├── README.md ├── confs ├── ARC-c │ ├── InternLM+Mistral+Yi+Skywork.json │ ├── InternLM+Mistral.json │ └── baseline │ │ ├── InternLM.json │ │ ├── LLaMA.json │ │ ├── Mistral.json │ │ ├── Skywork.json │ │ ├── Tigerbot.json │ │ └── Yi.json ├── GSM8K │ ├── 2models │ │ ├── InternLM+Skywork.json │ │ ├── InternLM+Skywork1.json │ │ ├── InternLM+Skywork2.json │ │ ├── InternLM+Skywork3.json │ │ └── InternLM+Skywork4.json │ ├── 4models │ │ ├── Sky4_1.json │ │ ├── Sky4_2.json │ │ ├── Sky4_3.json │ │ └── Sky4_4.json │ └── baseline │ │ ├── InternLM.json │ │ ├── LLaMA.json │ │ ├── Mistral.json │ │ ├── Skywork.json │ │ ├── Tigerbot.json │ │ └── Yi.json ├── MMLU │ ├── Yi+Mistral+Skywork+InernLM.json │ ├── Yi+Mistral.json │ └── baseline │ │ ├── InternLM.json │ │ ├── LLaMA.json │ │ ├── Mistral.json │ │ ├── Nanbeige.json │ │ ├── Skywork.json │ │ ├── Tigerbot.json │ │ └── Yi.json ├── NQ │ ├── LLaMA+Mistral+InternLM+Tigerbot.json │ ├── LLaMA+Mistral.json │ └── baseline │ │ ├── InternLM.json │ │ ├── LLaMA.json │ │ ├── LLaMA70.json │ │ ├── Mistral.json │ │ ├── Mixtral.json │ │ ├── Nanbeige.json │ │ ├── Skywork.json │ │ ├── Tigerbot.json │ │ └── Yi.json ├── PIQA │ ├── Yi+Skywork+Tigerbot+Mistral.json │ ├── Yi+Skywork.json │ └── baseline │ │ ├── InternLM.json │ │ ├── LLaMA.json │ │ ├── LLaMA70.json │ │ ├── Mistral.json │ │ ├── Mixtral.json │ │ ├── Nanbeige.json │ │ ├── Skywork.json │ │ ├── Tigerbot.json │ │ └── Yi.json └── TriviaQA │ ├── LLaMA+Mistral+InternLM+Tigerbot.json │ ├── LLaMA+Mistral.json │ └── baseline │ ├── InternLM.json │ ├── LLaMA.json │ ├── Mistral.json │ ├── Skywork.json │ ├── Tigerbot.json │ └── Yi.json ├── datasets ├── ARC-Challenge │ ├── test.jsonl │ └── train.jsonl ├── GSM │ └── data │ │ ├── demon_4.jsonl │ │ ├── test.cleand.jsonl │ │ └── train_sample300_seed42.cleand.jsonl ├── MMLU │ ├── dev-jsonl │ │ ├── abstract_algebra.jsonl │ │ ├── anatomy.jsonl │ │ ├── astronomy.jsonl │ │ ├── business_ethics.jsonl │ │ ├── clinical_knowledge.jsonl │ │ ├── college_biology.jsonl │ │ ├── college_chemistry.jsonl │ │ ├── college_computer_science.jsonl │ │ ├── college_mathematics.jsonl │ │ ├── college_medicine.jsonl │ │ ├── college_physics.jsonl │ │ ├── computer_security.jsonl │ │ ├── conceptual_physics.jsonl │ │ ├── econometrics.jsonl │ │ ├── electrical_engineering.jsonl │ │ ├── elementary_mathematics.jsonl │ │ ├── formal_logic.jsonl │ │ ├── global_facts.jsonl │ │ ├── high_school_biology.jsonl │ │ ├── high_school_chemistry.jsonl │ │ ├── high_school_computer_science.jsonl │ │ ├── high_school_european_history.jsonl │ │ ├── high_school_geography.jsonl │ │ ├── high_school_government_and_politics.jsonl │ │ ├── high_school_macroeconomics.jsonl │ │ ├── high_school_mathematics.jsonl │ │ ├── high_school_microeconomics.jsonl │ │ ├── high_school_physics.jsonl │ │ ├── high_school_psychology.jsonl │ │ ├── high_school_statistics.jsonl │ │ ├── high_school_us_history.jsonl │ │ ├── high_school_world_history.jsonl │ │ ├── human_aging.jsonl │ │ ├── human_sexuality.jsonl │ │ ├── international_law.jsonl │ │ ├── jurisprudence.jsonl │ │ ├── logical_fallacies.jsonl │ │ ├── machine_learning.jsonl │ │ ├── management.jsonl │ │ ├── marketing.jsonl │ │ ├── medical_genetics.jsonl │ │ ├── miscellaneous.jsonl │ │ ├── moral_disputes.jsonl │ │ ├── moral_scenarios.jsonl │ │ ├── nutrition.jsonl │ │ ├── philosophy.jsonl │ │ ├── prehistory.jsonl │ │ ├── professional_accounting.jsonl │ │ ├── professional_law.jsonl │ │ ├── professional_medicine.jsonl │ │ ├── professional_psychology.jsonl │ │ ├── public_relations.jsonl │ │ ├── security_studies.jsonl │ │ ├── sociology.jsonl │ │ ├── us_foreign_policy.jsonl │ │ ├── virology.jsonl │ │ └── world_religions.jsonl │ ├── test-jsonl │ │ ├── abstract_algebra.jsonl │ │ ├── anatomy.jsonl │ │ ├── astronomy.jsonl │ │ ├── business_ethics.jsonl │ │ ├── clinical_knowledge.jsonl │ │ ├── college_biology.jsonl │ │ ├── college_chemistry.jsonl │ │ ├── college_computer_science.jsonl │ │ ├── college_mathematics.jsonl │ │ ├── college_medicine.jsonl │ │ ├── college_physics.jsonl │ │ ├── computer_security.jsonl │ │ ├── conceptual_physics.jsonl │ │ ├── econometrics.jsonl │ │ ├── electrical_engineering.jsonl │ │ ├── elementary_mathematics.jsonl │ │ ├── formal_logic.jsonl │ │ ├── global_facts.jsonl │ │ ├── high_school_biology.jsonl │ │ ├── high_school_chemistry.jsonl │ │ ├── high_school_computer_science.jsonl │ │ ├── high_school_european_history.jsonl │ │ ├── high_school_geography.jsonl │ │ ├── high_school_government_and_politics.jsonl │ │ ├── high_school_macroeconomics.jsonl │ │ ├── high_school_mathematics.jsonl │ │ ├── high_school_microeconomics.jsonl │ │ ├── high_school_physics.jsonl │ │ ├── high_school_psychology.jsonl │ │ ├── high_school_statistics.jsonl │ │ ├── high_school_us_history.jsonl │ │ ├── high_school_world_history.jsonl │ │ ├── human_aging.jsonl │ │ ├── human_sexuality.jsonl │ │ ├── international_law.jsonl │ │ ├── jurisprudence.jsonl │ │ ├── logical_fallacies.jsonl │ │ ├── machine_learning.jsonl │ │ ├── management.jsonl │ │ ├── marketing.jsonl │ │ ├── medical_genetics.jsonl │ │ ├── miscellaneous.jsonl │ │ ├── moral_disputes.jsonl │ │ ├── moral_scenarios.jsonl │ │ ├── nutrition.jsonl │ │ ├── philosophy.jsonl │ │ ├── prehistory.jsonl │ │ ├── professional_accounting.jsonl │ │ ├── professional_law.jsonl │ │ ├── professional_medicine.jsonl │ │ ├── professional_psychology.jsonl │ │ ├── public_relations.jsonl │ │ ├── security_studies.jsonl │ │ ├── sociology.jsonl │ │ ├── us_foreign_policy.jsonl │ │ ├── virology.jsonl │ │ └── world_religions.jsonl │ └── val-jsonl │ │ ├── abstract_algebra.jsonl │ │ ├── anatomy.jsonl │ │ ├── astronomy.jsonl │ │ ├── business_ethics.jsonl │ │ ├── clinical_knowledge.jsonl │ │ ├── college_biology.jsonl │ │ ├── college_chemistry.jsonl │ │ ├── college_computer_science.jsonl │ │ ├── college_mathematics.jsonl │ │ ├── college_medicine.jsonl │ │ ├── college_physics.jsonl │ │ ├── computer_security.jsonl │ │ ├── conceptual_physics.jsonl │ │ ├── econometrics.jsonl │ │ ├── electrical_engineering.jsonl │ │ ├── elementary_mathematics.jsonl │ │ ├── formal_logic.jsonl │ │ ├── global_facts.jsonl │ │ ├── high_school_biology.jsonl │ │ ├── high_school_chemistry.jsonl │ │ ├── high_school_computer_science.jsonl │ │ ├── high_school_european_history.jsonl │ │ ├── high_school_geography.jsonl │ │ ├── high_school_government_and_politics.jsonl │ │ ├── high_school_macroeconomics.jsonl │ │ ├── high_school_mathematics.jsonl │ │ ├── high_school_microeconomics.jsonl │ │ ├── high_school_physics.jsonl │ │ ├── high_school_psychology.jsonl │ │ ├── high_school_statistics.jsonl │ │ ├── high_school_us_history.jsonl │ │ ├── high_school_world_history.jsonl │ │ ├── human_aging.jsonl │ │ ├── human_sexuality.jsonl │ │ ├── international_law.jsonl │ │ ├── jurisprudence.jsonl │ │ ├── logical_fallacies.jsonl │ │ ├── machine_learning.jsonl │ │ ├── management.jsonl │ │ ├── marketing.jsonl │ │ ├── medical_genetics.jsonl │ │ ├── miscellaneous.jsonl │ │ ├── moral_disputes.jsonl │ │ ├── moral_scenarios.jsonl │ │ ├── nutrition.jsonl │ │ ├── philosophy.jsonl │ │ ├── prehistory.jsonl │ │ ├── professional_accounting.jsonl │ │ ├── professional_law.jsonl │ │ ├── professional_medicine.jsonl │ │ ├── professional_psychology.jsonl │ │ ├── public_relations.jsonl │ │ ├── security_studies.jsonl │ │ ├── sociology.jsonl │ │ ├── us_foreign_policy.jsonl │ │ ├── virology.jsonl │ │ └── world_religions.jsonl ├── NaturalQuestions │ ├── dev │ │ ├── v1.0-simplified_simplified-nq-train.simpled_dev_100000_sample1600_seed42.jsonl │ │ └── v1.0-simplified_simplified-nq-train.simpled_few_shot_doman_6926_sample5_seed43.jsonl │ └── test │ │ └── natural-questions.jsonl ├── PIQA │ └── physicaliqa-train-dev │ │ ├── dev_our.jsonl │ │ └── train_our.jsonl └── TriviaQA │ ├── wikipedia-demon-all_sample5_seed42.jsonl │ ├── wikipedia-dev-1900.jsonl │ └── wikipedia-test-6000.jsonl ├── figures ├── Ensemble_Dense_and_Sparse.png ├── Ensemble_LLM_and_Expert.png ├── Main_Experiment.jpeg ├── Method.jpg ├── Multi_model_ensemble.jpg ├── no ├── overview.png └── performance.png ├── src ├── assist_model_thread.py ├── instruction_generate.py ├── logits_processor │ ├── assist_model_logits_processor.py │ ├── based_on_probaility_transfer_logits_processor.py │ ├── model_processor_factory.py │ └── ppl_based_on_probaility_transfer_logits_processor.py ├── main_many_ensemble_llama_series_local_matrix.py ├── main_many_ensemble_llama_series_local_matrix_mmlu.py ├── main_model_thread.py ├── model_load.py └── transfer_matrix │ ├── cal_and_save_transfer_matrix.py │ ├── common_vocabulary.py │ └── transfer_matrix.py └── utils ├── answer_extract.py ├── calculate └── block_cosine_similarity.py └── evaluate ├── EM_dir_test.py ├── GSM_dir_test.py └── utils ├── NQ_evaluate_predictions.py └── eval_utils.py /README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/OrangeInSouth/DeePEn/HEAD/README.md -------------------------------------------------------------------------------- /confs/ARC-c/InternLM+Mistral+Yi+Skywork.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/OrangeInSouth/DeePEn/HEAD/confs/ARC-c/InternLM+Mistral+Yi+Skywork.json -------------------------------------------------------------------------------- /confs/ARC-c/InternLM+Mistral.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/OrangeInSouth/DeePEn/HEAD/confs/ARC-c/InternLM+Mistral.json -------------------------------------------------------------------------------- /confs/ARC-c/baseline/InternLM.