Flash-Llama-13B / README.md
leaderboard-pr-bot's picture
Adding Evaluation Results
4002d72
|
raw
history blame
656 Bytes

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric Value
Avg. 46.87
ARC (25-shot) 59.3
HellaSwag (10-shot) 82.15
MMLU (5-shot) 55.67
TruthfulQA (0-shot) 37.39
Winogrande (5-shot) 76.64
GSM8K (5-shot) 10.84
DROP (3-shot) 6.08