Finetune of the DPO Bagel model (https://huggingface.co/jondurbin/nontoxic-bagel-34b-v0.2) on the MetamathFewshot (https://huggingface.co/datasets/abacusai/MetaMathFewshot) dataset
Evaluation Results
| Average | ARC | HellaSwag | MMLU | TruthfulQA | Winogrande | GSM8K |
|---|---|---|---|---|---|---|
For comparison the GSM8K score for the original nontoxic-bagel-34b-v0.2 model was 58.45 and average score was 74.69