add files

README.md

@@ -1,3 +1,12 @@
 ---
+language: code
 license: apache-2.0
+
 ---
+# CodeReviewer
+
+## Fine-tuning Process
+
+We fine-tuned the [original CodeReviewer model](https://huggingface.co/microsoft/codereviewer) on the [Comment Generation dataset](https://zenodo.org/record/6900648) using a single A100 GPU, 8 CPU cores, and 20 GB of RAM. The fine-tuning process was run for 12 hours. 
+
+For further information please consider taking a look at the original [CodeReviewer paper](https://arxiv.org/abs/2203.09095).

added_tokens.json

@@ -0,0 +1 @@
+{"<keep>": 32100, "<add>": 32101, "<del>": 32102, "<start>": 32103, "<end>": 32104, "<e99>": 32105, "<e98>": 32106, "<e97>": 32107, "<e96>": 32108, "<e95>": 32109, "<e94>": 32110, "<e93>": 32111, "<e92>": 32112, "<e91>": 32113, "<e90>": 32114, "<e89>": 32115, "<e88>": 32116, "<e87>": 32117, "<e86>": 32118, "<e85>": 32119, "<e84>": 32120, "<e83>": 32121, "<e82>": 32122, "<e81>": 32123, "<e80>": 32124, "<e79>": 32125, "<e78>": 32126, "<e77>": 32127, "<e76>": 32128, "<e75>": 32129, "<e74>": 32130, "<e73>": 32131, "<e72>": 32132, "<e71>": 32133, "<e70>": 32134, "<e69>": 32135, "<e68>": 32136, "<e67>": 32137, "<e66>": 32138, "<e65>": 32139, "<e64>": 32140, "<e63>": 32141, "<e62>": 32142, "<e61>": 32143, "<e60>": 32144, "<e59>": 32145, "<e58>": 32146, "<e57>": 32147, "<e56>": 32148, "<e55>": 32149, "<e54>": 32150, "<e53>": 32151, "<e52>": 32152, "<e51>": 32153, "<e50>": 32154, "<e49>": 32155, "<e48>": 32156, "<e47>": 32157, "<e46>": 32158, "<e45>": 32159, "<e44>": 32160, "<e43>": 32161, "<e42>": 32162, "<e41>": 32163, "<e40>": 32164, "<e39>": 32165, "<e38>": 32166, "<e37>": 32167, "<e36>": 32168, "<e35>": 32169, "<e34>": 32170, "<e33>": 32171, "<e32>": 32172, "<e31>": 32173, "<e30>": 32174, "<e29>": 32175, "<e28>": 32176, "<e27>": 32177, "<e26>": 32178, "<e25>": 32179, "<e24>": 32180, "<e23>": 32181, "<e22>": 32182, "<e21>": 32183, "<e20>": 32184, "<e19>": 32185, "<e18>": 32186, "<e17>": 32187, "<e16>": 32188, "<e15>": 32189, "<e14>": 32190, "<e13>": 32191, "<e12>": 32192, "<e11>": 32193, "<e10>": 32194, "<e9>": 32195, "<e8>": 32196, "<e7>": 32197, "<e6>": 32198, "<e5>": 32199, "<e4>": 32200, "<e3>": 32201, "<e2>": 32202, "<e1>": 32203, "<e0>": 32204, "<msg>": 32205, "<en>": 32206, "<python>": 32207, "<java>": 32208, "<javascript>": 32209, "<ruby>": 32210, "<php>": 32211, "<go>": 32212, "<c>": 32213, "<c_sharp>": 32214, "<c_plus_plus>": 32215}

config.json

@@ -0,0 +1,95 @@
+{
+  "_name_or_path": "/content/drive/MyDrive/CodeT5/pretrained_models/codet5_base",
+  "add_token_id": 32101,
+  "architectures": [
+    "T5ForConditionalGeneration"
+  ],
+  "bos_token_id": 1,
+  "d_ff": 3072,
+  "d_kv": 64,
+  "d_model": 768,
+  "decoder_start_token_id": 0,
+  "del_token_id": 32102,
+  "dropout_rate": 0.1,
+  "end_token_id": 32104,
+  "eos_token_id": 2,
+  "feed_forward_proj": "relu",
+  "gradient_checkpointing": false,
+  "id2label": {
+    "0": "LABEL_0"
+  },
+  "initializer_factor": 1.0,
+  "is_encoder_decoder": true,
+  "keep_token_id": 32100,
+  "label2id": {
+    "LABEL_0": 0
+  },
+  "lang_id": {
+    "<c>": 32213,
+    "<c_plus_plus>": 32215,
+    "<c_sharp>": 32214,
+    "<en>": 32206,
+    "<go>": 32212,
+    "<java>": 32208,
+    "<javascript>": 32209,
+    "<php>": 32211,
+    "<python>": 32207,
+    "<ruby>": 32210
+  },
+  "lang_tokens": [
+    "<en>",
+    "<python>",
+    "<java>",
+    "<javascript>",
+    "<ruby>",
+    "<php>",
+    "<go>",
+    "<c>",
+    "<c_sharp>",
+    "<c_plus_plus>"
+  ],
+  "layer_norm_epsilon": 1e-06,
+  "mask_token_id": 4,
+  "model_type": "t5",
+  "n_positions": 512,
+  "num_decoder_layers": 12,
+  "num_heads": 12,
+  "num_layers": 12,
+  "output_past": true,
+  "pad_token_id": 0,
+  "relative_attention_num_buckets": 32,
+  "start_token_id": 32103,
+  "task_specific_params": {
+    "summarization": {
+      "early_stopping": true,
+      "length_penalty": 2.0,
+      "max_length": 200,
+      "min_length": 30,
+      "no_repeat_ngram_size": 3,
+      "num_beams": 4,
+      "prefix": "summarize: "
+    },
+    "translation_en_to_de": {
+      "early_stopping": true,
+      "max_length": 300,
+      "num_beams": 4,
+      "prefix": "translate English to German: "
+    },
+    "translation_en_to_fr": {
+      "early_stopping": true,
+      "max_length": 300,
+      "num_beams": 4,
+      "prefix": "translate English to French: "
+    },
+    "translation_en_to_ro": {
+      "early_stopping": true,
+      "max_length": 300,
+      "num_beams": 4,
+      "prefix": "translate English to Romanian: "
+    }
+  },
+  "torch_dtype": "float32",
+  "transformers_version": "4.15.0",
+  "use_cache": true,
+  "vocab_size": 32216
+}

generation_config.json

@@ -0,0 +1,8 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "decoder_start_token_id": 0,
+  "eos_token_id": 2,
+  "pad_token_id": 0,
+  "transformers_version": "4.27.0.dev0"
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:edccaec26eb22f8e0c708d245f8ad528102aa17ca02b546a530a4775adf3fd74
+size 892009595

special_tokens_map.json

@@ -0,0 +1 @@
+{"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": ["<en>", "<python>", "<java>", "<javascript>", "<ruby>", "<php>", "<go>", "<c>", "<c_sharp>", "<c_plus_plus>"]}

tokenizer_config.json

@@ -0,0 +1 @@
+{"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, "special_tokens_map_file": "/home/shuailu/lushuai/code_review/PreViewer/pretrained_models/codet5/special_tokens_map.json", "tokenizer_file": null, "name_or_path": "/home/shuailu/lushuai/code_review/PreViewer/pretrained_models/codet5", "tokenizer_class": "RobertaTokenizer"}