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/OrangeInSouth/DeePEn/HEAD/confs/ARC-c/baseline/InternLM.json -------------------------------------------------------------------------------- /confs/ARC-c/baseline/LLaMA.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/OrangeInSouth/DeePEn/HEAD/confs/ARC-c/baseline/LLaMA.json -------------------------------------------------------------------------------- /confs/ARC-c/baseline/Mistral.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/OrangeInSouth/DeePEn/HEAD/confs/ARC-c/baseline/Mistral.json -------------------------------------------------------------------------------- /confs/ARC-c/baseline/Skywork.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/OrangeInSouth/DeePEn/HEAD/confs/ARC-c/baseline/Skywork.json -------------------------------------------------------------------------------- /confs/ARC-c/baseline/Tigerbot.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/OrangeInSouth/DeePEn/HEAD/confs/ARC-c/baseline/Tigerbot.json -------------------------------------------------------------------------------- /confs/ARC-c/baseline/Yi.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/OrangeInSouth/DeePEn/HEAD/confs/ARC-c/baseline/Yi.json -------------------------------------------------------------------------------- /confs/GSM8K/2models/InternLM+Skywork.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/OrangeInSouth/DeePEn/HEAD/confs/GSM8K/2models/InternLM+Skywork.json -------------------------------------------------------------------------------- /confs/GSM8K/2models/InternLM+Skywork1.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/OrangeInSouth/DeePEn/HEAD/confs/GSM8K/2models/InternLM+Skywork1.json -------------------------------------------------------------------------------- /confs/GSM8K/2models/InternLM+Skywork2.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/OrangeInSouth/DeePEn/HEAD/confs/GSM8K/2models/InternLM+Skywork2.json -------------------------------------------------------------------------------- /confs/GSM8K/2models/InternLM+Skywork3.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/OrangeInSouth/DeePEn/HEAD/confs/GSM8K/2models/InternLM+Skywork3.json -------------------------------------------------------------------------------- /confs/GSM8K/2models/InternLM+Skywork4.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/OrangeInSouth/DeePEn/HEAD/confs/GSM8K/2models/InternLM+Skywork4.json -------------------------------------------------------------------------------- /confs/GSM8K/4models/Sky4_1.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/OrangeInSouth/DeePEn/HEAD/confs/GSM8K/4models/Sky4_1.json -------------------------------------------------------------------------------- /confs/GSM8K/4models/Sky4_2.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/OrangeInSouth/DeePEn/HEAD/confs/GSM8K/4models/Sky4_2.json -------------------------------------------------------------------------------- /confs/GSM8K/4models/Sky4_3.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/OrangeInSouth/DeePEn/HEAD/confs/GSM8K/4models/Sky4_3.json -------------------------------------------------------------------------------- /confs/GSM8K/4models/Sky4_4.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/OrangeInSouth/DeePEn/HEAD/confs/GSM8K/4models/Sky4_4.json -------------------------------------------------------------------------------- /confs/GSM8K/baseline/InternLM.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/OrangeInSouth/DeePEn/HEAD/confs/GSM8K/baseline/InternLM.json -------------------------------------------------------------------------------- /confs/GSM8K/baseline/LLaMA.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/OrangeInSouth/DeePEn/HEAD/confs/GSM8K/baseline/LLaMA.json -------------------------------------------------------------------------------- /confs/GSM8K/baseline/Mistral.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/OrangeInSouth/DeePEn/HEAD/confs/GSM8K/baseline/Mistral.json -------------------------------------------------------------------------------- /confs/GSM8K/baseline/Skywork.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/OrangeInSouth/DeePEn/HEAD/confs/GSM8K/baseline/Skywork.json -------------------------------------------------------------------------------- /confs/GSM8K/baseline/Tigerbot.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/OrangeInSouth/DeePEn/HEAD/confs/GSM8K/baseline/Tigerbot.json -------------------------------------------------------------------------------- /confs/GSM8K/baseline/Yi.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/OrangeInSouth/DeePEn/HEAD/confs/GSM8K/baseline/Yi.json -------------------------------------------------------------------------------- /confs/MMLU/Yi+Mistral+Skywork+InernLM.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/OrangeInSouth/DeePEn/HEAD/confs/MMLU/Yi+Mistral+Skywork+InernLM.json -------------------------------------------------------------------------------- /confs/MMLU/Yi+Mistral.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/OrangeInSouth/DeePEn/HEAD/confs/MMLU/Yi+Mistral.json -------------------------------------------------------------------------------- /confs/MMLU/baseline/InternLM.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/OrangeInSouth/DeePEn/HEAD/confs/MMLU/baseline/InternLM.json -------------------------------------------------------------------------------- /confs/MMLU/baseline/LLaMA.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/OrangeInSouth/DeePEn/HEAD/confs/MMLU/baseline/LLaMA.json -------------------------------------------------------------------------------- /confs/MMLU/baseline/Mistral.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/OrangeInSouth/DeePEn/HEAD/confs/MMLU/baseline/Mistral.json -------------------------------------------------------------------------------- /confs/MMLU/baseline/Nanbeige.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/OrangeInSouth/DeePEn/HEAD/confs/MMLU/baseline/Nanbeige.json -------------------------------------------------------------------------------- /confs/MMLU/baseline/Skywork.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/OrangeInSouth/DeePEn/HEAD/confs/MMLU/baseline/Skywork.json -------------------------------------------------------------------------------- /confs/MMLU/baseline/Tigerbot.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/OrangeInSouth/DeePEn/HEAD/confs/MMLU/baseline/Tigerbot.json -------------------------------------------------------------------------------- /confs/MMLU/baseline/Yi.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/OrangeInSouth/DeePEn/HEAD/confs/MMLU/baseline/Yi.json -------------------------------------------------------------------------------- /confs/NQ/LLaMA+Mistral+InternLM+Tigerbot.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/OrangeInSouth/DeePEn/HEAD/confs/NQ/LLaMA+Mistral+InternLM+Tigerbot.json -------------------------------------------------------------------------------- /confs/NQ/LLaMA+Mistral.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/OrangeInSouth/DeePEn/HEAD/confs/NQ/LLaMA+Mistral.json -------------------------------------------------------------------------------- /confs/NQ/baseline/InternLM.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/OrangeInSouth/DeePEn/HEAD/confs/NQ/baseline/InternLM.json -------------------------------------------------------------------------------- /confs/NQ/baseline/LLaMA.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/OrangeInSouth/DeePEn/HEAD/confs/NQ/baseline/LLaMA.json -------------------------------------------------------------------------------- /confs/NQ/baseline/LLaMA70.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/OrangeInSouth/DeePEn/HEAD/confs/NQ/baseline/LLaMA70.json -------------------------------------------------------------------------------- /confs/NQ/baseline/Mistral.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/OrangeInSouth/DeePEn/HEAD/confs/NQ/baseline/Mistral.json -------------------------------------------------------------------------------- /confs/NQ/baseline/Mixtral.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/OrangeInSouth/DeePEn/HEAD/confs/NQ/baseline/Mixtral.json -------------------------------------------------------------------------------- /confs/NQ/baseline/Nanbeige.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/OrangeInSouth/DeePEn/HEAD/confs/NQ/baseline/Nanbeige.json -------------------------------------------------------------------------------- /confs/NQ/baseline/Skywork.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/OrangeInSouth/DeePEn/HEAD/confs/NQ/baseline/Skywork.json -------------------------------------------------------------------------------- /confs/NQ/baseline/Tigerbot.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/OrangeInSouth/DeePEn/HEAD/confs/NQ/baseline/Tigerbot.json -------------------------------------------------------------------------------- /confs/NQ/baseline/Yi.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/OrangeInSouth/DeePEn/HEAD/confs/NQ/baseline/Yi.json -------------------------------------------------------------------------------- /confs/PIQA/Yi+Skywork+Tigerbot+Mistral.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/OrangeInSouth/DeePEn/HEAD/confs/PIQA/Yi+Skywork+Tigerbot+Mistral.json -------------------------------------------------------------------------------- /confs/PIQA/Yi+Skywork.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/OrangeInSouth/DeePEn/HEAD/confs/PIQA/Yi+Skywork.json -------------------------------------------------------------------------------- /confs/PIQA/baseline/InternLM.