commit from ppy

README.md

@@ -1,3 +1,54 @@
 ---
 license: apache-2.0
 ---
+
+# codet5-small-go_generation_v2
+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: data_71421(44.2MB)
+
+max_src_len = 512, max_trg_len = 256
+
+> 5.5 upload the initial version.
+
+The model genarates the missing function body according to the input which privides the necessary class environment and an empty function.
+
+See example below for formatting.
+ 
+# How to use
+Here is how to use this model:
+
+```
+from transformers import T5ForConditionalGeneration, RobertaTokenizer
+
+# load model and tokenizer
+model_path = "PPY039/codet5-small-go_generation_v2"
+tokenizer = RobertaTokenizer.from_pretrained(model_path)
+model = T5ForConditionalGeneration.from_pretrained(model_path)
+
+# use model
+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_ids = tokenizer.encode(input_text, return_tensors="pt")
+
+output = model.generate(input_ids=input_ids, max_new_tokens=256)  # max_trg_len = 256
+
+# decode output
+output_text = tokenizer.decode(output[0], skip_special_tokens=True)
+print(output_text)
+
+
+# this prints "return kmeta.ChildName(rev.GetName(), "-pa")"
+```
+
+# Training data
+YinShicheng
+
+# Training process
+GuQiuhan
+
+# Advisor
+Prof.WangYu
+
+# Evaluation results
+TODO

added_tokens.json

@@ -0,0 +1 @@
+{}

config.json

@@ -0,0 +1,37 @@
+{
+  "_name_or_path": "/bigdata/qiuhan/codet5/CodeT5/saved_models/go_generation/codet5_small_all_lr10_bs32_src512_trg256_pat3_e30/checkpoint-best-ppl",
+  "architectures": [
+    "T5ForConditionalGeneration"
+  ],
+  "bos_token_id": 1,
+  "d_ff": 2048,
+  "d_kv": 64,
+  "d_model": 512,
+  "decoder_start_token_id": 0,
+  "dropout_rate": 0.1,
+  "eos_token_id": 2,
+  "feed_forward_proj": "relu",
+  "gradient_checkpointing": false,
+  "id2label": {
+    "0": "LABEL_0"
+  },
+  "initializer_factor": 1.0,
+  "is_encoder_decoder": true,
+  "label2id": {
+    "LABEL_0": 0
+  },
+  "layer_norm_epsilon": 1e-06,
+  "model_type": "t5",
+  "n_positions": 512,
+  "num_decoder_layers": 6,
+  "num_heads": 8,
+  "num_layers": 6,
+  "output_past": true,
+  "pad_token_id": 0,
+  "relative_attention_num_buckets": 32,
+  
+  "torch_dtype": "float32",
+  "transformers_version": "4.10.2",
+  "use_cache": true,
+  "vocab_size": 32100
+}

example_usage.py

@@ -0,0 +1,21 @@
+
+
+from transformers import T5ForConditionalGeneration, RobertaTokenizer
+
+# 加载模型和tokenizer
+model_path = "intm/codet5-small-go_generation"
+tokenizer = RobertaTokenizer.from_pretrained('intm/codet5-small-go_generation')
+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
+
+# 将生成的结果转换为字符串
+output_text = tokenizer.decode(output[0], skip_special_tokens=True)
+print(output_text)
+
+
+# 应当可以输出：return rev.GetName()

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:22f8e21dde297956192504b8b950fcd4f492b5154a2cee781d5ee911c1198589
+size 242029051

