Commit
•
dc7dfbe
1
Parent(s):
6e71700
Create README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
datasets:
|
| 4 |
+
- abacusai/MetaMathFewshot
|
| 5 |
+
---
|
| 6 |
+
|
| 7 |
+
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
|
| 8 |
+
|
| 9 |
+
### Evaluation Results
|
| 10 |
+
|
| 11 |
+
| Average | ARC | HellaSwag | MMLU | TruthfulQA | Winogrande | GSM8K |
|
| 12 |
+
| --- | --- | --- | --- | --- | --- | --- |
|
| 13 |
+
| | | | | | | |
|
| 14 |
+
|
| 15 |
+
For comparison the GSM8K score for the original `nontoxic-bagel-34b-v0.2` model was 58.45 and average score was 74.69
|