Update README.md

README.md

@@ -52,6 +52,7 @@ It is impratical for us to manually set specific configuration for each fine-tun
 
 Thus, OpenCSG strained our brains to provide a relatively fair method to compare the fine-tuned models on HumanEval benchmark.
 To simplify the comparision, we chosed the Pass@1 metric on python language, but our finetuning dataset includes samples in multi language.
+For fair, we evaluated the fine-tuned and origin codellama models **only with** the original cases' prompts, not including any other instruction else.
 
 | Model     | HumanEval python pass@1                                                 |
 | ---  |----------------------------------------------------------------------------- |