Update README.md
Browse files
README.md
CHANGED
|
@@ -77,7 +77,7 @@ DeepCoder generalizes better to long contexts than the base distilled model, due
|
|
| 77 |
| **DeepCoder-14B-Preview** | 45.6 | 57.9 | 60.6 |
|
| 78 |
| **DeepSeek-R1-Distill-Qwen-14B** | 50.2 | 53.0 | 53.0 |
|
| 79 |
|
| 80 |
-
A more detailed description of the training recipe can be found in our [blog post](https://
|
| 81 |
|
| 82 |
## Evaluation
|
| 83 |
|
|
|
|
| 77 |
| **DeepCoder-14B-Preview** | 45.6 | 57.9 | 60.6 |
|
| 78 |
| **DeepSeek-R1-Distill-Qwen-14B** | 50.2 | 53.0 | 53.0 |
|
| 79 |
|
| 80 |
+
A more detailed description of the training recipe can be found in our [blog post](https://pretty-radio-b75.notion.site/DeepCoder-A-Fully-Open-Source-14B-Coder-at-O3-mini-Level-1cf81902c14680b3bee5eb349a512a51).
|
| 81 |
|
| 82 |
## Evaluation
|
| 83 |
|