|
--- |
|
license: apache-2.0 |
|
datasets: |
|
- abacusai/MetaMathFewshot |
|
--- |
|
|
|
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 |
