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/mmlu/continuation/mmlu_college_chemistry.yaml +6 -0
- lm-quant-toolkit/.deps/lm-evaluation-harness/lm_eval/tasks/mmlu/continuation/mmlu_computer_security.yaml +6 -0
- lm-quant-toolkit/.deps/lm-evaluation-harness/lm_eval/tasks/mmlu/continuation/mmlu_conceptual_physics.yaml +6 -0
- lm-quant-toolkit/.deps/lm-evaluation-harness/lm_eval/tasks/mmlu/continuation/mmlu_formal_logic.yaml +6 -0
- lm-quant-toolkit/.deps/lm-evaluation-harness/lm_eval/tasks/mmlu/continuation/mmlu_global_facts.yaml +6 -0
- lm-quant-toolkit/.deps/lm-evaluation-harness/lm_eval/tasks/mmlu/continuation/mmlu_high_school_biology.yaml +6 -0
- lm-quant-toolkit/.deps/lm-evaluation-harness/lm_eval/tasks/mmlu/continuation/mmlu_high_school_chemistry.yaml +6 -0
- lm-quant-toolkit/.deps/lm-evaluation-harness/lm_eval/tasks/mmlu/continuation/mmlu_high_school_computer_science.yaml +6 -0
- lm-quant-toolkit/.deps/lm-evaluation-harness/lm_eval/tasks/mmlu/continuation/mmlu_high_school_geography.yaml +6 -0
- lm-quant-toolkit/.deps/lm-evaluation-harness/lm_eval/tasks/mmlu/continuation/mmlu_high_school_government_and_politics.yaml +6 -0
- lm-quant-toolkit/.deps/lm-evaluation-harness/lm_eval/tasks/mmlu/continuation/mmlu_high_school_macroeconomics.yaml +6 -0
- lm-quant-toolkit/.deps/lm-evaluation-harness/lm_eval/tasks/mmlu/continuation/mmlu_high_school_mathematics.yaml +6 -0
- lm-quant-toolkit/.deps/lm-evaluation-harness/lm_eval/tasks/mmlu/continuation/mmlu_high_school_microeconomics.yaml +6 -0
- lm-quant-toolkit/.deps/lm-evaluation-harness/lm_eval/tasks/mmlu/continuation/mmlu_high_school_physics.yaml +6 -0
- lm-quant-toolkit/.deps/lm-evaluation-harness/lm_eval/tasks/mmlu/continuation/mmlu_high_school_psychology.yaml +6 -0
- lm-quant-toolkit/.deps/lm-evaluation-harness/lm_eval/tasks/mmlu/continuation/mmlu_high_school_statistics.yaml +6 -0
- lm-quant-toolkit/.deps/lm-evaluation-harness/lm_eval/tasks/mmlu/continuation/mmlu_high_school_us_history.yaml +6 -0
- lm-quant-toolkit/.deps/lm-evaluation-harness/lm_eval/tasks/mmlu/continuation/mmlu_high_school_world_history.yaml +6 -0
- lm-quant-toolkit/.deps/lm-evaluation-harness/lm_eval/tasks/mmlu/continuation/mmlu_human_aging.yaml +6 -0
- lm-quant-toolkit/.deps/lm-evaluation-harness/lm_eval/tasks/mmlu/continuation/mmlu_human_sexuality.yaml +6 -0
- lm-quant-toolkit/.deps/lm-evaluation-harness/lm_eval/tasks/mmlu/continuation/mmlu_international_law.yaml +6 -0
- lm-quant-toolkit/.deps/lm-evaluation-harness/lm_eval/tasks/mmlu/continuation/mmlu_jurisprudence.yaml +6 -0
- lm-quant-toolkit/.deps/lm-evaluation-harness/lm_eval/tasks/mmlu/continuation/mmlu_logical_fallacies.yaml +6 -0
- lm-quant-toolkit/.deps/lm-evaluation-harness/lm_eval/tasks/mmlu/continuation/mmlu_machine_learning.yaml +6 -0
- lm-quant-toolkit/.deps/lm-evaluation-harness/lm_eval/tasks/mmlu/continuation/mmlu_management.yaml +6 -0
- lm-quant-toolkit/.deps/lm-evaluation-harness/lm_eval/tasks/mmlu/continuation/mmlu_marketing.yaml +6 -0
- lm-quant-toolkit/.deps/lm-evaluation-harness/lm_eval/tasks/mmlu/continuation/mmlu_medical_genetics.yaml +6 -0
- lm-quant-toolkit/.deps/lm-evaluation-harness/lm_eval/tasks/mmlu/continuation/mmlu_miscellaneous.yaml +6 -0
- lm-quant-toolkit/.deps/lm-evaluation-harness/lm_eval/tasks/mmlu/continuation/mmlu_moral_disputes.yaml +6 -0
- lm-quant-toolkit/.deps/lm-evaluation-harness/lm_eval/tasks/mmlu/continuation/mmlu_moral_scenarios.yaml +6 -0
- lm-quant-toolkit/.deps/lm-evaluation-harness/lm_eval/tasks/mmlu/continuation/mmlu_nutrition.yaml +6 -0
- lm-quant-toolkit/.deps/lm-evaluation-harness/lm_eval/tasks/mmlu/continuation/mmlu_philosophy.yaml +6 -0
