Add evaluation results to model card
#2
by pwxcdct - opened
Add benchmark scores from the Open LLM Leaderboard for Llama 2 7B
This PR adds benchmark scores from the Open LLM Leaderboard for the base Llama 2 7B model: ARC (25-shot), HellaSwag (10-shot), MMLU (5-shot), and GSM8K (5-shot).
pwxcdct changed pull request status to closed