Hugging Face's logo

opencsg
/
opencsg-CodeLlama-34b-v0.1

Text Generation
Transformers
Safetensors
code
llama
llama-2
text-generation-inference
Model card Files Community
TomPei commited on
Commit
524590e
·
verified ·
1 Parent(s): 8119074

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +12 -9
README.md CHANGED
@@ -62,13 +62,14 @@ To simplify the comparison, we chosed the Pass@1 metric for the Python language,
62
  | Model | HumanEval python pass@1 |
63
  | --- |----------------------------------------------------------------------------- |
64
  | CodeLlama-7b-hf | 30.5%|
65
- | opencsg-CodeLlama-7b-v0.1 | **43.9%** |
66
  | CodeLlama-13b-hf | 36.0%|
67
- | opencsg-CodeLlama-13b-v0.1 | **51.2%** |
68
  | CodeLlama-34b-hf | 48.2%|
69
- | opencsg-CodeLlama-34b-v0.1| **56.1%** |
70
- | opencsg-CodeLlama-34b-v0.2| **64.0%** |
71
-
 
72
 
73
  **TODO**
74
  - We will provide more benchmark scores on fine-tuned models in the future.
@@ -176,12 +177,14 @@ HumanEval 是评估模型在代码生成方面性能的最常见的基准，尤
176
  | 模型 | HumanEval python pass@1 |
177
  | --- |----------------------------------------------------------------------------- |
178
  | CodeLlama-7b-hf | 30.5%|
179
- | opencsg-CodeLlama-7b-v0.1 | **43.9%** |
180
  | CodeLlama-13b-hf | 36.0%|
181
- | opencsg-CodeLlama-13b-v0.1 | **51.2%** |
182
  | CodeLlama-34b-hf | 48.2%|
183
- | opencsg-CodeLlama-34b-v0.1| **56.1%** |
184
- | opencsg-CodeLlama-34b-v0.1| **64.0%** |
 
 
185
 
186
  **TODO**
187
  - 未来我们将提供更多微调模型的在各基准上的分数。
 
62
  | Model | HumanEval python pass@1 |
63
  | --- |----------------------------------------------------------------------------- |
64
  | CodeLlama-7b-hf | 30.5%|
65
+ | **opencsg-CodeLlama-7b-v0.1** | **43.9%** |
66
  | CodeLlama-13b-hf | 36.0%|
67
+ | **opencsg-CodeLlama-13b-v0.1** | **51.2%** |
68
  | CodeLlama-34b-hf | 48.2%|
69
+ | **opencsg-CodeLlama-34b-v0.1**| **56.1%** |
70
+ | **opencsg-CodeLlama-34b-v0.2**| **64.0%** |
71
+ | CodeLlama-70b-hf| 53.0% |
72
+ | CodeLlama-70b-Instruct-hf| **67.8%** |
73
 
74
  **TODO**
75
  - We will provide more benchmark scores on fine-tuned models in the future.
 
177
  | 模型 | HumanEval python pass@1 |
178
  | --- |----------------------------------------------------------------------------- |
179
  | CodeLlama-7b-hf | 30.5%|
180
+ | **opencsg-CodeLlama-7b-v0.1** | **43.9%** |
181
  | CodeLlama-13b-hf | 36.0%|
182
+ | **opencsg-CodeLlama-13b-v0.1** | **51.2%** |
183
  | CodeLlama-34b-hf | 48.2%|
184
+ | **opencsg-CodeLlama-34b-v0.1**| **56.1%** |
185
+ | **opencsg-CodeLlama-34b-v0.2**| **64.0%** |
186
+ | CodeLlama-70b-hf| 53.0% |
187
+ | CodeLlama-70b-Instruct-hf| **67.8%** |
188
 
189
  **TODO**
190
  - 未来我们将提供更多微调模型的在各基准上的分数。