- lm-quant-toolkit/.deps/lm-evaluation-harness/lm_eval/tasks/mmlu/continuation/mmlu_prehistory.yaml +6 -0
- lm-quant-toolkit/.deps/lm-evaluation-harness/lm_eval/tasks/mmlu/continuation/mmlu_professional_accounting.yaml +6 -0
- lm-quant-toolkit/.deps/lm-evaluation-harness/lm_eval/tasks/mmlu/continuation/mmlu_professional_law.yaml +6 -0
- lm-quant-toolkit/.deps/lm-evaluation-harness/lm_eval/tasks/mmlu/continuation/mmlu_professional_medicine.yaml +6 -0
- lm-quant-toolkit/.deps/lm-evaluation-harness/lm_eval/tasks/mmlu/continuation/mmlu_professional_psychology.yaml +6 -0
- lm-quant-toolkit/.deps/lm-evaluation-harness/lm_eval/tasks/mmlu/continuation/mmlu_public_relations.yaml +6 -0
- lm-quant-toolkit/.deps/lm-evaluation-harness/lm_eval/tasks/mmlu/continuation/mmlu_security_studies.yaml +6 -0
- lm-quant-toolkit/.deps/lm-evaluation-harness/lm_eval/tasks/mmlu/continuation/mmlu_sociology.yaml +6 -0
- lm-quant-toolkit/.deps/lm-evaluation-harness/lm_eval/tasks/mmlu/continuation/mmlu_us_foreign_policy.yaml +6 -0
- lm-quant-toolkit/.deps/lm-evaluation-harness/lm_eval/tasks/mmlu/continuation/mmlu_virology.yaml +6 -0
- lm-quant-toolkit/.deps/lm-evaluation-harness/lm_eval/tasks/mmlu/continuation/mmlu_world_religions.yaml +6 -0
- lm-quant-toolkit/.deps/lm-evaluation-harness/lm_eval/tasks/mmlu/default/_default_template_yaml +17 -0
- lm-quant-toolkit/.deps/lm-evaluation-harness/lm_eval/tasks/mmlu/default/_mmlu.yaml +11 -0
- lm-quant-toolkit/.deps/lm-evaluation-harness/lm_eval/tasks/mmlu/default/_mmlu_humanities.yaml +9 -0
- lm-quant-toolkit/.deps/lm-evaluation-harness/lm_eval/tasks/mmlu/default/_mmlu_other.yaml +9 -0
- lm-quant-toolkit/.deps/lm-evaluation-harness/lm_eval/tasks/mmlu/default/_mmlu_social_sciences.yaml +9 -0
- lm-quant-toolkit/.deps/lm-evaluation-harness/lm_eval/tasks/mmlu/default/_mmlu_stem.yaml +9 -0
- lm-quant-toolkit/.deps/lm-evaluation-harness/lm_eval/tasks/mmlu/default/mmlu_abstract_algebra.yaml +7 -0
lm-quant-toolkit/.deps/lm-evaluation-harness/lm_eval/tasks/mmlu/continuation/mmlu_college_chemistry.yaml
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
"dataset_name": "college_chemistry"
|
| 2 |
+
"description": "The following are questions (with answers) about college\
|
| 3 |
+
\ chemistry.\n\n"
|
| 4 |
+
"tag": "mmlu_continuation_stem"
|
| 5 |
+
"include": "_continuation_template_yaml"
|
| 6 |
+
"task": "mmlu_continuation_college_chemistry"
|
lm-quant-toolkit/.deps/lm-evaluation-harness/lm_eval/tasks/mmlu/continuation/mmlu_computer_security.yaml
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
"dataset_name": "computer_security"
|
| 2 |
+
"description": "The following are questions (with answers) about computer\
|
| 3 |
+
\ security.\n\n"
|
| 4 |
+
"tag": "mmlu_continuation_stem"
|
| 5 |
+
"include": "_continuation_template_yaml"
|
| 6 |
+
"task": "mmlu_continuation_computer_security"
|
lm-quant-toolkit/.deps/lm-evaluation-harness/lm_eval/tasks/mmlu/continuation/mmlu_conceptual_physics.yaml
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
"dataset_name": "conceptual_physics"
|
| 2 |
+
"description": "The following are questions (with answers) about conceptual\
|
| 3 |
+
\ physics.\n\n"
|
| 4 |
+
"tag": "mmlu_continuation_stem"
|
| 5 |
+
"include": "_continuation_template_yaml"
|
| 6 |
+
"task": "mmlu_continuation_conceptual_physics"
|
lm-quant-toolkit/.deps/lm-evaluation-harness/lm_eval/tasks/mmlu/continuation/mmlu_formal_logic.yaml
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
"dataset_name": "formal_logic"
|
| 2 |
+
"description": "The following are questions (with answers) about formal\
