Upload 22 files

app.py

@@ -5,6 +5,31 @@ from utils import *
 
 PATH = os.getcwd()
 
+def show_cwe_sev(input_code):
+    # more predictions
+    cwe_pred = predict_cweid([input_code])["cwe_id"][0]
+    sev_pred = predict_sev([input_code])
+    sev_score = int(sev_pred["batch_sev_score"][0])
+    sev_class = sev_pred["batch_sev_class"][0]
+    
+    if "CWE-" in cwe_pred:
+        id_ = cwe_pred.split("CWE-")[-1]
+        link = f"https://cwe.mitre.org/data/definitions/{id_}.html"
+        st.markdown(f'**CWE ID: <a href="{link}">{cwe_pred}</a>**', unsafe_allow_html=True)
+    if sev_score < 4:
+        st.markdown(f"**Severity: <span style='color:blue'>{sev_class}</span>**", unsafe_allow_html=True)
+        st.markdown(f"**Severity Score: <span style='color:blue'>{sev_score}</span>**", unsafe_allow_html=True)
+    elif sev_score < 7:
+        st.markdown(f"**Severity: <span style='color:orange'>{sev_class}</span>**", unsafe_allow_html=True)
+        st.markdown(f"**Severity Score: <span style='color:orange'>{sev_score}</span>**", unsafe_allow_html=True)
+    elif sev_score < 9:
+        st.markdown(f"**Severity: <span style='color:red'>{sev_class}</span>**", unsafe_allow_html=True)
+        st.markdown(f"**Severity Score: <span style='color:red'>{sev_score}</span>**", unsafe_allow_html=True)
+    else:
+        st.markdown(f"**Severity: <span style='color:red'>{sev_class}</span>**", unsafe_allow_html=True)
+        st.markdown(f"**Severity Score: <span style='color:red'>{sev_score}</span>**", unsafe_allow_html=True)
+        
+
 if __name__ == "__main__":
     MAX_NUM_STATEMENTS = 155
     
@@ -43,16 +68,17 @@ if __name__ == "__main__":
                 print_code = input_code.split("\n")[:MAX_NUM_STATEMENTS]
                 st.markdown("### Scanning Results:")                                
                 if func_pred == 0:
-                    st.write("<span style='color:green'>" + "No vulnerabilities detected"+ "</span>", unsafe_allow_html=True)
+                    st.markdown("<span style='color:green'>" + "**No vulnerabilities detected**"+ "</span>", unsafe_allow_html=True)
                     st.markdown("### Non-Vulnerable Function:")
                 else:
+                    show_cwe_sev(input_code)
                     for i in range(len(print_code)):
                         c = print_code[i]
                         vul = line_pred[i]
                         if vul == 1:
-                            st.write(f"<span style='color:red'> Vulnerable Line {i+1} </span>", unsafe_allow_html=True)
+                            st.markdown(f"<span style='color:red'> Vulnerable Line **{i+1}** </span>", unsafe_allow_html=True)
                             st.code(c)
-                    st.markdown("### Vulnerable Function:")   
+                    st.markdown("### Vulnerable Function:")
                 st.code(input_code, language="cpp", line_numbers=True)
                     
     elif behavior == "Analyze my own":
@@ -79,6 +105,7 @@ if __name__ == "__main__":
                     st.write("<span style='color:green'>" + "No vulnerabilities detected"+ "</span>", unsafe_allow_html=True)
                     st.markdown("### Non-Vulnerable Function:")
                 else:
+                    show_cwe_sev(input_code)
                     for i in range(len(print_code)):
                         c = print_code[i]
                         vul = line_pred[i]

models/cwe_model.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3ac47f1247f508d32fc066a9be350b3167812c32be05ec260854c8ad156f6468
+size 501315094

models/sev_model.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5cf1d0ec1f7f7555c7bea95f954f53ab6fb1142e4fcbdb58c787e3321b4b2f5e
+size 498659773