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/OrangeInSouth/DeePEn/HEAD/confs/PIQA/baseline/InternLM.json -------------------------------------------------------------------------------- /confs/PIQA/baseline/LLaMA.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/OrangeInSouth/DeePEn/HEAD/confs/PIQA/baseline/LLaMA.json -------------------------------------------------------------------------------- /confs/PIQA/baseline/LLaMA70.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/OrangeInSouth/DeePEn/HEAD/confs/PIQA/baseline/LLaMA70.json -------------------------------------------------------------------------------- /confs/PIQA/baseline/Mistral.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/OrangeInSouth/DeePEn/HEAD/confs/PIQA/baseline/Mistral.json -------------------------------------------------------------------------------- /confs/PIQA/baseline/Mixtral.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/OrangeInSouth/DeePEn/HEAD/confs/PIQA/baseline/Mixtral.json -------------------------------------------------------------------------------- /confs/PIQA/baseline/Nanbeige.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/OrangeInSouth/DeePEn/HEAD/confs/PIQA/baseline/Nanbeige.json -------------------------------------------------------------------------------- /confs/PIQA/baseline/Skywork.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/OrangeInSouth/DeePEn/HEAD/confs/PIQA/baseline/Skywork.json -------------------------------------------------------------------------------- /confs/PIQA/baseline/Tigerbot.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/OrangeInSouth/DeePEn/HEAD/confs/PIQA/baseline/Tigerbot.json -------------------------------------------------------------------------------- /confs/PIQA/baseline/Yi.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/OrangeInSouth/DeePEn/HEAD/confs/PIQA/baseline/Yi.json -------------------------------------------------------------------------------- /confs/TriviaQA/LLaMA+Mistral+InternLM+Tigerbot.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/OrangeInSouth/DeePEn/HEAD/confs/TriviaQA/LLaMA+Mistral+InternLM+Tigerbot.json -------------------------------------------------------------------------------- /confs/TriviaQA/LLaMA+Mistral.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/OrangeInSouth/DeePEn/HEAD/confs/TriviaQA/LLaMA+Mistral.json -------------------------------------------------------------------------------- /confs/TriviaQA/baseline/InternLM.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/OrangeInSouth/DeePEn/HEAD/confs/TriviaQA/baseline/InternLM.json -------------------------------------------------------------------------------- /confs/TriviaQA/baseline/LLaMA.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/OrangeInSouth/DeePEn/HEAD/confs/TriviaQA/baseline/LLaMA.json -------------------------------------------------------------------------------- /confs/TriviaQA/baseline/Mistral.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/OrangeInSouth/DeePEn/HEAD/confs/TriviaQA/baseline/Mistral.json -------------------------------------------------------------------------------- /confs/TriviaQA/baseline/Skywork.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/OrangeInSouth/DeePEn/HEAD/confs/TriviaQA/baseline/Skywork.json -------------------------------------------------------------------------------- /confs/TriviaQA/baseline/Tigerbot.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/OrangeInSouth/DeePEn/HEAD/confs/TriviaQA/baseline/Tigerbot.json -------------------------------------------------------------------------------- /confs/TriviaQA/baseline/Yi.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/OrangeInSouth/DeePEn/HEAD/confs/TriviaQA/baseline/Yi.json -------------------------------------------------------------------------------- /datasets/ARC-Challenge/test.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/OrangeInSouth/DeePEn/HEAD/datasets/ARC-Challenge/test.jsonl -------------------------------------------------------------------------------- /datasets/ARC-Challenge/train.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/OrangeInSouth/DeePEn/HEAD/datasets/ARC-Challenge/train.jsonl -------------------------------------------------------------------------------- /datasets/GSM/data/demon_4.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/OrangeInSouth/DeePEn/HEAD/datasets/GSM/data/demon_4.jsonl -------------------------------------------------------------------------------- /datasets/GSM/data/test.cleand.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/OrangeInSouth/DeePEn/HEAD/datasets/GSM/data/test.cleand.jsonl -------------------------------------------------------------------------------- /datasets/GSM/data/train_sample300_seed42.cleand.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/OrangeInSouth/DeePEn/HEAD/datasets/GSM/data/train_sample300_seed42.cleand.jsonl -------------------------------------------------------------------------------- /datasets/MMLU/dev-jsonl/abstract_algebra.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/OrangeInSouth/DeePEn/HEAD/datasets/MMLU/dev-jsonl/abstract_algebra.jsonl -------------------------------------------------------------------------------- /datasets/MMLU/dev-jsonl/anatomy.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/OrangeInSouth/DeePEn/HEAD/datasets/MMLU/dev-jsonl/anatomy.jsonl -------------------------------------------------------------------------------- /datasets/MMLU/dev-jsonl/astronomy.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/OrangeInSouth/DeePEn/HEAD/datasets/MMLU/dev-jsonl/astronomy.jsonl -------------------------------------------------------------------------------- /datasets/MMLU/dev-jsonl/business_ethics.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/OrangeInSouth/DeePEn/HEAD/datasets/MMLU/dev-jsonl/business_ethics.jsonl -------------------------------------------------------------------------------- /datasets/MMLU/dev-jsonl/clinical_knowledge.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/OrangeInSouth/DeePEn/HEAD/datasets/MMLU/dev-jsonl/clinical_knowledge.jsonl -------------------------------------------------------------------------------- /datasets/MMLU/dev-jsonl/college_biology.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/OrangeInSouth/DeePEn/HEAD/datasets/MMLU/dev-jsonl/college_biology.jsonl -------------------------------------------------------------------------------- /datasets/MMLU/dev-jsonl/college_chemistry.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/OrangeInSouth/DeePEn/HEAD/datasets/MMLU/dev-jsonl/college_chemistry.jsonl -------------------------------------------------------------------------------- /datasets/MMLU/dev-jsonl/college_computer_science.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/OrangeInSouth/DeePEn/HEAD/datasets/MMLU/dev-jsonl/college_computer_science.jsonl -------------------------------------------------------------------------------- /datasets/MMLU/dev-jsonl/college_mathematics.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/OrangeInSouth/DeePEn/HEAD/datasets/MMLU/dev-jsonl/college_mathematics.jsonl -------------------------------------------------------------------------------- /datasets/MMLU/dev-jsonl/college_medicine.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/OrangeInSouth/DeePEn/HEAD/datasets/MMLU/dev-jsonl/college_medicine.jsonl -------------------------------------------------------------------------------- /datasets/MMLU/dev-jsonl/college_physics.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/OrangeInSouth/DeePEn/HEAD/datasets/MMLU/dev-jsonl/college_physics.jsonl -------------------------------------------------------------------------------- /datasets/MMLU/dev-jsonl/computer_security.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/OrangeInSouth/DeePEn/HEAD/datasets/MMLU/dev-jsonl/computer_security.jsonl -------------------------------------------------------------------------------- /datasets/MMLU/dev-jsonl/conceptual_physics.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/OrangeInSouth/DeePEn/HEAD/datasets/MMLU/dev-jsonl/conceptual_physics.jsonl -------------------------------------------------------------------------------- /datasets/MMLU/dev-jsonl/econometrics.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/OrangeInSouth/DeePEn/HEAD/datasets/MMLU/dev-jsonl/econometrics.jsonl -------------------------------------------------------------------------------- /datasets/MMLU/dev-jsonl/electrical_engineering.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/OrangeInSouth/DeePEn/HEAD/datasets/MMLU/dev-jsonl/electrical_engineering.jsonl -------------------------------------------------------------------------------- /datasets/MMLU/dev-jsonl/elementary_mathematics.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/OrangeInSouth/DeePEn/HEAD/datasets/MMLU/dev-jsonl/elementary_mathematics.jsonl -------------------------------------------------------------------------------- /datasets/MMLU/dev-jsonl/formal_logic.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/OrangeInSouth/DeePEn/HEAD/datasets/MMLU/dev-jsonl/formal_logic.jsonl -------------------------------------------------------------------------------- /datasets/MMLU/dev-jsonl/global_facts.