yaml +4 -0
  9. scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/generate_until/reasoning_about_colored_objects.yaml +4 -0
  10. scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/analytic_entailment.yaml +4 -0
  11. scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/arithmetic.yaml +4 -0
  12. scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/authorship_verification.yaml +4 -0
  13. scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/bbq_lite_json.yaml +4 -0
  14. scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/causal_judgment.yaml +4 -0
  15. scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/checkmate_in_one.yaml +4 -0
  16. scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/code_line_description.yaml +4 -0
  17. scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/conceptual_combinations.yaml +4 -0
  18. scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/contextual_parametric_knowledge_conflicts.yaml +4 -0
  19. scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/cs_algorithms.yaml +4 -0
  20. scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/dark_humor_detection.yaml +4 -0
  21. scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/disambiguation_qa.yaml +4 -0
  22. scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/discourse_marker_prediction.yaml +4 -0
  23. scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/emoji_movie.yaml +4 -0
  24. scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/emojis_emotion_prediction.yaml +4 -0
  25. scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/empirical_judgments.yaml +4 -0
  26. scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/entailed_polarity.yaml +4 -0
  27. scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/entailed_polarity_hindi.yaml +4 -0
  28. scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/epistemic_reasoning.yaml +4 -0
  29. scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/figure_of_speech_detection.yaml +4 -0
  30. scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/formal_fallacies_syllogisms_negation.yaml +4 -0
  31. scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/general_knowledge.yaml +4 -0
  32. scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/hhh_alignment.yaml +4 -0
  33. scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/human_organs_senses.yaml +4 -0
  34. scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/implicatures.yaml +4 -0
  35. scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/international_phonetic_alphabet_nli.yaml +4 -0
  36. scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/intersect_geometry.yaml +4 -0
  37. scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/kanji_ascii.yaml +4 -0
  38. scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/known_unknowns.yaml +4 -0
  39. scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/logical_args.yaml +4 -0
  40. scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/logical_deduction.yaml +4 -0
  41. scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/logical_sequence.yaml +4 -0
  42. scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/metaphor_boolean.yaml +4 -0
  43. scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/metaphor_understanding.yaml +4 -0
  44. scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/misconceptions.yaml +4 -0
  45. scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/misconceptions_russian.yaml +4 -0
  46. scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/mnist_ascii.yaml +4 -0
  47. scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/movie_dialog_same_or_different.yaml +4 -0
  48. scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/movie_recommendation.yaml +4 -0
  49. scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/multiemo.yaml +4 -0
  50. scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/novel_concepts.yaml +4 -0
scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/generate_until/analogical_similarity.yaml ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ # Generated by utils.py
2
+ dataset_name: analogical_similarity_zero_shot
3
+ include: ../generate_until_template_yaml
4
+ task: bigbench_analogical_similarity_generate_until
scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/generate_until/elementary_math_qa.yaml ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ # Generated by utils.py
2
+ dataset_name: elementary_math_qa_zero_shot
3
+ include: ../generate_until_template_yaml
4
+ task: bigbench_elementary_math_qa_generate_until
scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/generate_until/evaluating_information_essentiality.yaml ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ # Generated by utils.py
2
+ dataset_name: evaluating_information_essentiality_zero_shot
3
+ include: ../generate_until_template_yaml
4
+ task: bigbench_evaluating_information_essentiality_generate_until
scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/generate_until/gre_reading_comprehension.yaml ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ # Generated by utils.py
2
+ dataset_name: gre_reading_comprehension_zero_shot
3
+ include: ../generate_until_template_yaml
4
+ task: bigbench_gre_reading_comprehension_generate_until
scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/generate_until/key_value_maps.yaml ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ # Generated by utils.py
