Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric Value
Avg. 44.13
ARC (25-shot) 53.67
HellaSwag (10-shot) 78.21
MMLU (5-shot) 45.9
TruthfulQA (0-shot) 46.13
Winogrande (5-shot) 73.8
GSM8K (5-shot) 4.7
DROP (3-shot) 6.53
Description
Model synced from source: dhmeltzer/Llama-2-7b-hf-eli5-cleaned-1024_qlora_merged
Readme 580 KiB