|
| 3 |
+
\ logic.\n\n"
|
| 4 |
+
"tag": "mmlu_continuation_humanities"
|
| 5 |
+
"include": "_continuation_template_yaml"
|
| 6 |
+
"task": "mmlu_continuation_formal_logic"
|
lm-quant-toolkit/.deps/lm-evaluation-harness/lm_eval/tasks/mmlu/continuation/mmlu_global_facts.yaml
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
"dataset_name": "global_facts"
|
| 2 |
+
"description": "The following are questions (with answers) about global\
|
| 3 |
+
\ facts.\n\n"
|
| 4 |
+
"tag": "mmlu_continuation_other"
|
| 5 |
+
"include": "_continuation_template_yaml"
|
| 6 |
+
"task": "mmlu_continuation_global_facts"
|
lm-quant-toolkit/.deps/lm-evaluation-harness/lm_eval/tasks/mmlu/continuation/mmlu_high_school_biology.yaml
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
"dataset_name": "high_school_biology"
|
| 2 |
+
"description": "The following are questions (with answers) about high\
|
| 3 |
+
\ school biology.\n\n"
|
| 4 |
+
"tag": "mmlu_continuation_stem"
|
| 5 |
+
"include": "_continuation_template_yaml"
|
| 6 |
+
"task": "mmlu_continuation_high_school_biology"
|
lm-quant-toolkit/.deps/lm-evaluation-harness/lm_eval/tasks/mmlu/continuation/mmlu_high_school_chemistry.yaml
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
"dataset_name": "high_school_chemistry"
|
| 2 |
+
"description": "The following are questions (with answers) about high\
|
| 3 |
+
\ school chemistry.\n\n"
|
| 4 |
+
"tag": "mmlu_continuation_stem"
|
| 5 |
+
"include": "_continuation_template_yaml"
|
| 6 |
+
"task": "mmlu_continuation_high_school_chemistry"
|
lm-quant-toolkit/.deps/lm-evaluation-harness/lm_eval/tasks/mmlu/continuation/mmlu_high_school_computer_science.yaml
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
"dataset_name": "high_school_computer_science"
|
| 2 |
+
"description": "The following are questions (with answers) about high\
|
| 3 |
+
\ school computer science.\n\n"
|
| 4 |
+
"tag": "mmlu_continuation_stem"
|
| 5 |
+
"include": "_continuation_template_yaml"
|
| 6 |
+
"task": "mmlu_continuation_high_school_computer_science"
|
lm-quant-toolkit/.deps/lm-evaluation-harness/lm_eval/tasks/mmlu/continuation/mmlu_high_school_geography.yaml
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
"dataset_name": "high_school_geography"
|
| 2 |
+
"description": "The following are questions (with answers) about high\
|
| 3 |
+
\ school geography.\n\n"
|
| 4 |
+
"tag": "mmlu_continuation_social_sciences"
|
| 5 |
+
"include": "_continuation_template_yaml"
|
| 6 |
+
"task": "mmlu_continuation_high_school_geography"
|
lm-quant-toolkit/.deps/lm-evaluation-harness/lm_eval/tasks/mmlu/continuation/mmlu_high_school_government_and_politics.yaml
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
"dataset_name": "high_school_government_and_politics"
|
| 2 |
+
"description": "The following are questions (with answers) about high\
|
| 3 |
+
\ school government and politics.\n\n"
|
| 4 |
+
"tag": "mmlu_continuation_social_sciences"
|
| 5 |
+
"include": "_continuation_template_yaml"
|
| 6 |
+
"task": "mmlu_continuation_high_school_government_and_politics"
|
lm-quant-toolkit/.deps/lm-evaluation-harness/lm_eval/tasks/mmlu/continuation/mmlu_high_school_macroeconomics.yaml
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
"dataset_name": "high_school_macroeconomics"
|
| 2 |
+
"description": "The following are questions (with answers) about high\
|
| 3 |
+
\ school macroeconomics.\n\n"
|
| 4 |
+
"tag": "mmlu_continuation_social_sciences"
|
| 5 |
+
"include": "_continuation_template_yaml"
|
| 6 |
+
