Update README.md
Browse files
README.md
CHANGED
|
@@ -20,8 +20,8 @@ Currently, we only provide a subset of evaluations from the lm_eval repository.
|
|
| 20 |
|
| 21 |
| Tasks | Metric | gpt-oss-20b | **gpt-oss-46b** | Improvement |
|
| 22 |
| :--- | :--- | :---: | :---: | :---: |
|
| 23 |
-
| **GSM8K** (0-shot) | Exact Match (flexible) | **0.2290** | 0.1638 | <font color="
|
| 24 |
-
| **LAMBADA** (OpenAI) | Accuracy | 0.2038 | **0.2668**| <font color="
|
| 25 |
|
| 26 |
|
| 27 |
> [!NOTE]
|
|
|
|
| 20 |
|
| 21 |
| Tasks | Metric | gpt-oss-20b | **gpt-oss-46b** | Improvement |
|
| 22 |
| :--- | :--- | :---: | :---: | :---: |
|
| 23 |
+
| **GSM8K** (0-shot) | Exact Match (flexible) | **0.2290** | 0.1638 | <font color="red">-28.47%</font> |
|
| 24 |
+
| **LAMBADA** (OpenAI) | Accuracy | 0.2038 | **0.2668**| <font color="green">+30.91%</font> |
|
| 25 |
|
| 26 |
|
| 27 |
> [!NOTE]
|