Modelpublic

vicgalle/NeuralBeagle-11B-truthy

sourceHugging Faceapache-2.0updated 3y agoView on Hugging Face

1likes77downloads

Model Card

NeuralBeagle-11B

DPO'd from vicgalle/franken-Beagle-11B, a Beagle-like model upscaled to 11B. It is a frankenmerge model created using mergekit. Then, we applied DPO over a high-quality preference dataset.

image/png

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	72.06
AI2 Reasoning Challenge (25-Shot)	73.63
HellaSwag (10-Shot)	87.86
MMLU (5-Shot)	63.11
TruthfulQA (0-shot)	75.92
Winogrande (5-shot)	82.08
GSM8k (5-shot)	49.73