"task": "mmlu_continuation_high_school_macroeconomics"
|
lm-quant-toolkit/.deps/lm-evaluation-harness/lm_eval/tasks/mmlu/continuation/mmlu_high_school_mathematics.yaml
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
"dataset_name": "high_school_mathematics"
|
| 2 |
+
"description": "The following are questions (with answers) about high\
|
| 3 |
+
\ school mathematics.\n\n"
|
| 4 |
+
"tag": "mmlu_continuation_stem"
|
| 5 |
+
"include": "_continuation_template_yaml"
|
| 6 |
+
"task": "mmlu_continuation_high_school_mathematics"
|
lm-quant-toolkit/.deps/lm-evaluation-harness/lm_eval/tasks/mmlu/continuation/mmlu_high_school_microeconomics.yaml
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
"dataset_name": "high_school_microeconomics"
|
| 2 |
+
"description": "The following are questions (with answers) about high\
|
| 3 |
+
\ school microeconomics.\n\n"
|
| 4 |
+
"tag": "mmlu_continuation_social_sciences"
|
| 5 |
+
"include": "_continuation_template_yaml"
|
| 6 |
+
"task": "mmlu_continuation_high_school_microeconomics"
|
lm-quant-toolkit/.deps/lm-evaluation-harness/lm_eval/tasks/mmlu/continuation/mmlu_high_school_physics.yaml
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
"dataset_name": "high_school_physics"
|
| 2 |
+
"description": "The following are questions (with answers) about high\
|
| 3 |
+
\ school physics.\n\n"
|
| 4 |
+
"tag": "mmlu_continuation_stem"
|
| 5 |
+
"include": "_continuation_template_yaml"
|
| 6 |
+
"task": "mmlu_continuation_high_school_physics"
|
lm-quant-toolkit/.deps/lm-evaluation-harness/lm_eval/tasks/mmlu/continuation/mmlu_high_school_psychology.yaml
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
"dataset_name": "high_school_psychology"
|
| 2 |
+
"description": "The following are questions (with answers) about high\
|
| 3 |
+
\ school psychology.\n\n"
|
| 4 |
+
"tag": "mmlu_continuation_social_sciences"
|
| 5 |
+
"include": "_continuation_template_yaml"
|
| 6 |
+
"task": "mmlu_continuation_high_school_psychology"
|
lm-quant-toolkit/.deps/lm-evaluation-harness/lm_eval/tasks/mmlu/continuation/mmlu_high_school_statistics.yaml
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
"dataset_name": "high_school_statistics"
|
| 2 |
+
"description": "The following are questions (with answers) about high\
|
| 3 |
+
\ school statistics.\n\n"
|
| 4 |
+
"tag": "mmlu_continuation_stem"
|
| 5 |
+
"include": "_continuation_template_yaml"
|
| 6 |
+
"task": "mmlu_continuation_high_school_statistics"
|
lm-quant-toolkit/.deps/lm-evaluation-harness/lm_eval/tasks/mmlu/continuation/mmlu_high_school_us_history.yaml
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
"dataset_name": "high_school_us_history"
|
| 2 |
+
"description": "The following are questions (with answers) about high\
|
| 3 |
+
\ school us history.\n\n"
|
| 4 |
+
"tag": "mmlu_continuation_humanities"
|
| 5 |
+
"include": "_continuation_template_yaml"
|
| 6 |
+
"task": "mmlu_continuation_high_school_us_history"
|
lm-quant-toolkit/.deps/lm-evaluation-harness/lm_eval/tasks/mmlu/continuation/mmlu_high_school_world_history.yaml
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
"dataset_name": "high_school_world_history"
|
| 2 |
+
"description": "The following are questions (with answers) about high\
|
| 3 |
+
\ school world history.\n\n"
|
| 4 |
+
"tag": "mmlu_continuation_humanities"
|
| 5 |
+
"include": "_continuation_template_yaml"
|
| 6 |
+
"task": "mmlu_continuation_high_school_world_history"
|
lm-quant-toolkit/.deps/lm-evaluation-harness/lm_eval/tasks/mmlu/continuation/mmlu_human_aging.yaml
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