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/OrangeInSouth/DeePEn/HEAD/datasets/MMLU/dev-jsonl/global_facts.jsonl -------------------------------------------------------------------------------- /datasets/MMLU/dev-jsonl/high_school_biology.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/OrangeInSouth/DeePEn/HEAD/datasets/MMLU/dev-jsonl/high_school_biology.jsonl -------------------------------------------------------------------------------- /datasets/MMLU/dev-jsonl/high_school_chemistry.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/OrangeInSouth/DeePEn/HEAD/datasets/MMLU/dev-jsonl/high_school_chemistry.jsonl -------------------------------------------------------------------------------- /datasets/MMLU/dev-jsonl/high_school_computer_science.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/OrangeInSouth/DeePEn/HEAD/datasets/MMLU/dev-jsonl/high_school_computer_science.jsonl -------------------------------------------------------------------------------- /datasets/MMLU/dev-jsonl/high_school_european_history.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/OrangeInSouth/DeePEn/HEAD/datasets/MMLU/dev-jsonl/high_school_european_history.jsonl -------------------------------------------------------------------------------- /datasets/MMLU/dev-jsonl/high_school_geography.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/OrangeInSouth/DeePEn/HEAD/datasets/MMLU/dev-jsonl/high_school_geography.jsonl -------------------------------------------------------------------------------- /datasets/MMLU/dev-jsonl/high_school_government_and_politics.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/OrangeInSouth/DeePEn/HEAD/datasets/MMLU/dev-jsonl/high_school_government_and_politics.jsonl -------------------------------------------------------------------------------- /datasets/MMLU/dev-jsonl/high_school_macroeconomics.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/OrangeInSouth/DeePEn/HEAD/datasets/MMLU/dev-jsonl/high_school_macroeconomics.jsonl -------------------------------------------------------------------------------- /datasets/MMLU/dev-jsonl/high_school_mathematics.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/OrangeInSouth/DeePEn/HEAD/datasets/MMLU/dev-jsonl/high_school_mathematics.jsonl -------------------------------------------------------------------------------- /datasets/MMLU/dev-jsonl/high_school_microeconomics.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/OrangeInSouth/DeePEn/HEAD/datasets/MMLU/dev-jsonl/high_school_microeconomics.jsonl -------------------------------------------------------------------------------- /datasets/MMLU/dev-jsonl/high_school_physics.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/OrangeInSouth/DeePEn/HEAD/datasets/MMLU/dev-jsonl/high_school_physics.jsonl -------------------------------------------------------------------------------- /datasets/MMLU/dev-jsonl/high_school_psychology.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/OrangeInSouth/DeePEn/HEAD/datasets/MMLU/dev-jsonl/high_school_psychology.jsonl -------------------------------------------------------------------------------- /datasets/MMLU/dev-jsonl/high_school_statistics.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/OrangeInSouth/DeePEn/HEAD/datasets/MMLU/dev-jsonl/high_school_statistics.jsonl -------------------------------------------------------------------------------- /datasets/MMLU/dev-jsonl/high_school_us_history.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/OrangeInSouth/DeePEn/HEAD/datasets/MMLU/dev-jsonl/high_school_us_history.jsonl -------------------------------------------------------------------------------- /datasets/MMLU/dev-jsonl/high_school_world_history.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/OrangeInSouth/DeePEn/HEAD/datasets/MMLU/dev-jsonl/high_school_world_history.jsonl -------------------------------------------------------------------------------- /datasets/MMLU/dev-jsonl/human_aging.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/OrangeInSouth/DeePEn/HEAD/datasets/MMLU/dev-jsonl/human_aging.jsonl -------------------------------------------------------------------------------- /datasets/MMLU/dev-jsonl/human_sexuality.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/OrangeInSouth/DeePEn/HEAD/datasets/MMLU/dev-jsonl/human_sexuality.jsonl -------------------------------------------------------------------------------- /datasets/MMLU/dev-jsonl/international_law.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/OrangeInSouth/DeePEn/HEAD/datasets/MMLU/dev-jsonl/international_law.jsonl -------------------------------------------------------------------------------- /datasets/MMLU/dev-jsonl/jurisprudence.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/OrangeInSouth/DeePEn/HEAD/datasets/MMLU/dev-jsonl/jurisprudence.jsonl -------------------------------------------------------------------------------- /datasets/MMLU/dev-jsonl/logical_fallacies.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/OrangeInSouth/DeePEn/HEAD/datasets/MMLU/dev-jsonl/logical_fallacies.jsonl -------------------------------------------------------------------------------- /datasets/MMLU/dev-jsonl/machine_learning.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/OrangeInSouth/DeePEn/HEAD/datasets/MMLU/dev-jsonl/machine_learning.jsonl -------------------------------------------------------------------------------- /datasets/MMLU/dev-jsonl/management.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/OrangeInSouth/DeePEn/HEAD/datasets/MMLU/dev-jsonl/management.jsonl -------------------------------------------------------------------------------- /datasets/MMLU/dev-jsonl/marketing.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/OrangeInSouth/DeePEn/HEAD/datasets/MMLU/dev-jsonl/marketing.jsonl -------------------------------------------------------------------------------- /datasets/MMLU/dev-jsonl/medical_genetics.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/OrangeInSouth/DeePEn/HEAD/datasets/MMLU/dev-jsonl/medical_genetics.jsonl -------------------------------------------------------------------------------- /datasets/MMLU/dev-jsonl/miscellaneous.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/OrangeInSouth/DeePEn/HEAD/datasets/MMLU/dev-jsonl/miscellaneous.jsonl -------------------------------------------------------------------------------- /datasets/MMLU/dev-jsonl/moral_disputes.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/OrangeInSouth/DeePEn/HEAD/datasets/MMLU/dev-jsonl/moral_disputes.jsonl -------------------------------------------------------------------------------- /datasets/MMLU/dev-jsonl/moral_scenarios.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/OrangeInSouth/DeePEn/HEAD/datasets/MMLU/dev-jsonl/moral_scenarios.jsonl -------------------------------------------------------------------------------- /datasets/MMLU/dev-jsonl/nutrition.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/OrangeInSouth/DeePEn/HEAD/datasets/MMLU/dev-jsonl/nutrition.jsonl -------------------------------------------------------------------------------- /datasets/MMLU/dev-jsonl/philosophy.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/OrangeInSouth/DeePEn/HEAD/datasets/MMLU/dev-jsonl/philosophy.jsonl -------------------------------------------------------------------------------- /datasets/MMLU/dev-jsonl/prehistory.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/OrangeInSouth/DeePEn/HEAD/datasets/MMLU/dev-jsonl/prehistory.jsonl -------------------------------------------------------------------------------- /datasets/MMLU/dev-jsonl/professional_accounting.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/OrangeInSouth/DeePEn/HEAD/datasets/MMLU/dev-jsonl/professional_accounting.jsonl -------------------------------------------------------------------------------- /datasets/MMLU/dev-jsonl/professional_law.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/OrangeInSouth/DeePEn/HEAD/datasets/MMLU/dev-jsonl/professional_law.jsonl -------------------------------------------------------------------------------- /datasets/MMLU/dev-jsonl/professional_medicine.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/OrangeInSouth/DeePEn/HEAD/datasets/MMLU/dev-jsonl/professional_medicine.jsonl -------------------------------------------------------------------------------- /datasets/MMLU/dev-jsonl/professional_psychology.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/OrangeInSouth/DeePEn/HEAD/datasets/MMLU/dev-jsonl/professional_psychology.jsonl -------------------------------------------------------------------------------- /datasets/MMLU/dev-jsonl/public_relations.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/OrangeInSouth/DeePEn/HEAD/datasets/MMLU/dev-jsonl/public_relations.jsonl -------------------------------------------------------------------------------- /datasets/MMLU/dev-jsonl/security_studies.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/OrangeInSouth/DeePEn/HEAD/datasets/MMLU/dev-jsonl/security_studies.jsonl -------------------------------------------------------------------------------- /datasets/MMLU/dev-jsonl/sociology.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/OrangeInSouth/DeePEn/HEAD/datasets/MMLU/dev-jsonl/sociology.jsonl -------------------------------------------------------------------------------- /datasets/MMLU/dev-jsonl/us_foreign_policy.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/OrangeInSouth/DeePEn/HEAD/datasets/MMLU/dev-jsonl/us_foreign_policy.jsonl -------------------------------------------------------------------------------- /datasets/MMLU/dev-jsonl/virology.