Panchovix's picture
Adding Evaluation Results (#1)
156d5ab
metadata
license: other

Airoboros 33b GPT4 1.2 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. 25.35
ARC (25-shot) 24.66
HellaSwag (10-shot) 31.23
MMLU (5-shot) 23.13
TruthfulQA (0-shot) 47.44
Winogrande (5-shot) 50.43
GSM8K (5-shot) 0.0
DROP (3-shot) 0.59