add dataset

README.md

@@ -4,8 +4,10 @@ license: apache-2.0
 
 # CodeT5-small-Go_generation
 This model is finetuned based on the pre-trained [CodeT5-small model](https://github.com/salesforce/CodeT5#fine-tuning). 
+This model is fine-tuned on dataset: [codet5_go-generation](https://huggingface.co/datasets/intm/codet5_go-generation).
 
 > 5.3 upload the initial version.
+> 5.6 upload the dataset
 
 The model genarates the missing function body according to the input which privides the necessary class environment and an empty function.
 

example_usage.py

@@ -9,6 +9,7 @@ model = T5ForConditionalGeneration.from_pretrained(model_path)
 
 # 使用模型进行推理
 input_text = "package names\n\nimport \"knative.dev/pkg/kmeta\"\n\n\nfunc Deployment(rev kmeta.Accessor) string {\n\treturn kmeta.ChildName(rev.GetName(), \"-deployment\")\n}\n\n\nfunc ImageCache(rev kmeta.Accessor) string {\n\treturn kmeta.ChildName(rev.GetName(), \"-cache\")\n}\n\n\n\n\nfunc PA(rev kmeta.Accessor) string"
+#input_text="\n\nfunc twoSum(nums []int, target int) []int "
 input_ids = tokenizer.encode(input_text, return_tensors="pt")
 output = model.generate(input_ids=input_ids, max_new_tokens=256)  #最大长度按照数据集的max_trg_len设置