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/OrangeInSouth/DeePEn/HEAD/datasets/MMLU/dev-jsonl/virology.jsonl -------------------------------------------------------------------------------- /datasets/MMLU/dev-jsonl/world_religions.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/OrangeInSouth/DeePEn/HEAD/datasets/MMLU/dev-jsonl/world_religions.jsonl -------------------------------------------------------------------------------- /datasets/MMLU/test-jsonl/abstract_algebra.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/OrangeInSouth/DeePEn/HEAD/datasets/MMLU/test-jsonl/abstract_algebra.jsonl -------------------------------------------------------------------------------- /datasets/MMLU/test-jsonl/anatomy.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/OrangeInSouth/DeePEn/HEAD/datasets/MMLU/test-jsonl/anatomy.jsonl -------------------------------------------------------------------------------- /datasets/MMLU/test-jsonl/astronomy.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/OrangeInSouth/DeePEn/HEAD/datasets/MMLU/test-jsonl/astronomy.jsonl -------------------------------------------------------------------------------- /datasets/MMLU/test-jsonl/business_ethics.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/OrangeInSouth/DeePEn/HEAD/datasets/MMLU/test-jsonl/business_ethics.jsonl -------------------------------------------------------------------------------- /datasets/MMLU/test-jsonl/clinical_knowledge.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/OrangeInSouth/DeePEn/HEAD/datasets/MMLU/test-jsonl/clinical_knowledge.jsonl -------------------------------------------------------------------------------- /datasets/MMLU/test-jsonl/college_biology.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/OrangeInSouth/DeePEn/HEAD/datasets/MMLU/test-jsonl/college_biology.jsonl -------------------------------------------------------------------------------- /datasets/MMLU/test-jsonl/college_chemistry.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/OrangeInSouth/DeePEn/HEAD/datasets/MMLU/test-jsonl/college_chemistry.jsonl -------------------------------------------------------------------------------- /datasets/MMLU/test-jsonl/college_computer_science.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/OrangeInSouth/DeePEn/HEAD/datasets/MMLU/test-jsonl/college_computer_science.jsonl -------------------------------------------------------------------------------- /datasets/MMLU/test-jsonl/college_mathematics.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/OrangeInSouth/DeePEn/HEAD/datasets/MMLU/test-jsonl/college_mathematics.jsonl -------------------------------------------------------------------------------- /datasets/MMLU/test-jsonl/college_medicine.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/OrangeInSouth/DeePEn/HEAD/datasets/MMLU/test-jsonl/college_medicine.jsonl -------------------------------------------------------------------------------- /datasets/MMLU/test-jsonl/college_physics.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/OrangeInSouth/DeePEn/HEAD/datasets/MMLU/test-jsonl/college_physics.jsonl -------------------------------------------------------------------------------- /datasets/MMLU/test-jsonl/computer_security.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/OrangeInSouth/DeePEn/HEAD/datasets/MMLU/test-jsonl/computer_security.jsonl -------------------------------------------------------------------------------- /datasets/MMLU/test-jsonl/conceptual_physics.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/OrangeInSouth/DeePEn/HEAD/datasets/MMLU/test-jsonl/conceptual_physics.jsonl -------------------------------------------------------------------------------- /datasets/MMLU/test-jsonl/econometrics.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/OrangeInSouth/DeePEn/HEAD/datasets/MMLU/test-jsonl/econometrics.jsonl -------------------------------------------------------------------------------- /datasets/MMLU/test-jsonl/electrical_engineering.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/OrangeInSouth/DeePEn/HEAD/datasets/MMLU/test-jsonl/electrical_engineering.jsonl -------------------------------------------------------------------------------- /datasets/MMLU/test-jsonl/elementary_mathematics.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/OrangeInSouth/DeePEn/HEAD/datasets/MMLU/test-jsonl/elementary_mathematics.jsonl -------------------------------------------------------------------------------- /datasets/MMLU/test-jsonl/formal_logic.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/OrangeInSouth/DeePEn/HEAD/datasets/MMLU/test-jsonl/formal_logic.jsonl -------------------------------------------------------------------------------- /datasets/MMLU/test-jsonl/global_facts.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/OrangeInSouth/DeePEn/HEAD/datasets/MMLU/test-jsonl/global_facts.jsonl -------------------------------------------------------------------------------- /datasets/MMLU/test-jsonl/high_school_biology.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/OrangeInSouth/DeePEn/HEAD/datasets/MMLU/test-jsonl/high_school_biology.jsonl -------------------------------------------------------------------------------- /datasets/MMLU/test-jsonl/high_school_chemistry.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/OrangeInSouth/DeePEn/HEAD/datasets/MMLU/test-jsonl/high_school_chemistry.jsonl -------------------------------------------------------------------------------- /datasets/MMLU/test-jsonl/high_school_computer_science.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/OrangeInSouth/DeePEn/HEAD/datasets/MMLU/test-jsonl/high_school_computer_science.jsonl -------------------------------------------------------------------------------- /datasets/MMLU/test-jsonl/high_school_european_history.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/OrangeInSouth/DeePEn/HEAD/datasets/MMLU/test-jsonl/high_school_european_history.jsonl -------------------------------------------------------------------------------- /datasets/MMLU/test-jsonl/high_school_geography.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/OrangeInSouth/DeePEn/HEAD/datasets/MMLU/test-jsonl/high_school_geography.jsonl -------------------------------------------------------------------------------- /datasets/MMLU/test-jsonl/high_school_government_and_politics.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/OrangeInSouth/DeePEn/HEAD/datasets/MMLU/test-jsonl/high_school_government_and_politics.jsonl -------------------------------------------------------------------------------- /datasets/MMLU/test-jsonl/high_school_macroeconomics.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/OrangeInSouth/DeePEn/HEAD/datasets/MMLU/test-jsonl/high_school_macroeconomics.jsonl -------------------------------------------------------------------------------- /datasets/MMLU/test-jsonl/high_school_mathematics.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/OrangeInSouth/DeePEn/HEAD/datasets/MMLU/test-jsonl/high_school_mathematics.jsonl -------------------------------------------------------------------------------- /datasets/MMLU/test-jsonl/high_school_microeconomics.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/OrangeInSouth/DeePEn/HEAD/datasets/MMLU/test-jsonl/high_school_microeconomics.jsonl -------------------------------------------------------------------------------- /datasets/MMLU/test-jsonl/high_school_physics.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/OrangeInSouth/DeePEn/HEAD/datasets/MMLU/test-jsonl/high_school_physics.jsonl -------------------------------------------------------------------------------- /datasets/MMLU/test-jsonl/high_school_psychology.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/OrangeInSouth/DeePEn/HEAD/datasets/MMLU/test-jsonl/high_school_psychology.jsonl -------------------------------------------------------------------------------- /datasets/MMLU/test-jsonl/high_school_statistics.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/OrangeInSouth/DeePEn/HEAD/datasets/MMLU/test-jsonl/high_school_statistics.jsonl -------------------------------------------------------------------------------- /datasets/MMLU/test-jsonl/high_school_us_history.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/OrangeInSouth/DeePEn/HEAD/datasets/MMLU/test-jsonl/high_school_us_history.jsonl -------------------------------------------------------------------------------- /datasets/MMLU/test-jsonl/high_school_world_history.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/OrangeInSouth/DeePEn/HEAD/datasets/MMLU/test-jsonl/high_school_world_history.jsonl -------------------------------------------------------------------------------- /datasets/MMLU/test-jsonl/human_aging.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/OrangeInSouth/DeePEn/HEAD/datasets/MMLU/test-jsonl/human_aging.jsonl -------------------------------------------------------------------------------- /datasets/MMLU/test-jsonl/human_sexuality.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/OrangeInSouth/DeePEn/HEAD/datasets/MMLU/test-jsonl/human_sexuality.jsonl -------------------------------------------------------------------------------- /datasets/MMLU/test-jsonl/international_law.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/OrangeInSouth/DeePEn/HEAD/datasets/MMLU/test-jsonl/international_law.jsonl -------------------------------------------------------------------------------- /datasets/MMLU/test-jsonl/jurisprudence.