2
+ dataset_name: key_value_maps_zero_shot
3
+ include: ../generate_until_template_yaml
4
+ task: bigbench_key_value_maps_generate_until
scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/generate_until/language_identification.yaml ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ # Generated by utils.py
2
+ dataset_name: language_identification_zero_shot
3
+ include: ../generate_until_template_yaml
4
+ task: bigbench_language_identification_generate_until
scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/generate_until/moral_permissibility.yaml ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ # Generated by utils.py
2
+ dataset_name: moral_permissibility_zero_shot
3
+ include: ../generate_until_template_yaml
4
+ task: bigbench_moral_permissibility_generate_until
scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/generate_until/periodic_elements.yaml ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ # Generated by utils.py
2
+ dataset_name: periodic_elements_zero_shot
3
+ include: ../generate_until_template_yaml
4
+ task: bigbench_periodic_elements_generate_until
scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/generate_until/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: ../generate_until_template_yaml
4
+ task: bigbench_reasoning_about_colored_objects_generate_until
scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/analytic_entailment.yaml ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ # Generated by utils.py
2
+ dataset_name: analytic_entailment_zero_shot
3
+ include: ../multiple_choice_template_a_yaml
4
+ task: bigbench_analytic_entailment_multiple_choice
scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/arithmetic.yaml ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ # Generated by utils.py
2
+ dataset_name: arithmetic_zero_shot
3
+ include: ../multiple_choice_template_a_yaml
4
+ task: bigbench_arithmetic_multiple_choice
scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/authorship_verification.yaml ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ # Generated by utils.py
2
+ dataset_name: authorship_verification_zero_shot
3
+ include: ../multiple_choice_template_a_yaml
4
+ task: bigbench_authorship_verification_multiple_choice
scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/bbq_lite_json.yaml ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ # Generated by utils.py
2
+ dataset_name: bbq_lite_json_zero_shot
3
+ include: ../multiple_choice_template_a_yaml
4
+ task: bigbench_bbq_lite_json_multiple_choice
scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/causal_judgment.yaml ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ # Generated by utils.py
2
+ dataset_name: causal_judgment_zero_shot
3
+ include: ../multiple_choice_template_a_yaml
4
+ task: bigbench_causal_judgment_multiple_choice
scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/checkmate_in_one.yaml ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ # Generated by utils.py
2
+ dataset_name: checkmate_in_one_zero_shot
3
+ include: ../multiple_choice_template_a_yaml
4
+ task: bigbench_checkmate_in_one_multiple_choice
scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/code_line_description.yaml ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ # Generated by utils.py
2
+ dataset_name: code_line_description_zero_shot
3
+ include: ../multiple_choice_template_a_yaml
4
+ task: bigbench_code_line_description_multiple_choice
scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/conceptual_combinations.yaml ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ # Generated by utils.py
2
+ dataset_name: conceptual_combinations_zero_shot
3
+ include: ../multiple_choice_template_a_yaml
4
+ task: bigbench_conceptual_combinations_multiple_choice
scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/contextual_parametric_knowledge_conflicts.yaml ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ # Generated by utils.py
2
+ dataset_name: contextual_parametric_knowledge_conflicts_zero_shot
3
+ include: ../multiple_choice_template_a_yaml
4
+ task: bigbench_contextual_parametric_knowledge_conflicts_multiple_choice
scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/cs_algorithms.yaml ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ # Generated by utils.py
2
+ dataset_name: cs_algorithms_zero_shot
3
+ include: ../multiple_choice_template_a_yaml
4
+ task: bigbench_cs_algorithms_multiple_choice
scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/dark_humor_detection.yaml ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ # Generated by utils.py
2
+ dataset_name: dark_humor_detection_zero_shot
3
+ include: ../multiple_choice_template_a_yaml
4
+ task: bigbench_dark_humor_detection_multiple_choice
scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/disambiguation_qa.yaml ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ # Generated by utils.py
2
+ dataset_name: disambiguation_qa_zero_shot
3
+ include: ../multiple_choice_template_a_yaml
4
+ task: bigbench_disambiguation_qa_multiple_choice
scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/discourse_marker_prediction.yaml ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ # Generated by utils.py
2
+ dataset_name: discourse_marker_prediction_zero_shot
3
+ include: ../multiple_choice_template_a_yaml
4
+ task: bigbench_discourse_marker_prediction_multiple_choice
scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/emoji_movie.yaml ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ # Generated by utils.py
2
+ dataset_name: emoji_movie_zero_shot
3
+ include: ../multiple_choice_template_a_yaml
4
+ task: bigbench_emoji_movie_multiple_choice
scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/emojis_emotion_prediction.yaml ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ # Generated by utils.py
2
+ dataset_name: emojis_emotion_prediction_zero_shot
3
+ include: ../multiple_choice_template_a_yaml
4
+ task: bigbench_emojis_emotion_prediction_multiple_choice
scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/empirical_judgments.yaml ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ # Generated by utils.py
2
+ dataset_name: empirical_judgments_zero_shot
3
+ include: ../multiple_choice_template_a_yaml
4
+ task: bigbench_empirical_judgments_multiple_choice
scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/entailed_polarity.yaml ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ # Generated by utils.py
2
+ dataset_name: entailed_polarity_zero_shot
3
+ include: ../multiple_choice_template_a_yaml
4
+ task: bigbench_entailed_polarity_multiple_choice
scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/entailed_polarity_hindi.yaml ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ # Generated by utils.py
2
+ dataset_name: entailed_polarity_hindi_zero_shot
3
+ include: ../multiple_choice_template_a_yaml
4
+ task: bigbench_entailed_polarity_hindi_multiple_choice
scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/epistemic_reasoning.yaml ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ # Generated by utils.py
2
+ dataset_name: epistemic_reasoning_zero_shot
3
+ include: ../multiple_choice_template_a_yaml
4
+ task: bigbench_epistemic_reasoning_multiple_choice
scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/figure_of_speech_detection.yaml ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ # Generated by utils.py
2
+ dataset_name: figure_of_speech_detection_zero_shot
3
+ include: ../multiple_choice_template_a_yaml
4
+ task: bigbench_figure_of_speech_detection_multiple_choice
scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/formal_fallacies_syllogisms_negation.yaml ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ # Generated by utils.py
2
+ dataset_name: formal_fallacies_syllogisms_negation_zero_shot
3
+ include: ../multiple_choice_template_a_yaml
4
+ task: bigbench_formal_fallacies_syllogisms_negation_multiple_choice
scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/general_knowledge.yaml ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ # Generated by utils.py
2
+ dataset_name: general_knowledge_zero_shot
3
+ include: ../multiple_choice_template_a_yaml
4
+ task: bigbench_general_knowledge_multiple_choice
scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/hhh_alignment.yaml ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ # Generated by utils.py
2
+ dataset_name: hhh_alignment_zero_shot
3
+ include: ../multiple_choice_template_a_yaml
4
+ task: bigbench_hhh_alignment_multiple_choice
scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/human_organs_senses.yaml ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ # Generated by utils.py
2
+ dataset_name: human_organs_senses_zero_shot
3
+ include: ../multiple_choice_template_a_yaml
4
+ task: bigbench_human_organs_senses_multiple_choice
scripts/yans/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
scripts/yans/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
scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/intersect_geometry.yaml ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ # Generated by utils.py
2
+ dataset_name: intersect_geometry_zero_shot
3
+ include: ../multiple_choice_template_a_yaml
4
+ task: bigbench_intersect_geometry_multiple_choice
scripts/yans/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
scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/known_unknowns.yaml ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ # Generated by utils.py
2
+ dataset_name: known_unknowns_zero_shot
3
+ include: ../multiple_choice_template_a_yaml
4
+ task: bigbench_known_unknowns_multiple_choice
scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/logical_args.yaml ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ # Generated by utils.py
2
+ dataset_name: logical_args_zero_shot
3
+ include: ../multiple_choice_template_a_yaml
4
+ task: bigbench_logical_args_multiple_choice
scripts/yans/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
scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/logical_sequence.yaml ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ # Generated by utils.py
2
+ dataset_name: logical_sequence_zero_shot
3
+ include: ../multiple_choice_template_a_yaml
4
+ task: bigbench_logical_sequence_multiple_choice
scripts/yans/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
scripts/yans/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
scripts/yans/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
scripts/yans/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
scripts/yans/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
scripts/yans/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
scripts/yans/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
scripts/yans/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
scripts/yans/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