Update README.md
Browse files
README.md
CHANGED
|
@@ -43,7 +43,7 @@ To simplify the comparison, we chosed the Pass@1 metric for the Python language,
|
|
| 43 |
| Model | HumanEval python pass@1 |
|
| 44 |
| --- |----------------------------------------------------------------------------- |
|
| 45 |
| starcoder | 35.98%|
|
| 46 |
-
| opencsg-starcoder-v0.1| **
|
| 47 |
|
| 48 |
**TODO**
|
| 49 |
- We will provide more benchmark scores on fine-tuned models in the future.
|
|
@@ -149,7 +149,7 @@ HumanEval 是评估模型在代码生成方面性能的最常见的基准，尤
|
|
| 149 |
| 模型 | HumanEval python pass@1 |
|
| 150 |
| --- |----------------------------------------------------------------------------- |
|
| 151 |
| starcoder | 35.98%|
|
| 152 |
-
| opencsg-starcoder-v0.1| **
|
| 153 |
|
| 154 |
**TODO**
|
| 155 |
- 未来我们将提供更多微调模型的在各基准上的分数。
|
|
|
|
| 43 |
| Model | HumanEval python pass@1 |
|
| 44 |
| --- |----------------------------------------------------------------------------- |
|
| 45 |
| starcoder | 35.98%|
|
| 46 |
+
| opencsg-starcoder-v0.1| **42.68%** |
|
| 47 |
|
| 48 |
**TODO**
|
| 49 |
- We will provide more benchmark scores on fine-tuned models in the future.
|
|
|
|
| 149 |
| 模型 | HumanEval python pass@1 |
|
| 150 |
| --- |----------------------------------------------------------------------------- |
|
| 151 |
| starcoder | 35.98%|
|
| 152 |
+
| opencsg-starcoder-v0.1| **42.68%** |
|
| 153 |
|
| 154 |
**TODO**
|
| 155 |
- 未来我们将提供更多微调模型的在各基准上的分数。
|