Add GPQA (diamond) dataset to eval

This commit is contained in:
Debanjum
2024-11-27 16:30:20 -08:00
parent f1190ccf32
commit 22aef9bf53
2 changed files with 114 additions and 11 deletions

View File

@@ -25,6 +25,7 @@ on:
options:
- frames
- simpleqa
- gpqa
sample_size:
description: 'Number of samples to evaluate'
required: false
@@ -97,6 +98,7 @@ jobs:
GEMINI_API_KEY: ${{ secrets.GEMINI_API_KEY }}
SERPER_DEV_API_KEY: ${{ secrets.SERPER_DEV_API_KEY }}
OLOSTEP_API_KEY: ${{ secrets.OLOSTEP_API_KEY }}
HF_TOKEN: ${{ secrets.HF_TOKEN }}
KHOJ_ADMIN_EMAIL: khoj
KHOJ_ADMIN_PASSWORD: khoj
POSTGRES_HOST: localhost