Update README.md
Browse files
README.md
CHANGED
|
@@ -17,6 +17,7 @@ Similar to R1, it adapts a two-step problem-solving process (\<think\> and \<sol
|
|
| 17 |
The model’s performance is evaluated on subsets of the HRM8K benchmark ([Ko et al., 2025](https://www.arxiv.org/abs/2501.02448)).
|
| 18 |
The evaluation files are also available [here](https://huggingface.co/OLAIR/ko-r1-1.5b-preview/tree/main/eval).
|
| 19 |
|
|
|
|
| 20 |
|
| 21 |
|
| 22 |
## Inference Settings
|
|
|
|
| 17 |
The model’s performance is evaluated on subsets of the HRM8K benchmark ([Ko et al., 2025](https://www.arxiv.org/abs/2501.02448)).
|
| 18 |
The evaluation files are also available [here](https://huggingface.co/OLAIR/ko-r1-1.5b-preview/tree/main/eval).
|
| 19 |
|
| 20 |
+
|
| 21 |
|
| 22 |
|
| 23 |
## Inference Settings
|