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/OrangeInSouth/DeePEn/HEAD/datasets/MMLU/test-jsonl/jurisprudence.jsonl -------------------------------------------------------------------------------- /datasets/MMLU/test-jsonl/logical_fallacies.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/OrangeInSouth/DeePEn/HEAD/datasets/MMLU/test-jsonl/logical_fallacies.jsonl -------------------------------------------------------------------------------- /datasets/MMLU/test-jsonl/machine_learning.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/OrangeInSouth/DeePEn/HEAD/datasets/MMLU/test-jsonl/machine_learning.jsonl -------------------------------------------------------------------------------- /datasets/MMLU/test-jsonl/management.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/OrangeInSouth/DeePEn/HEAD/datasets/MMLU/test-jsonl/management.jsonl -------------------------------------------------------------------------------- /datasets/MMLU/test-jsonl/marketing.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/OrangeInSouth/DeePEn/HEAD/datasets/MMLU/test-jsonl/marketing.jsonl -------------------------------------------------------------------------------- /datasets/MMLU/test-jsonl/medical_genetics.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/OrangeInSouth/DeePEn/HEAD/datasets/MMLU/test-jsonl/medical_genetics.jsonl -------------------------------------------------------------------------------- /datasets/MMLU/test-jsonl/miscellaneous.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/OrangeInSouth/DeePEn/HEAD/datasets/MMLU/test-jsonl/miscellaneous.jsonl -------------------------------------------------------------------------------- /datasets/MMLU/test-jsonl/moral_disputes.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/OrangeInSouth/DeePEn/HEAD/datasets/MMLU/test-jsonl/moral_disputes.jsonl -------------------------------------------------------------------------------- /datasets/MMLU/test-jsonl/moral_scenarios.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/OrangeInSouth/DeePEn/HEAD/datasets/MMLU/test-jsonl/moral_scenarios.jsonl -------------------------------------------------------------------------------- /datasets/MMLU/test-jsonl/nutrition.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/OrangeInSouth/DeePEn/HEAD/datasets/MMLU/test-jsonl/nutrition.jsonl -------------------------------------------------------------------------------- /datasets/MMLU/test-jsonl/philosophy.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/OrangeInSouth/DeePEn/HEAD/datasets/MMLU/test-jsonl/philosophy.jsonl -------------------------------------------------------------------------------- /datasets/MMLU/test-jsonl/prehistory.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/OrangeInSouth/DeePEn/HEAD/datasets/MMLU/test-jsonl/prehistory.jsonl -------------------------------------------------------------------------------- /datasets/MMLU/test-jsonl/professional_accounting.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/OrangeInSouth/DeePEn/HEAD/datasets/MMLU/test-jsonl/professional_accounting.jsonl -------------------------------------------------------------------------------- /datasets/MMLU/test-jsonl/professional_law.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/OrangeInSouth/DeePEn/HEAD/datasets/MMLU/test-jsonl/professional_law.jsonl -------------------------------------------------------------------------------- /datasets/MMLU/test-jsonl/professional_medicine.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/OrangeInSouth/DeePEn/HEAD/datasets/MMLU/test-jsonl/professional_medicine.jsonl -------------------------------------------------------------------------------- /datasets/MMLU/test-jsonl/professional_psychology.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/OrangeInSouth/DeePEn/HEAD/datasets/MMLU/test-jsonl/professional_psychology.jsonl -------------------------------------------------------------------------------- /datasets/MMLU/test-jsonl/public_relations.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/OrangeInSouth/DeePEn/HEAD/datasets/MMLU/test-jsonl/public_relations.jsonl -------------------------------------------------------------------------------- /datasets/MMLU/test-jsonl/security_studies.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/OrangeInSouth/DeePEn/HEAD/datasets/MMLU/test-jsonl/security_studies.jsonl -------------------------------------------------------------------------------- /datasets/MMLU/test-jsonl/sociology.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/OrangeInSouth/DeePEn/HEAD/datasets/MMLU/test-jsonl/sociology.jsonl -------------------------------------------------------------------------------- /datasets/MMLU/test-jsonl/us_foreign_policy.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/OrangeInSouth/DeePEn/HEAD/datasets/MMLU/test-jsonl/us_foreign_policy.jsonl -------------------------------------------------------------------------------- /datasets/MMLU/test-jsonl/virology.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/OrangeInSouth/DeePEn/HEAD/datasets/MMLU/test-jsonl/virology.jsonl -------------------------------------------------------------------------------- /datasets/MMLU/test-jsonl/world_religions.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/OrangeInSouth/DeePEn/HEAD/datasets/MMLU/test-jsonl/world_religions.jsonl -------------------------------------------------------------------------------- /datasets/MMLU/val-jsonl/abstract_algebra.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/OrangeInSouth/DeePEn/HEAD/datasets/MMLU/val-jsonl/abstract_algebra.jsonl -------------------------------------------------------------------------------- /datasets/MMLU/val-jsonl/anatomy.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/OrangeInSouth/DeePEn/HEAD/datasets/MMLU/val-jsonl/anatomy.jsonl -------------------------------------------------------------------------------- /datasets/MMLU/val-jsonl/astronomy.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/OrangeInSouth/DeePEn/HEAD/datasets/MMLU/val-jsonl/astronomy.jsonl -------------------------------------------------------------------------------- /datasets/MMLU/val-jsonl/business_ethics.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/OrangeInSouth/DeePEn/HEAD/datasets/MMLU/val-jsonl/business_ethics.jsonl -------------------------------------------------------------------------------- /datasets/MMLU/val-jsonl/clinical_knowledge.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/OrangeInSouth/DeePEn/HEAD/datasets/MMLU/val-jsonl/clinical_knowledge.jsonl -------------------------------------------------------------------------------- /datasets/MMLU/val-jsonl/college_biology.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/OrangeInSouth/DeePEn/HEAD/datasets/MMLU/val-jsonl/college_biology.jsonl -------------------------------------------------------------------------------- /datasets/MMLU/val-jsonl/college_chemistry.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/OrangeInSouth/DeePEn/HEAD/datasets/MMLU/val-jsonl/college_chemistry.jsonl -------------------------------------------------------------------------------- /datasets/MMLU/val-jsonl/college_computer_science.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/OrangeInSouth/DeePEn/HEAD/datasets/MMLU/val-jsonl/college_computer_science.jsonl -------------------------------------------------------------------------------- /datasets/MMLU/val-jsonl/college_mathematics.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/OrangeInSouth/DeePEn/HEAD/datasets/MMLU/val-jsonl/college_mathematics.jsonl -------------------------------------------------------------------------------- /datasets/MMLU/val-jsonl/college_medicine.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/OrangeInSouth/DeePEn/HEAD/datasets/MMLU/val-jsonl/college_medicine.jsonl -------------------------------------------------------------------------------- /datasets/MMLU/val-jsonl/college_physics.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/OrangeInSouth/DeePEn/HEAD/datasets/MMLU/val-jsonl/college_physics.jsonl -------------------------------------------------------------------------------- /datasets/MMLU/val-jsonl/computer_security.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/OrangeInSouth/DeePEn/HEAD/datasets/MMLU/val-jsonl/computer_security.jsonl -------------------------------------------------------------------------------- /datasets/MMLU/val-jsonl/conceptual_physics.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/OrangeInSouth/DeePEn/HEAD/datasets/MMLU/val-jsonl/conceptual_physics.jsonl -------------------------------------------------------------------------------- /datasets/MMLU/val-jsonl/econometrics.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/OrangeInSouth/DeePEn/HEAD/datasets/MMLU/val-jsonl/econometrics.jsonl -------------------------------------------------------------------------------- /datasets/MMLU/val-jsonl/electrical_engineering.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/OrangeInSouth/DeePEn/HEAD/datasets/MMLU/val-jsonl/electrical_engineering.jsonl -------------------------------------------------------------------------------- /datasets/MMLU/val-jsonl/elementary_mathematics.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/OrangeInSouth/DeePEn/HEAD/datasets/MMLU/val-jsonl/elementary_mathematics.jsonl -------------------------------------------------------------------------------- /datasets/MMLU/val-jsonl/formal_logic.