Undi95's picture
Adding Evaluation Results (#2)
c8ae0c6
metadata
license: cc-by-nc-4.0

(0.70) NousResearch/Nous-Hermes-Llama2-13b & (0.30) jondurbin/airoboros-lmoe-13b-2.1/adapters/code

Nous-Hermes-Llama2-13b merged with a LoRA at 0.30 weight.

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric Value
Avg. 51.98
ARC (25-shot) 61.18
HellaSwag (10-shot) 83.21
MMLU (5-shot) 55.13
TruthfulQA (0-shot) 50.56
Winogrande (5-shot) 75.14
GSM8K (5-shot) 10.39
DROP (3-shot) 28.28