"dataset_name": "human_aging"
|
| 2 |
+
"description": "The following are questions (with answers) about human\
|
| 3 |
+
\ aging.\n\n"
|
| 4 |
+
"tag": "mmlu_continuation_other"
|
| 5 |
+
"include": "_continuation_template_yaml"
|
| 6 |
+
"task": "mmlu_continuation_human_aging"
|
lm-quant-toolkit/.deps/lm-evaluation-harness/lm_eval/tasks/mmlu/continuation/mmlu_human_sexuality.yaml
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
"dataset_name": "human_sexuality"
|
| 2 |
+
"description": "The following are questions (with answers) about human\
|
| 3 |
+
\ sexuality.\n\n"
|
| 4 |
+
"tag": "mmlu_continuation_social_sciences"
|
| 5 |
+
"include": "_continuation_template_yaml"
|
| 6 |
+
"task": "mmlu_continuation_human_sexuality"
|
lm-quant-toolkit/.deps/lm-evaluation-harness/lm_eval/tasks/mmlu/continuation/mmlu_international_law.yaml
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
"dataset_name": "international_law"
|
| 2 |
+
"description": "The following are questions (with answers) about international\
|
| 3 |
+
\ law.\n\n"
|
| 4 |
+
"tag": "mmlu_continuation_humanities"
|
| 5 |
+
"include": "_continuation_template_yaml"
|
| 6 |
+
"task": "mmlu_continuation_international_law"
|
lm-quant-toolkit/.deps/lm-evaluation-harness/lm_eval/tasks/mmlu/continuation/mmlu_jurisprudence.yaml
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
"dataset_name": "jurisprudence"
|
| 2 |
+
"description": "The following are questions (with answers) about jurisprudence.\n\
|
| 3 |
+
\n"
|
| 4 |
+
"tag": "mmlu_continuation_humanities"
|
| 5 |
+
"include": "_continuation_template_yaml"
|
| 6 |
+
"task": "mmlu_continuation_jurisprudence"
|
lm-quant-toolkit/.deps/lm-evaluation-harness/lm_eval/tasks/mmlu/continuation/mmlu_logical_fallacies.yaml
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
"dataset_name": "logical_fallacies"
|
| 2 |
+
"description": "The following are questions (with answers) about logical\
|
| 3 |
+
\ fallacies.\n\n"
|
| 4 |
+
"tag": "mmlu_continuation_humanities"
|
| 5 |
+
"include": "_continuation_template_yaml"
|
| 6 |
+
"task": "mmlu_continuation_logical_fallacies"
|
lm-quant-toolkit/.deps/lm-evaluation-harness/lm_eval/tasks/mmlu/continuation/mmlu_machine_learning.yaml
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
"dataset_name": "machine_learning"
|
| 2 |
+
"description": "The following are questions (with answers) about machine\
|
| 3 |
+
\ learning.\n\n"
|
| 4 |
+
"tag": "mmlu_continuation_stem"
|
| 5 |
+
"include": "_continuation_template_yaml"
|
| 6 |
+
"task": "mmlu_continuation_machine_learning"
|
lm-quant-toolkit/.deps/lm-evaluation-harness/lm_eval/tasks/mmlu/continuation/mmlu_management.yaml
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
"dataset_name": "management"
|
| 2 |
+
"description": "The following are questions (with answers) about management.\n\
|
| 3 |
+
\n"
|
| 4 |
+
"tag": "mmlu_continuation_other"
|
| 5 |
+
"include": "_continuation_template_yaml"
|
| 6 |
+
"task": "mmlu_continuation_management"
|
lm-quant-toolkit/.deps/lm-evaluation-harness/lm_eval/tasks/mmlu/continuation/mmlu_marketing.yaml
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
"dataset_name": "marketing"
|
| 2 |
+
"description": "The following are questions (with answers) about marketing.\n\
|
| 3 |
+
\n"
|
| 4 |
+
"tag": "mmlu_continuation_other"
|
| 5 |
+
"include": "_continuation_template_yaml"
|
| 6 |
+
"task": "mmlu_continuation_marketing"
|
lm-quant-toolkit/.deps/lm-evaluation-harness/lm_eval/tasks/mmlu/continuation/mmlu_medical_genetics.yaml
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
