WisdomShell
/

CodeShell-7B

Text Generation

Model card Files Files and versions Community

pkudavid commited on Oct 9, 2023

Commit

81b7769

•

1 Parent(s): 53e57cd

Update README.md

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -87,7 +87,7 @@ Code Shell uses GPT-2 as its foundational architecture and incorporates technolo
 We selected the two most popular code evaluation datasets currently available (HumanEval and MBPP) to assess the model. Compared to the two most advanced 7b LLM for code, CodeLllama and Starcoder, Codeshell achieved the best results. The specific evaluation results are as follows.
 ### Pass@1
-|   任务   |  iter_0000230 | codellama | starcoder7b |
 | ------- | --------- | --------- | --------- |
 | humaneval	 | **34.32** | 29.44 | 27.80 |
 | mbpp		 | **38.65** | 37.60 | 34.16 |

 We selected the two most popular code evaluation datasets currently available (HumanEval and MBPP) to assess the model. Compared to the two most advanced 7b LLM for code, CodeLllama and Starcoder, Codeshell achieved the best results. The specific evaluation results are as follows.
 ### Pass@1
+|   任务   |  CodeShell | codellama | starcoder7b |
 | ------- | --------- | --------- | --------- |
 | humaneval	 | **34.32** | 29.44 | 27.80 |
 | mbpp		 | **38.65** | 37.60 | 34.16 |