Panchovix's picture
Adding Evaluation Results (#2)
d6ca5f9
metadata
license: other

WizardLM-33B-V1.0-Uncensored merged with kaiokendev's 33b SuperHOT 8k LoRA, without quant. (Full FP16 model)

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric Value
Avg. 25.58
ARC (25-shot) 25.43
HellaSwag (10-shot) 31.97
MMLU (5-shot) 23.43
TruthfulQA (0-shot) 47.0
Winogrande (5-shot) 51.07
GSM8K (5-shot) 0.0
DROP (3-shot) 0.19