added deepseekv2

74df9bea · zhaoying1 · 74df9bea · 74df9bea · 74df9bea · 74df9bea
Commit 74df9bea authored Sep 02, 2024 by zhaoying1
20 changed files
--- a/LM-Evaluation-Harness-240310/lm_eval/tasks/ammlu/ammlu_medical_genetics.yaml
+++ b/LM-Evaluation-Harness-240310/lm_eval/tasks/ammlu/ammlu_medical_genetics.yaml
--- a/LM-Evaluation-Harness-240310/lm_eval/tasks/ammlu/ammlu_miscellaneous.yaml
+++ b/LM-Evaluation-Harness-240310/lm_eval/tasks/ammlu/ammlu_miscellaneous.yaml
--- a/LM-Evaluation-Harness-240310/lm_eval/tasks/ammlu/ammlu_moral_disputes.yaml
+++ b/LM-Evaluation-Harness-240310/lm_eval/tasks/ammlu/ammlu_moral_disputes.yaml
--- a/LM-Evaluation-Harness-240310/lm_eval/tasks/ammlu/ammlu_moral_scenarios.yaml
+++ b/LM-Evaluation-Harness-240310/lm_eval/tasks/ammlu/ammlu_moral_scenarios.yaml
--- a/LM-Evaluation-Harness-240310/lm_eval/tasks/ammlu/ammlu_nutrition.yaml
+++ b/LM-Evaluation-Harness-240310/lm_eval/tasks/ammlu/ammlu_nutrition.yaml
--- a/LM-Evaluation-Harness-240310/lm_eval/tasks/ammlu/ammlu_philosophy.yaml
+++ b/LM-Evaluation-Harness-240310/lm_eval/tasks/ammlu/ammlu_philosophy.yaml
--- a/LM-Evaluation-Harness-240310/lm_eval/tasks/ammlu/ammlu_prehistory.yaml
+++ b/LM-Evaluation-Harness-240310/lm_eval/tasks/ammlu/ammlu_prehistory.yaml
--- a/LM-Evaluation-Harness-240310/lm_eval/tasks/ammlu/ammlu_professional_accounting.yaml
+++ b/LM-Evaluation-Harness-240310/lm_eval/tasks/ammlu/ammlu_professional_accounting.yaml
--- a/LM-Evaluation-Harness-240310/lm_eval/tasks/ammlu/ammlu_professional_law.yaml
+++ b/LM-Evaluation-Harness-240310/lm_eval/tasks/ammlu/ammlu_professional_law.yaml
--- a/LM-Evaluation-Harness-240310/lm_eval/tasks/ammlu/ammlu_professional_medicine.yaml
+++ b/LM-Evaluation-Harness-240310/lm_eval/tasks/ammlu/ammlu_professional_medicine.yaml
--- a/LM-Evaluation-Harness-240310/lm_eval/tasks/ammlu/ammlu_professional_psychology.yaml
+++ b/LM-Evaluation-Harness-240310/lm_eval/tasks/ammlu/ammlu_professional_psychology.yaml
--- a/LM-Evaluation-Harness-240310/lm_eval/tasks/ammlu/ammlu_public_relations.yaml
+++ b/LM-Evaluation-Harness-240310/lm_eval/tasks/ammlu/ammlu_public_relations.yaml
--- a/LM-Evaluation-Harness-240310/lm_eval/tasks/ammlu/ammlu_security_studies.yaml
+++ b/LM-Evaluation-Harness-240310/lm_eval/tasks/ammlu/ammlu_security_studies.yaml
--- a/LM-Evaluation-Harness-240310/lm_eval/tasks/ammlu/ammlu_sociology.yaml
+++ b/LM-Evaluation-Harness-240310/lm_eval/tasks/ammlu/ammlu_sociology.yaml
--- a/LM-Evaluation-Harness-240310/lm_eval/tasks/ammlu/ammlu_us_foreign_policy.yaml
+++ b/LM-Evaluation-Harness-240310/lm_eval/tasks/ammlu/ammlu_us_foreign_policy.yaml
--- a/LM-Evaluation-Harness-240310/lm_eval/tasks/ammlu/ammlu_virology.yaml
+++ b/LM-Evaluation-Harness-240310/lm_eval/tasks/ammlu/ammlu_virology.yaml
--- a/LM-Evaluation-Harness-240310/lm_eval/tasks/ammlu/ammlu_world_religions.yaml
+++ b/LM-Evaluation-Harness-240310/lm_eval/tasks/ammlu/ammlu_world_religions.yaml
--- a/LM-Evaluation-Harness-240310/lm_eval/tasks/anli/README.md
+++ b/LM-Evaluation-Harness-240310/lm_eval/tasks/anli/README.md
--- a/LM-Evaluation-Harness-240310/lm_eval/tasks/anli/anli_r1.yaml
+++ b/LM-Evaluation-Harness-240310/lm_eval/tasks/anli/anli_r1.yaml
--- a/LM-Evaluation-Harness-240310/lm_eval/tasks/anli/anli_r2.yaml
+++ b/LM-Evaluation-Harness-240310/lm_eval/tasks/anli/anli_r2.yaml