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/OrangeInSouth/DeePEn/HEAD/datasets/MMLU/val-jsonl/formal_logic.jsonl -------------------------------------------------------------------------------- /datasets/MMLU/val-jsonl/global_facts.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/OrangeInSouth/DeePEn/HEAD/datasets/MMLU/val-jsonl/global_facts.jsonl -------------------------------------------------------------------------------- /datasets/MMLU/val-jsonl/high_school_biology.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/OrangeInSouth/DeePEn/HEAD/datasets/MMLU/val-jsonl/high_school_biology.jsonl -------------------------------------------------------------------------------- /datasets/MMLU/val-jsonl/high_school_chemistry.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/OrangeInSouth/DeePEn/HEAD/datasets/MMLU/val-jsonl/high_school_chemistry.jsonl -------------------------------------------------------------------------------- /datasets/MMLU/val-jsonl/high_school_computer_science.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/OrangeInSouth/DeePEn/HEAD/datasets/MMLU/val-jsonl/high_school_computer_science.jsonl -------------------------------------------------------------------------------- /datasets/MMLU/val-jsonl/high_school_european_history.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/OrangeInSouth/DeePEn/HEAD/datasets/MMLU/val-jsonl/high_school_european_history.jsonl -------------------------------------------------------------------------------- /datasets/MMLU/val-jsonl/high_school_geography.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/OrangeInSouth/DeePEn/HEAD/datasets/MMLU/val-jsonl/high_school_geography.jsonl -------------------------------------------------------------------------------- /datasets/MMLU/val-jsonl/high_school_government_and_politics.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/OrangeInSouth/DeePEn/HEAD/datasets/MMLU/val-jsonl/high_school_government_and_politics.jsonl -------------------------------------------------------------------------------- /datasets/MMLU/val-jsonl/high_school_macroeconomics.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/OrangeInSouth/DeePEn/HEAD/datasets/MMLU/val-jsonl/high_school_macroeconomics.jsonl -------------------------------------------------------------------------------- /datasets/MMLU/val-jsonl/high_school_mathematics.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/OrangeInSouth/DeePEn/HEAD/datasets/MMLU/val-jsonl/high_school_mathematics.jsonl -------------------------------------------------------------------------------- /datasets/MMLU/val-jsonl/high_school_microeconomics.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/OrangeInSouth/DeePEn/HEAD/datasets/MMLU/val-jsonl/high_school_microeconomics.jsonl -------------------------------------------------------------------------------- /datasets/MMLU/val-jsonl/high_school_physics.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/OrangeInSouth/DeePEn/HEAD/datasets/MMLU/val-jsonl/high_school_physics.jsonl -------------------------------------------------------------------------------- /datasets/MMLU/val-jsonl/high_school_psychology.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/OrangeInSouth/DeePEn/HEAD/datasets/MMLU/val-jsonl/high_school_psychology.jsonl -------------------------------------------------------------------------------- /datasets/MMLU/val-jsonl/high_school_statistics.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/OrangeInSouth/DeePEn/HEAD/datasets/MMLU/val-jsonl/high_school_statistics.jsonl -------------------------------------------------------------------------------- /datasets/MMLU/val-jsonl/high_school_us_history.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/OrangeInSouth/DeePEn/HEAD/datasets/MMLU/val-jsonl/high_school_us_history.jsonl -------------------------------------------------------------------------------- /datasets/MMLU/val-jsonl/high_school_world_history.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/OrangeInSouth/DeePEn/HEAD/datasets/MMLU/val-jsonl/high_school_world_history.jsonl -------------------------------------------------------------------------------- /datasets/MMLU/val-jsonl/human_aging.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/OrangeInSouth/DeePEn/HEAD/datasets/MMLU/val-jsonl/human_aging.jsonl -------------------------------------------------------------------------------- /datasets/MMLU/val-jsonl/human_sexuality.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/OrangeInSouth/DeePEn/HEAD/datasets/MMLU/val-jsonl/human_sexuality.jsonl -------------------------------------------------------------------------------- /datasets/MMLU/val-jsonl/international_law.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/OrangeInSouth/DeePEn/HEAD/datasets/MMLU/val-jsonl/international_law.jsonl -------------------------------------------------------------------------------- /datasets/MMLU/val-jsonl/jurisprudence.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/OrangeInSouth/DeePEn/HEAD/datasets/MMLU/val-jsonl/jurisprudence.jsonl -------------------------------------------------------------------------------- /datasets/MMLU/val-jsonl/logical_fallacies.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/OrangeInSouth/DeePEn/HEAD/datasets/MMLU/val-jsonl/logical_fallacies.jsonl -------------------------------------------------------------------------------- /datasets/MMLU/val-jsonl/machine_learning.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/OrangeInSouth/DeePEn/HEAD/datasets/MMLU/val-jsonl/machine_learning.jsonl -------------------------------------------------------------------------------- /datasets/MMLU/val-jsonl/management.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/OrangeInSouth/DeePEn/HEAD/datasets/MMLU/val-jsonl/management.jsonl -------------------------------------------------------------------------------- /datasets/MMLU/val-jsonl/marketing.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/OrangeInSouth/DeePEn/HEAD/datasets/MMLU/val-jsonl/marketing.jsonl -------------------------------------------------------------------------------- /datasets/MMLU/val-jsonl/medical_genetics.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/OrangeInSouth/DeePEn/HEAD/datasets/MMLU/val-jsonl/medical_genetics.jsonl -------------------------------------------------------------------------------- /datasets/MMLU/val-jsonl/miscellaneous.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/OrangeInSouth/DeePEn/HEAD/datasets/MMLU/val-jsonl/miscellaneous.jsonl -------------------------------------------------------------------------------- /datasets/MMLU/val-jsonl/moral_disputes.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/OrangeInSouth/DeePEn/HEAD/datasets/MMLU/val-jsonl/moral_disputes.jsonl -------------------------------------------------------------------------------- /datasets/MMLU/val-jsonl/moral_scenarios.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/OrangeInSouth/DeePEn/HEAD/datasets/MMLU/val-jsonl/moral_scenarios.jsonl -------------------------------------------------------------------------------- /datasets/MMLU/val-jsonl/nutrition.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/OrangeInSouth/DeePEn/HEAD/datasets/MMLU/val-jsonl/nutrition.jsonl -------------------------------------------------------------------------------- /datasets/MMLU/val-jsonl/philosophy.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/OrangeInSouth/DeePEn/HEAD/datasets/MMLU/val-jsonl/philosophy.jsonl -------------------------------------------------------------------------------- /datasets/MMLU/val-jsonl/prehistory.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/OrangeInSouth/DeePEn/HEAD/datasets/MMLU/val-jsonl/prehistory.jsonl -------------------------------------------------------------------------------- /datasets/MMLU/val-jsonl/professional_accounting.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/OrangeInSouth/DeePEn/HEAD/datasets/MMLU/val-jsonl/professional_accounting.jsonl -------------------------------------------------------------------------------- /datasets/MMLU/val-jsonl/professional_law.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/OrangeInSouth/DeePEn/HEAD/datasets/MMLU/val-jsonl/professional_law.jsonl -------------------------------------------------------------------------------- /datasets/MMLU/val-jsonl/professional_medicine.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/OrangeInSouth/DeePEn/HEAD/datasets/MMLU/val-jsonl/professional_medicine.jsonl -------------------------------------------------------------------------------- /datasets/MMLU/val-jsonl/professional_psychology.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/OrangeInSouth/DeePEn/HEAD/datasets/MMLU/val-jsonl/professional_psychology.jsonl -------------------------------------------------------------------------------- /datasets/MMLU/val-jsonl/public_relations.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/OrangeInSouth/DeePEn/HEAD/datasets/MMLU/val-jsonl/public_relations.jsonl -------------------------------------------------------------------------------- /datasets/MMLU/val-jsonl/security_studies.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/OrangeInSouth/DeePEn/HEAD/datasets/MMLU/val-jsonl/security_studies.jsonl -------------------------------------------------------------------------------- /datasets/MMLU/val-jsonl/sociology.