From 7990ef209abd55eeb7bb353081a676d4caf4212d Mon Sep 17 00:00:00 2001 From: Yifan Mai Date: Thu, 7 Nov 2024 10:26:29 -0800 Subject: [PATCH] Release MMLU v1.10.0, Lite v1.10.0, AIR-Bench v1.2.0 --- helm-frontend/project_metadata.json | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/helm-frontend/project_metadata.json b/helm-frontend/project_metadata.json index 9ce3d5dab7..95b6b6fd28 100644 --- a/helm-frontend/project_metadata.json +++ b/helm-frontend/project_metadata.json @@ -3,7 +3,7 @@ "title": "Lite", "description": "Lightweight, broad evaluation of the capabilities of language models using in-context learning", "id": "lite", - "releases": ["v1.9.0", "v1.8.0", "v1.7.0", "v1.6.0", "v1.5.0", "v1.4.0", "v1.3.0", "v1.2.0", "v1.1.0", "v1.0.0"] + "releases": ["v1.10.0", "v1.9.0", "v1.8.0", "v1.7.0", "v1.6.0", "v1.5.0", "v1.4.0", "v1.3.0", "v1.2.0", "v1.1.0", "v1.0.0"] }, { "title": "Classic", @@ -27,7 +27,7 @@ "title": "MMLU", "description": "Massive Multitask Language Understanding (MMLU) evaluations using standardized prompts", "id": "mmlu", - "releases": ["v1.9.0", "v1.8.0", "v1.7.0", "v1.6.0", "v1.5.0", "v1.4.0", "v1.3.0", "v1.2.0", "v1.1.0", "v1.0.0"] + "releases": ["v1.10.0", "v1.9.0", "v1.8.0", "v1.7.0", "v1.6.0", "v1.5.0", "v1.4.0", "v1.3.0", "v1.2.0", "v1.1.0", "v1.0.0"] }, { "title": "VHELM", @@ -45,7 +45,7 @@ "title": "AIR-Bench", "description": "Safety benchmark based on emerging government regulations and company policies", "id": "air-bench", - "releases": ["v1.1.0", "v1.0.0"] + "releases": ["v1.2.0", "v1.1.0", "v1.0.0"] }, { "title": "CLEVA",