special_tokens_map.json

@@ -0,0 +1,147 @@
+{
+    "bos_token": {
+        "content": "<s>",
+        "single_word": false,
+        "lstrip": false,
+        "rstrip": false,
+        "normalized": true
+    },
+    "eos_token": {
+        "content": "</s>",
+        "single_word": false,
+        "lstrip": false,
+        "rstrip": false,
+        "normalized": true
+    },
+    "unk_token": {
+        "content": "<unk>",
+        "single_word": false,
+        "lstrip": false,
+        "rstrip": false,
+        "normalized": true
+    },
+    "sep_token": {
+        "content": "</s>",
+        "single_word": false,
+        "lstrip": false,
+        "rstrip": false,
+        "normalized": true
+    },
+    "pad_token": {
+        "content": "<pad>",
+        "single_word": false,
+        "lstrip": false,
+        "rstrip": false,
+        "normalized": true
+    },
+    "cls_token": {
+        "content": "<s>",
+        "single_word": false,
+        "lstrip": false,
+        "rstrip": false,
+        "normalized": true
+    },
+    "mask_token": { "content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true },
+    "additional_special_tokens": [
+        { "content":"<extra_id_99>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true },
+        { "content":"<extra_id_98>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true },
+        { "content":"<extra_id_97>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true },
+        { "content":"<extra_id_96>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true },
+        { "content":"<extra_id_95>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true },
+        { "content":"<extra_id_94>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true },
+        { "content":"<extra_id_93>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true },
+        { "content":"<extra_id_92>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true },
+        { "content":"<extra_id_91>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true },
+        { "content":"<extra_id_90>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true },
+        { "content":"<extra_id_89>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true },
+        { "content":"<extra_id_88>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true },
+        { "content":"<extra_id_87>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true },
+        { "content":"<extra_id_86>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true },
+        { "content":"<extra_id_85>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true },
+        { "content":"<extra_id_84>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true },
+        { "content":"<extra_id_83>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true },
+        { "content":"<extra_id_82>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true },
+        { "content":"<extra_id_81>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true },
+        { "content":"<extra_id_80>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true },
+        { "content":"<extra_id_79>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true },
+        { "content":"<extra_id_78>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true },
+        { "content":"<extra_id_77>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true },
+        { "content":"<extra_id_76>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true },
+        { "content":"<extra_id_75>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true },
+        { "content":"<extra_id_74>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true },
+        { "content":"<extra_id_73>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true },
+        { "content":"<extra_id_72>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true },
+        { "content":"<extra_id_71>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true },
+        { "content":"<extra_id_70>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true },
+        { "content":"<extra_id_69>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true },
+        { "content":"<extra_id_68>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true },
+        { "content":"<extra_id_67>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true },
+        { "content":"<extra_id_66>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true },
+        { "content":"<extra_id_65>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true },
+        { "content":"<extra_id_64>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true },
+        { "content":"<extra_id_63>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true },
+        { "content":"<extra_id_62>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true },
+        { "content":"<extra_id_61>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true },
+        { "content":"<extra_id_60>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true },
+        { "content":"<extra_id_59>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true },
+        { "content":"<extra_id_58>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true },
+        { "content":"<extra_id_57>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true },
+        { "content":"<extra_id_56>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true },
+        { "content":"<extra_id_55>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true },
+        { "content":"<extra_id_54>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true },
+        { "content":"<extra_id_53>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true },
+        { "content":"<extra_id_52>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true },
+        { "content":"<extra_id_51>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true },
+        { "content":"<extra_id_50>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true },
+        { "content":"<extra_id_49>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true },
+        { "content":"<extra_id_48>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true },
+        { "content":"<extra_id_47>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true },
+        { "content":"<extra_id_46>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true },
+        { "content":"<extra_id_45>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true },
+        { "content":"<extra_id_44>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true },
+        { "content":"<extra_id_43>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true },
+        { "content":"<extra_id_42>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true },
+        { "content":"<extra_id_41>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true },
+        { "content":"<extra_id_40>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true },
+        { "content":"<extra_id_39>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true },
+        { "content":"<extra_id_38>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true },
+        { "content":"<extra_id_37>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true },
+        { "content":"<extra_id_36>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true },
+        { "content":"<extra_id_35>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true },
+        { "content":"<extra_id_34>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true },
+        { "content":"<extra_id_33>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true },
+        { "content":"<extra_id_32>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true },
+        { "content":"<extra_id_31>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true },
+        { "content":"<extra_id_30>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true },
+        { "content":"<extra_id_29>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true },
+        { "content":"<extra_id_28>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true },
+        { "content":"<extra_id_27>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true },
+        { "content":"<extra_id_26>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true },
+        { "content":"<extra_id_25>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true },
+        { "content":"<extra_id_24>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true },
+        { "content":"<extra_id_23>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true },
+        { "content":"<extra_id_22>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true },
+        { "content":"<extra_id_21>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true },
+        { "content":"<extra_id_20>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true },
+        { "content":"<extra_id_19>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true },
+        { "content":"<extra_id_18>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true },
+        { "content":"<extra_id_17>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true },
+        { "content":"<extra_id_16>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true },
+        { "content":"<extra_id_15>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true },
+        { "content":"<extra_id_14>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true },
+        { "content":"<extra_id_13>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true },
+        { "content":"<extra_id_12>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true },
+        { "content":"<extra_id_11>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true },
+        { "content":"<extra_id_10>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true },
+        { "content":"<extra_id_9>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true },
+        { "content":"<extra_id_8>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true },
+        { "content":"<extra_id_7>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true },
+        { "content":"<extra_id_6>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true },
+        { "content":"<extra_id_5>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true },
+        { "content":"<extra_id_4>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true },
+        { "content":"<extra_id_3>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true },
+        { "content":"<extra_id_2>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true },
+        { "content":"<extra_id_1>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true },
+        { "content":"<extra_id_0>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true }
+    ]
+}

tokenizer_config.json

@@ -0,0 +1,63 @@
+{
+    "errors": "replace",
+    "unk_token": {
+        "content": "<unk>",
+        "single_word": false,
+        "lstrip": false,
+        "rstrip": false,
+        "normalized": true,
+        "__type": "AddedToken"
+    },
+    "bos_token": {
+        "content": "<s>",
+        "single_word": false,
+        "lstrip": false,
+        "rstrip": false,
+        "normalized": true,
+        "__type": "AddedToken"
+    },
+    "eos_token": {
+        "content": "</s>",
+        "single_word": false,
+        "lstrip": false,
+        "rstrip": false,
+        "normalized": true,
+        "__type": "AddedToken"
+    },
+    "add_prefix_space": false,
+    "sep_token": {
+        "content": "</s>",
+        "single_word": false,
+        "lstrip": false,
+        "rstrip": false,
+        "normalized": true,
+        "__type": "AddedToken"
+    },
+    "cls_token": {
+        "content": "<s>",
+        "single_word": false,
+        "lstrip": false,
+        "rstrip": false,
+        "normalized": true,
+        "__type": "AddedToken"
+    },
+    "pad_token": {
+        "content": "<pad>",
+        "single_word": false,
+        "lstrip": false,
+        "rstrip": false,
+        "normalized": true,
+        "__type": "AddedToken"
+    },
+    "mask_token": {
+        "content": "<mask>",
+        "single_word": false,
+        "lstrip": true,
+        "rstrip": false,
+        "normalized": true,
+        "__type": "AddedToken"
+    },
+    "model_max_length": 512,
+    "tokenizer_class": "RobertaTokenizer"
+}
+