Update README.md
Browse files
README.md
CHANGED
|
@@ -13,7 +13,7 @@ Omni-Judge can be applied to various mathematical reasoning benchmarks, such as
|
|
| 13 |
|
| 14 |
Omni-Judge builds on the `meta-llama/Llama-3.1-8B-Instruct`, incorporating GPT-4o evaluation data for instruction tuning. The training dataset comprises 17,618 examples, with a total of 2 epochs. Omni-Judge's performance is closely aligned with GPT-4o. We created an internal evaluation set using queries not previously seen by the model, consisting of 2,220 test samples. The agreement rate between Omni-Judge and GPT-4o evaluations is approximately 91%.
|
| 15 |
|
| 16 |
-
## Quickstart
|
| 17 |
|
| 18 |
|
| 19 |
```python
|
|
|
|
| 13 |
|
| 14 |
Omni-Judge builds on the `meta-llama/Llama-3.1-8B-Instruct`, incorporating GPT-4o evaluation data for instruction tuning. The training dataset comprises 17,618 examples, with a total of 2 epochs. Omni-Judge's performance is closely aligned with GPT-4o. We created an internal evaluation set using queries not previously seen by the model, consisting of 2,220 test samples. The agreement rate between Omni-Judge and GPT-4o evaluations is approximately 91%.
|
| 15 |
|
| 16 |
+
## Quickstart
|
| 17 |
|
| 18 |
|
| 19 |
```python
|