"dataset_name": "medical_genetics"
|
| 2 |
+
"description": "The following are questions (with answers) about medical\
|
| 3 |
+
\ genetics.\n\n"
|
| 4 |
+
"tag": "mmlu_continuation_other"
|
| 5 |
+
"include": "_continuation_template_yaml"
|
| 6 |
+
"task": "mmlu_continuation_medical_genetics"
|
lm-quant-toolkit/.deps/lm-evaluation-harness/lm_eval/tasks/mmlu/continuation/mmlu_miscellaneous.yaml
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
"dataset_name": "miscellaneous"
|
| 2 |
+
"description": "The following are questions (with answers) about miscellaneous.\n\
|
| 3 |
+
\n"
|
| 4 |
+
"tag": "mmlu_continuation_other"
|
| 5 |
+
"include": "_continuation_template_yaml"
|
| 6 |
+
"task": "mmlu_continuation_miscellaneous"
|
lm-quant-toolkit/.deps/lm-evaluation-harness/lm_eval/tasks/mmlu/continuation/mmlu_moral_disputes.yaml
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
"dataset_name": "moral_disputes"
|
| 2 |
+
"description": "The following are questions (with answers) about moral\
|
| 3 |
+
\ disputes.\n\n"
|
| 4 |
+
"tag": "mmlu_continuation_humanities"
|
| 5 |
+
"include": "_continuation_template_yaml"
|
| 6 |
+
"task": "mmlu_continuation_moral_disputes"
|
lm-quant-toolkit/.deps/lm-evaluation-harness/lm_eval/tasks/mmlu/continuation/mmlu_moral_scenarios.yaml
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
"dataset_name": "moral_scenarios"
|
| 2 |
+
"description": "The following are questions (with answers) about moral\
|
| 3 |
+
\ scenarios.\n\n"
|
| 4 |
+
"tag": "mmlu_continuation_humanities"
|
| 5 |
+
"include": "_continuation_template_yaml"
|
| 6 |
+
"task": "mmlu_continuation_moral_scenarios"
|
lm-quant-toolkit/.deps/lm-evaluation-harness/lm_eval/tasks/mmlu/continuation/mmlu_nutrition.yaml
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
"dataset_name": "nutrition"
|
| 2 |
+
"description": "The following are questions (with answers) about nutrition.\n\
|
| 3 |
+
\n"
|
| 4 |
+
"tag": "mmlu_continuation_other"
|
| 5 |
+
"include": "_continuation_template_yaml"
|
| 6 |
+
"task": "mmlu_continuation_nutrition"
|
lm-quant-toolkit/.deps/lm-evaluation-harness/lm_eval/tasks/mmlu/continuation/mmlu_philosophy.yaml
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
"dataset_name": "philosophy"
|
| 2 |
+
"description": "The following are questions (with answers) about philosophy.\n\
|
| 3 |
+
\n"
|
| 4 |
+
"tag": "mmlu_continuation_humanities"
|
| 5 |
+
"include": "_continuation_template_yaml"
|
| 6 |
+
"task": "mmlu_continuation_philosophy"
|
lm-quant-toolkit/.deps/lm-evaluation-harness/lm_eval/tasks/mmlu/continuation/mmlu_prehistory.yaml
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
"dataset_name": "prehistory"
|
| 2 |
+
"description": "The following are questions (with answers) about prehistory.\n\
|
| 3 |
+
\n"
|
| 4 |
+
"tag": "mmlu_continuation_humanities"
|
| 5 |
+
"include": "_continuation_template_yaml"
|
| 6 |
+
"task": "mmlu_continuation_prehistory"
|
lm-quant-toolkit/.deps/lm-evaluation-harness/lm_eval/tasks/mmlu/continuation/mmlu_professional_accounting.yaml
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
"dataset_name": "professional_accounting"
|
| 2 |
+
"description": "The following are questions (with answers) about professional\
|
| 3 |
+
\ accounting.\n\n"
|
| 4 |
+
"tag": "mmlu_continuation_other"
|
| 5 |
+
"include": "_continuation_template_yaml"
|
| 6 |
+
"task": "mmlu_continuation_professional_accounting"
|
lm-quant-toolkit/.deps/lm-evaluation-harness/lm_eval/tasks/mmlu/continuation/mmlu_professional_law.yaml
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
