Update README.md
Browse files
README.md
CHANGED
|
@@ -42,6 +42,7 @@ This is the repository for the base 13B version finetuned based on [CodeLlama-13
|
|
| 42 |
| 7B | [opencsg/Opencsg-CodeLlama-7b-v0.1](https://huggingface.co/opencsg/opencsg-CodeLlama-7b-v0.1) |
|
| 43 |
| 13B | [opencsg/Opencsg-CodeLlama-13b-v0.1](https://huggingface.co/opencsg/opencsg-CodeLlama-13b-v0.1) |
|
| 44 |
| 34B | [opencsg/Opencsg-CodeLlama-34b-v0.1](https://huggingface.co/opencsg/opencsg-CodeLlama-34b-v0.1) |
|
|
|
|
| 45 |
|
| 46 |
|
| 47 |
## Model Eval
|
|
@@ -65,6 +66,7 @@ To simplify the comparison, we chosed the Pass@1 metric for the Python language,
|
|
| 65 |
| opencsg-CodeLlama-13b-v0.1(4k) | **51.2%** |
|
| 66 |
| CodeLlama-34b-hf | 48.2%|
|
| 67 |
| opencsg-CodeLlama-34b-v0.1(4k)| **56.1%** |
|
|
|
|
| 68 |
|
| 69 |
**TODO**
|
| 70 |
- We will provide more benchmark scores on fine-tuned models in the future.
|
|
@@ -152,6 +154,8 @@ opencsg-CodeLlama-v0.1是一系列基于CodeLlama的通过全参数微调方法
|
|
| 152 |
| 7B | [opencsg/Opencsg-CodeLlama-7b-v0.1](https://huggingface.co/opencsg/opencsg-CodeLlama-7b-v0.1) |
|
| 153 |
| 13B | [opencsg/Opencsg-CodeLlama-13b-v0.1](https://huggingface.co/opencsg/opencsg-CodeLlama-13b-v0.1) |
|
| 154 |
| 34B | [opencsg/Opencsg-CodeLlama-34b-v0.1](https://huggingface.co/opencsg/opencsg-CodeLlama-34b-v0.1) |
|
|
|
|
|
|
|
| 155 |
|
| 156 |
|
| 157 |
## 模型评估
|
|
@@ -175,6 +179,8 @@ HumanEval 是评估模型在代码生成方面性能的最常见的基准，尤
|
|
| 175 |
| opencsg-CodeLlama-13b-v0.1 | **51.2%** |
|
| 176 |
| CodeLlama-34b-hf | 48.2%|
|
| 177 |
| opencsg-CodeLlama-34b-v0.1| **56.1%** |
|
|
|
|
|
|
|
| 178 |
|
| 179 |
**TODO**
|
| 180 |
- 未来我们将提供更多微调模型的在各基准上的分数。
|
|
|
|
| 42 |
| 7B | [opencsg/Opencsg-CodeLlama-7b-v0.1](https://huggingface.co/opencsg/opencsg-CodeLlama-7b-v0.1) |
|
| 43 |
| 13B | [opencsg/Opencsg-CodeLlama-13b-v0.1](https://huggingface.co/opencsg/opencsg-CodeLlama-13b-v0.1) |
|
| 44 |
| 34B | [opencsg/Opencsg-CodeLlama-34b-v0.1](https://huggingface.co/opencsg/opencsg-CodeLlama-34b-v0.1) |
|
| 45 |
+
| 34B | [opencsg/Opencsg-CodeLlama-34b-v0.2](https://huggingface.co/opencsg/opencsg-CodeLlama-34b-v0.2) |
|
| 46 |
|
| 47 |
|
| 48 |
## Model Eval
|
|
|
|
| 66 |
| opencsg-CodeLlama-13b-v0.1(4k) | **51.2%** |
|
| 67 |
| CodeLlama-34b-hf | 48.2%|
|
| 68 |
| opencsg-CodeLlama-34b-v0.1(4k)| **56.1%** |
|
| 69 |
+
| opencsg-CodeLlama-34b-v0.1(4k)| **64.0%** |
|
| 70 |
|
| 71 |
**TODO**
|
| 72 |
- We will provide more benchmark scores on fine-tuned models in the future.
|
|
|
|
| 154 |
| 7B | [opencsg/Opencsg-CodeLlama-7b-v0.1](https://huggingface.co/opencsg/opencsg-CodeLlama-7b-v0.1) |
|
| 155 |
| 13B | [opencsg/Opencsg-CodeLlama-13b-v0.1](https://huggingface.co/opencsg/opencsg-CodeLlama-13b-v0.1) |
|
| 156 |
| 34B | [opencsg/Opencsg-CodeLlama-34b-v0.1](https://huggingface.co/opencsg/opencsg-CodeLlama-34b-v0.1) |
|
| 157 |
+
| 34B | [opencsg/Opencsg-CodeLlama-34b-v0.2](https://huggingface.co/opencsg/opencsg-CodeLlama-34b-v0.2) |
|
| 158 |
+
|
| 159 |
|
| 160 |
|
| 161 |
## 模型评估
|
|
|
|
| 179 |
| opencsg-CodeLlama-13b-v0.1 | **51.2%** |
|
| 180 |
| CodeLlama-34b-hf | 48.2%|
|
| 181 |
| opencsg-CodeLlama-34b-v0.1| **56.1%** |
|
| 182 |
+
| opencsg-CodeLlama-34b-v0.1| **64.0%** |
|
| 183 |
+
|
| 184 |
|
| 185 |
**TODO**
|
| 186 |
- 未来我们将提供更多微调模型的在各基准上的分数。
|