Merge branch 'main' of https://github.com/EleutherAI/lm-evaluation-harness into mela

741a6a69 · lintangsutawika · 494a4515 · b536f067 · 741a6a69 · 741a6a69
Commit 741a6a69 authored Aug 20, 2024 by lintangsutawika
20 changed files
--- a/lm_eval/tasks/med_concepts_qa/med_concepts_qa_icd10cm_medium.yaml
+++ b/lm_eval/tasks/med_concepts_qa/med_concepts_qa_icd10cm_medium.yaml
--- a/lm_eval/tasks/med_concepts_qa/med_concepts_qa_icd10proc_easy.yaml
+++ b/lm_eval/tasks/med_concepts_qa/med_concepts_qa_icd10proc_easy.yaml
--- a/lm_eval/tasks/med_concepts_qa/med_concepts_qa_icd10proc_hard.yaml
+++ b/lm_eval/tasks/med_concepts_qa/med_concepts_qa_icd10proc_hard.yaml
--- a/lm_eval/tasks/med_concepts_qa/med_concepts_qa_icd10proc_medium.yaml
+++ b/lm_eval/tasks/med_concepts_qa/med_concepts_qa_icd10proc_medium.yaml
--- a/lm_eval/tasks/med_concepts_qa/med_concepts_qa_icd9cm_easy.yaml
+++ b/lm_eval/tasks/med_concepts_qa/med_concepts_qa_icd9cm_easy.yaml
--- a/lm_eval/tasks/med_concepts_qa/med_concepts_qa_icd9cm_hard.yaml
+++ b/lm_eval/tasks/med_concepts_qa/med_concepts_qa_icd9cm_hard.yaml
--- a/lm_eval/tasks/med_concepts_qa/med_concepts_qa_icd9cm_medium.yaml
+++ b/lm_eval/tasks/med_concepts_qa/med_concepts_qa_icd9cm_medium.yaml
--- a/lm_eval/tasks/med_concepts_qa/med_concepts_qa_icd9proc_easy.yaml
+++ b/lm_eval/tasks/med_concepts_qa/med_concepts_qa_icd9proc_easy.yaml
--- a/lm_eval/tasks/med_concepts_qa/med_concepts_qa_icd9proc_hard.yaml
+++ b/lm_eval/tasks/med_concepts_qa/med_concepts_qa_icd9proc_hard.yaml
--- a/lm_eval/tasks/med_concepts_qa/med_concepts_qa_icd9proc_medium.yaml
+++ b/lm_eval/tasks/med_concepts_qa/med_concepts_qa_icd9proc_medium.yaml
--- a/lm_eval/tasks/mmlu/_generate_configs.py
+++ b/lm_eval/tasks/mmlu/_generate_configs.py
--- a/lm_eval/tasks/mmlu/continuation/_continuation_template_yaml
+++ b/lm_eval/tasks/mmlu/continuation/_continuation_template_yaml
--- a/lm_eval/tasks/mmlu/continuation/_mmlu.yaml
+++ b/lm_eval/tasks/mmlu/continuation/_mmlu.yaml
--- a/lm_eval/tasks/mmlu/continuation/mmlu_abstract_algebra.yaml
+++ b/lm_eval/tasks/mmlu/continuation/mmlu_abstract_algebra.yaml
--- a/lm_eval/tasks/mmlu/continuation/mmlu_anatomy.yaml
+++ b/lm_eval/tasks/mmlu/continuation/mmlu_anatomy.yaml
--- a/lm_eval/tasks/mmlu/continuation/mmlu_astronomy.yaml
+++ b/lm_eval/tasks/mmlu/continuation/mmlu_astronomy.yaml
--- a/lm_eval/tasks/mmlu/continuation/mmlu_business_ethics.yaml
+++ b/lm_eval/tasks/mmlu/continuation/mmlu_business_ethics.yaml
--- a/lm_eval/tasks/mmlu/continuation/mmlu_clinical_knowledge.yaml
+++ b/lm_eval/tasks/mmlu/continuation/mmlu_clinical_knowledge.yaml
--- a/lm_eval/tasks/mmlu/continuation/mmlu_college_biology.yaml
+++ b/lm_eval/tasks/mmlu/continuation/mmlu_college_biology.yaml
--- a/lm_eval/tasks/mmlu/continuation/mmlu_college_chemistry.yaml
+++ b/lm_eval/tasks/mmlu/continuation/mmlu_college_chemistry.yaml