"dataset_name": "professional_law"
|
| 2 |
+
"description": "The following are questions (with answers) about professional\
|
| 3 |
+
\ law.\n\n"
|
| 4 |
+
"tag": "mmlu_continuation_humanities"
|
| 5 |
+
"include": "_continuation_template_yaml"
|
| 6 |
+
"task": "mmlu_continuation_professional_law"
|
lm-quant-toolkit/.deps/lm-evaluation-harness/lm_eval/tasks/mmlu/continuation/mmlu_professional_medicine.yaml
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
"dataset_name": "professional_medicine"
|
| 2 |
+
"description": "The following are questions (with answers) about professional\
|
| 3 |
+
\ medicine.\n\n"
|
| 4 |
+
"tag": "mmlu_continuation_other"
|
| 5 |
+
"include": "_continuation_template_yaml"
|
| 6 |
+
"task": "mmlu_continuation_professional_medicine"
|
lm-quant-toolkit/.deps/lm-evaluation-harness/lm_eval/tasks/mmlu/continuation/mmlu_professional_psychology.yaml
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
"dataset_name": "professional_psychology"
|
| 2 |
+
"description": "The following are questions (with answers) about professional\
|
| 3 |
+
\ psychology.\n\n"
|
| 4 |
+
"tag": "mmlu_continuation_social_sciences"
|
| 5 |
+
"include": "_continuation_template_yaml"
|
| 6 |
+
"task": "mmlu_continuation_professional_psychology"
|
lm-quant-toolkit/.deps/lm-evaluation-harness/lm_eval/tasks/mmlu/continuation/mmlu_public_relations.yaml
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
"dataset_name": "public_relations"
|
| 2 |
+
"description": "The following are questions (with answers) about public\
|
| 3 |
+
\ relations.\n\n"
|
| 4 |
+
"tag": "mmlu_continuation_social_sciences"
|
| 5 |
+
"include": "_continuation_template_yaml"
|
| 6 |
+
"task": "mmlu_continuation_public_relations"
|
lm-quant-toolkit/.deps/lm-evaluation-harness/lm_eval/tasks/mmlu/continuation/mmlu_security_studies.yaml
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
"dataset_name": "security_studies"
|
| 2 |
+
"description": "The following are questions (with answers) about security\
|
| 3 |
+
\ studies.\n\n"
|
| 4 |
+
"tag": "mmlu_continuation_social_sciences"
|
| 5 |
+
"include": "_continuation_template_yaml"
|
| 6 |
+
"task": "mmlu_continuation_security_studies"
|
lm-quant-toolkit/.deps/lm-evaluation-harness/lm_eval/tasks/mmlu/continuation/mmlu_sociology.yaml
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
"dataset_name": "sociology"
|
| 2 |
+
"description": "The following are questions (with answers) about sociology.\n\
|
| 3 |
+
\n"
|
| 4 |
+
"tag": "mmlu_continuation_social_sciences"
|
| 5 |
+
"include": "_continuation_template_yaml"
|
| 6 |
+
"task": "mmlu_continuation_sociology"
|
lm-quant-toolkit/.deps/lm-evaluation-harness/lm_eval/tasks/mmlu/continuation/mmlu_us_foreign_policy.yaml
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
"dataset_name": "us_foreign_policy"
|
| 2 |
+
"description": "The following are questions (with answers) about us\
|
| 3 |
+
\ foreign policy.\n\n"
|
| 4 |
+
"tag": "mmlu_continuation_social_sciences"
|
| 5 |
+
"include": "_continuation_template_yaml"
|
| 6 |
+
"task": "mmlu_continuation_us_foreign_policy"
|
lm-quant-toolkit/.deps/lm-evaluation-harness/lm_eval/tasks/mmlu/continuation/mmlu_virology.yaml
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
"dataset_name": "virology"
|
| 2 |
+
"description": "The following are questions (with answers) about virology.\n\
|
| 3 |
+
\n"
|
| 4 |
+
"tag": "mmlu_continuation_other"
|
| 5 |
+
"include": "_continuation_template_yaml"
|
| 6 |
+
"task": "mmlu_continuation_virology"
|
lm-quant-toolkit/.deps/lm-evaluation-harness/lm_eval/tasks/mmlu/continuation/mmlu_world_religions.yaml