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/OrangeInSouth/DeePEn/HEAD/datasets/MMLU/val-jsonl/sociology.jsonl -------------------------------------------------------------------------------- /datasets/MMLU/val-jsonl/us_foreign_policy.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/OrangeInSouth/DeePEn/HEAD/datasets/MMLU/val-jsonl/us_foreign_policy.jsonl -------------------------------------------------------------------------------- /datasets/MMLU/val-jsonl/virology.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/OrangeInSouth/DeePEn/HEAD/datasets/MMLU/val-jsonl/virology.jsonl -------------------------------------------------------------------------------- /datasets/MMLU/val-jsonl/world_religions.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/OrangeInSouth/DeePEn/HEAD/datasets/MMLU/val-jsonl/world_religions.jsonl -------------------------------------------------------------------------------- /datasets/NaturalQuestions/dev/v1.0-simplified_simplified-nq-train.simpled_dev_100000_sample1600_seed42.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/OrangeInSouth/DeePEn/HEAD/datasets/NaturalQuestions/dev/v1.0-simplified_simplified-nq-train.simpled_dev_100000_sample1600_seed42.jsonl -------------------------------------------------------------------------------- /datasets/NaturalQuestions/dev/v1.0-simplified_simplified-nq-train.simpled_few_shot_doman_6926_sample5_seed43.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/OrangeInSouth/DeePEn/HEAD/datasets/NaturalQuestions/dev/v1.0-simplified_simplified-nq-train.simpled_few_shot_doman_6926_sample5_seed43.jsonl -------------------------------------------------------------------------------- /datasets/NaturalQuestions/test/natural-questions.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/OrangeInSouth/DeePEn/HEAD/datasets/NaturalQuestions/test/natural-questions.jsonl -------------------------------------------------------------------------------- /datasets/PIQA/physicaliqa-train-dev/dev_our.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/OrangeInSouth/DeePEn/HEAD/datasets/PIQA/physicaliqa-train-dev/dev_our.jsonl -------------------------------------------------------------------------------- /datasets/PIQA/physicaliqa-train-dev/train_our.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/OrangeInSouth/DeePEn/HEAD/datasets/PIQA/physicaliqa-train-dev/train_our.jsonl -------------------------------------------------------------------------------- /datasets/TriviaQA/wikipedia-demon-all_sample5_seed42.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/OrangeInSouth/DeePEn/HEAD/datasets/TriviaQA/wikipedia-demon-all_sample5_seed42.jsonl -------------------------------------------------------------------------------- /datasets/TriviaQA/wikipedia-dev-1900.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/OrangeInSouth/DeePEn/HEAD/datasets/TriviaQA/wikipedia-dev-1900.jsonl -------------------------------------------------------------------------------- /datasets/TriviaQA/wikipedia-test-6000.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/OrangeInSouth/DeePEn/HEAD/datasets/TriviaQA/wikipedia-test-6000.jsonl -------------------------------------------------------------------------------- /figures/Ensemble_Dense_and_Sparse.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/OrangeInSouth/DeePEn/HEAD/figures/Ensemble_Dense_and_Sparse.png -------------------------------------------------------------------------------- /figures/Ensemble_LLM_and_Expert.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/OrangeInSouth/DeePEn/HEAD/figures/Ensemble_LLM_and_Expert.png -------------------------------------------------------------------------------- /figures/Main_Experiment.jpeg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/OrangeInSouth/DeePEn/HEAD/figures/Main_Experiment.jpeg -------------------------------------------------------------------------------- /figures/Method.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/OrangeInSouth/DeePEn/HEAD/figures/Method.jpg -------------------------------------------------------------------------------- /figures/Multi_model_ensemble.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/OrangeInSouth/DeePEn/HEAD/figures/Multi_model_ensemble.jpg -------------------------------------------------------------------------------- /figures/no: -------------------------------------------------------------------------------- 1 | 2 | -------------------------------------------------------------------------------- /figures/overview.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/OrangeInSouth/DeePEn/HEAD/figures/overview.png -------------------------------------------------------------------------------- /figures/performance.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/OrangeInSouth/DeePEn/HEAD/figures/performance.png -------------------------------------------------------------------------------- /src/assist_model_thread.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/OrangeInSouth/DeePEn/HEAD/src/assist_model_thread.py -------------------------------------------------------------------------------- /src/instruction_generate.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/OrangeInSouth/DeePEn/HEAD/src/instruction_generate.py -------------------------------------------------------------------------------- /src/logits_processor/assist_model_logits_processor.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/OrangeInSouth/DeePEn/HEAD/src/logits_processor/assist_model_logits_processor.py -------------------------------------------------------------------------------- /src/logits_processor/based_on_probaility_transfer_logits_processor.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/OrangeInSouth/DeePEn/HEAD/src/logits_processor/based_on_probaility_transfer_logits_processor.py -------------------------------------------------------------------------------- /src/logits_processor/model_processor_factory.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/OrangeInSouth/DeePEn/HEAD/src/logits_processor/model_processor_factory.py -------------------------------------------------------------------------------- /src/logits_processor/ppl_based_on_probaility_transfer_logits_processor.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/OrangeInSouth/DeePEn/HEAD/src/logits_processor/ppl_based_on_probaility_transfer_logits_processor.py -------------------------------------------------------------------------------- /src/main_many_ensemble_llama_series_local_matrix.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/OrangeInSouth/DeePEn/HEAD/src/main_many_ensemble_llama_series_local_matrix.py -------------------------------------------------------------------------------- /src/main_many_ensemble_llama_series_local_matrix_mmlu.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/OrangeInSouth/DeePEn/HEAD/src/main_many_ensemble_llama_series_local_matrix_mmlu.py -------------------------------------------------------------------------------- /src/main_model_thread.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/OrangeInSouth/DeePEn/HEAD/src/main_model_thread.py -------------------------------------------------------------------------------- /src/model_load.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/OrangeInSouth/DeePEn/HEAD/src/model_load.py -------------------------------------------------------------------------------- /src/transfer_matrix/cal_and_save_transfer_matrix.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/OrangeInSouth/DeePEn/HEAD/src/transfer_matrix/cal_and_save_transfer_matrix.py -------------------------------------------------------------------------------- /src/transfer_matrix/common_vocabulary.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/OrangeInSouth/DeePEn/HEAD/src/transfer_matrix/common_vocabulary.py -------------------------------------------------------------------------------- /src/transfer_matrix/transfer_matrix.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/OrangeInSouth/DeePEn/HEAD/src/transfer_matrix/transfer_matrix.py -------------------------------------------------------------------------------- /utils/answer_extract.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/OrangeInSouth/DeePEn/HEAD/utils/answer_extract.py -------------------------------------------------------------------------------- /utils/calculate/block_cosine_similarity.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/OrangeInSouth/DeePEn/HEAD/utils/calculate/block_cosine_similarity.py -------------------------------------------------------------------------------- /utils/evaluate/EM_dir_test.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/OrangeInSouth/DeePEn/HEAD/utils/evaluate/EM_dir_test.py -------------------------------------------------------------------------------- /utils/evaluate/GSM_dir_test.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/OrangeInSouth/DeePEn/HEAD/utils/evaluate/GSM_dir_test.py -------------------------------------------------------------------------------- /utils/evaluate/utils/NQ_evaluate_predictions.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/OrangeInSouth/DeePEn/HEAD/utils/evaluate/utils/NQ_evaluate_predictions.py -------------------------------------------------------------------------------- /utils/evaluate/utils/eval_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/OrangeInSouth/DeePEn/HEAD/utils/evaluate/utils/eval_utils.py --------------------------------------------------------------------------------