Update README.md
Browse files
README.md
CHANGED
@@ -60,11 +60,11 @@ To simplify the comparison, we chosed the Pass@1 metric for the Python language,
|
|
60 |
| Model | HumanEval python pass@1 |
|
61 |
| --- |----------------------------------------------------------------------------- |
|
62 |
| CodeLlama-7b-hf | 30.5%|
|
63 |
-
| opencsg-CodeLlama-7b-v0.1
|
64 |
| CodeLlama-13b-hf | 36.0%|
|
65 |
-
| opencsg-CodeLlama-13b-v0.1
|
66 |
| CodeLlama-34b-hf | 48.2%|
|
67 |
-
| opencsg-CodeLlama-34b-v0.1
|
68 |
|
69 |
**TODO**
|
70 |
- We will provide more benchmark scores on fine-tuned models in the future.
|
|
|
60 |
| Model | HumanEval python pass@1 |
|
61 |
| --- |----------------------------------------------------------------------------- |
|
62 |
| CodeLlama-7b-hf | 30.5%|
|
63 |
+
| opencsg-CodeLlama-7b-v0.1 | **43.9%** |
|
64 |
| CodeLlama-13b-hf | 36.0%|
|
65 |
+
| opencsg-CodeLlama-13b-v0.1| **51.2%** |
|
66 |
| CodeLlama-34b-hf | 48.2%|
|
67 |
+
| opencsg-CodeLlama-34b-v0.1| **56.1%** |
|
68 |
|
69 |
**TODO**
|
70 |
- We will provide more benchmark scores on fine-tuned models in the future.
|