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
"dataset_name": "world_religions"
|
| 2 |
+
"description": "The following are questions (with answers) about world\
|
| 3 |
+
\ religions.\n\n"
|
| 4 |
+
"tag": "mmlu_continuation_humanities"
|
| 5 |
+
"include": "_continuation_template_yaml"
|
| 6 |
+
"task": "mmlu_continuation_world_religions"
|
lm-quant-toolkit/.deps/lm-evaluation-harness/lm_eval/tasks/mmlu/default/_default_template_yaml
ADDED
|
@@ -0,0 +1,17 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
dataset_path: hails/mmlu_no_train # a copy of `cais/mmlu` with no auxiliary_train split
|
| 2 |
+
test_split: test
|
| 3 |
+
fewshot_split: dev
|
| 4 |
+
fewshot_config:
|
| 5 |
+
sampler: first_n
|
| 6 |
+
output_type: multiple_choice
|
| 7 |
+
doc_to_text: "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:"
|
| 8 |
+
doc_to_choice: ["A", "B", "C", "D"]
|
| 9 |
+
doc_to_target: answer
|
| 10 |
+
metric_list:
|
| 11 |
+
- metric: acc
|
| 12 |
+
aggregation: mean
|
| 13 |
+
higher_is_better: true
|
| 14 |
+
metadata:
|
| 15 |
+
version: 1.0
|
| 16 |
+
dataset_kwargs:
|
| 17 |
+
trust_remote_code: true
|
lm-quant-toolkit/.deps/lm-evaluation-harness/lm_eval/tasks/mmlu/default/_mmlu.yaml
ADDED
|
@@ -0,0 +1,11 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
group: mmlu
|
| 2 |
+
task:
|
| 3 |
+
- mmlu_stem
|
| 4 |
+
- mmlu_other
|
| 5 |
+
- mmlu_social_sciences
|
| 6 |
+
- mmlu_humanities
|
| 7 |
+
aggregate_metric_list:
|
| 8 |
+
- metric: acc
|
| 9 |
+
weight_by_size: True
|
| 10 |
+
metadata:
|
| 11 |
+
version: 2
|
lm-quant-toolkit/.deps/lm-evaluation-harness/lm_eval/tasks/mmlu/default/_mmlu_humanities.yaml
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
group: mmlu_humanities
|
| 2 |
+
group_alias: humanities
|
| 3 |
+
task:
|
| 4 |
+
- mmlu_humanities_tasks
|
| 5 |
+
aggregate_metric_list:
|
| 6 |
+
- metric: acc
|
| 7 |
+
weight_by_size: True
|
| 8 |
+
metadata:
|
| 9 |
+
version: 2
|
lm-quant-toolkit/.deps/lm-evaluation-harness/lm_eval/tasks/mmlu/default/_mmlu_other.yaml
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
group: mmlu_other
|
| 2 |
+
group_alias: other
|
| 3 |
+
task:
|
| 4 |
+
- mmlu_other_tasks
|
| 5 |
+
aggregate_metric_list:
|
| 6 |
+
- metric: acc
|
| 7 |
+
weight_by_size: True
|
| 8 |
+
metadata:
|
| 9 |
+
version: 2
|
lm-quant-toolkit/.deps/lm-evaluation-harness/lm_eval/tasks/mmlu/default/_mmlu_social_sciences.yaml
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
group: mmlu_social_sciences
|
| 2 |
+
group_alias: social sciences
|
| 3 |
+
task:
|
| 4 |
+
- mmlu_social_sciences_tasks
|
| 5 |
+
aggregate_metric_list:
|
| 6 |
+
- metric: acc
|
| 7 |
+
weight_by_size: True
|
| 8 |
+
metadata:
|
| 9 |
+
version: 2
|
lm-quant-toolkit/.deps/lm-evaluation-harness/lm_eval/tasks/mmlu/default/_mmlu_stem.yaml
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
group: mmlu_stem
|
| 2 |
+
group_alias: stem
|
| 3 |
+
task:
|
| 4 |
+
- mmlu_stem_tasks
|
| 5 |
+
aggregate_metric_list:
|
| 6 |
+
- metric: acc
|
| 7 |
+
weight_by_size: True
|
| 8 |
+
metadata:
|
| 9 |
+
version: 2
|
lm-quant-toolkit/.deps/lm-evaluation-harness/lm_eval/tasks/mmlu/default/mmlu_abstract_algebra.yaml
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
"dataset_name": "abstract_algebra"
|
| 2 |
+
"description": "The following are multiple choice questions (with answers) about abstract\
|
| 3 |
+
\ algebra.\n\n"
|
| 4 |
+
"tag": "mmlu_stem_tasks"
|
| 5 |
+
"include": "_default_template_yaml"
|
| 6 |
+
"task": "mmlu_abstract_algebra"
|
| 7 |
+
"task_alias": "abstract_algebra"
|