requirements.txt

@@ -1,5 +1,6 @@
 transformers
 torch
+pickle
 numpy
 onnxruntime
 pandas

utils.py

@@ -30,9 +30,9 @@ def predict_vul_lines(code: list, gpu: bool = False) -> dict:
     MAX_STATEMENT_LENGTH = 20
     DEVICE = 'cuda' if gpu else 'cpu'
     # load tokenizer
-    tokenizer = RobertaTokenizer.from_pretrained("./statement_t5_tokenizer")
+    tokenizer = RobertaTokenizer.from_pretrained("./utils/statement_t5_tokenizer")
     # load model
-    config = T5Config.from_pretrained("./t5_config.json")
+    config = T5Config.from_pretrained("./utils/t5_config.json")
     model = T5EncoderModel(config=config)    
     model = StatementT5(model, tokenizer, device=DEVICE)
     output_dir = "./models/statement_t5_model.bin"
@@ -96,10 +96,10 @@ def predict_cweid(code: list, gpu: bool = False) -> dict:
         "cwe_type_prob" stores a list of confidence scores of CWE abstract types predictions [0.9, 0.7, ...]
     """
     provider = ["CUDAExecutionProvider", "CPUExecutionProvider"] if gpu else ["CPUExecutionProvider"]
-    with open("./inference-common/label_map.pkl", "rb") as f:
+    with open("./utils/label_map.pkl", "rb") as f:
         cwe_id_map, cwe_type_map = pickle.load(f)
     # load tokenizer
-    tokenizer = RobertaTokenizer.from_pretrained("./inference-common/tokenizer")
+    tokenizer = RobertaTokenizer.from_pretrained("./utils/tokenizer")
     tokenizer.add_tokens(["<cls_type>"])
     tokenizer.cls_type_token = "<cls_type>"
     model_input = []
@@ -155,7 +155,7 @@ def predict_sev(code: list, gpu: bool = False) -> dict:
     """
     provider = ["CUDAExecutionProvider", "CPUExecutionProvider"] if gpu else ["CPUExecutionProvider"]
     # load tokenizer
-    tokenizer = RobertaTokenizer.from_pretrained("./inference-common/tokenizer")
+    tokenizer = RobertaTokenizer.from_pretrained("./utils/tokenizer")
     model_input = tokenizer(code, truncation=True, max_length=512, padding='max_length',
                             return_tensors="pt").input_ids
     # onnx runtime session
@@ -177,12 +177,7 @@ def predict_sev(code: list, gpu: bool = False) -> dict:
         else:
             batch_sev_class.append("Critical")
     return {"batch_sev_score": batch_sev_score, "batch_sev_class": batch_sev_class}
-
-def predict(code: list):
-    vul_preds = predict_vul_lines(code)
-    cwe_preds = predict_cweid(code)
-    sev_preds = predict_sev(code)
-    
+ 
 if __name__ == "__main__":
     import pandas as pd
     df = pd.read_csv("./data/processed_test.csv")

utils/label_map.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f8047aabb5286aefb088ca1017fbf7775f9da3ab56248a7620d117ff15f11a45
+size 1419

utils/repair_model_config.json

@@ -0,0 +1,65 @@
+{
+  "_name_or_path": "/content/drive/MyDrive/CodeT5/pretrained_models/codet5_base",
+  "architectures": [
+    "T5ForConditionalGeneration"
+  ],
+  "bos_token_id": 1,
+  "d_ff": 3072,
+  "d_kv": 64,
+  "d_model": 768,
+  "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": 12,
+  "num_heads": 12,
+  "num_layers": 12,
+  "output_past": true,
+  "pad_token_id": 0,
+  "relative_attention_num_buckets": 32,
+  "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": "4.10.2",
+  "use_cache": true,
+  "vocab_size": 32100
+}

utils/statement_t5_tokenizer/special_tokens_map.json

@@ -0,0 +1,753 @@
+{
+  "additional_special_tokens": [
+    {
+      "content": "<extra_id_99>",
+      "lstrip": true,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<extra_id_98>",
+      "lstrip": true,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<extra_id_97>",
+      "lstrip": true,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<extra_id_96>",
+      "lstrip": true,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<extra_id_95>",
+      "lstrip": true,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<extra_id_94>",
+      "lstrip": true,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<extra_id_93>",
+      "lstrip": true,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<extra_id_92>",
+      "lstrip": true,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<extra_id_91>",
+      "lstrip": true,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<extra_id_90>",
+      "lstrip": true,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<extra_id_89>",
+      "lstrip": true,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<extra_id_88>",
+      "lstrip": true,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<extra_id_87>",
+      "lstrip": true,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<extra_id_86>",
+      "lstrip": true,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<extra_id_85>",
+      "lstrip": true,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<extra_id_84>",
+      "lstrip": true,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<extra_id_83>",
+      "lstrip": true,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<extra_id_82>",
+      "lstrip": true,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<extra_id_81>",
+      "lstrip": true,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<extra_id_80>",
+      "lstrip": true,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<extra_id_79>",
+      "lstrip": true,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<extra_id_78>",
+      "lstrip": true,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<extra_id_77>",
+      "lstrip": true,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<extra_id_76>",
+      "lstrip": true,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<extra_id_75>",
+      "lstrip": true,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<extra_id_74>",
+      "lstrip": true,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<extra_id_73>",
+      "lstrip": true,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<extra_id_72>",
+      "lstrip": true,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<extra_id_71>",
+      "lstrip": true,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<extra_id_70>",
+      "lstrip": true,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<extra_id_69>",
+      "lstrip": true,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<extra_id_68>",
+      "lstrip": true,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<extra_id_67>",
+      "lstrip": true,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<extra_id_66>",
+      "lstrip": true,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<extra_id_65>",
+      "lstrip": true,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<extra_id_64>",
+      "lstrip": true,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<extra_id_63>",
+      "lstrip": true,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<extra_id_62>",
+      "lstrip": true,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<extra_id_61>",
+      "lstrip": true,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<extra_id_60>",
+      "lstrip": true,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<extra_id_59>",
+      "lstrip": true,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<extra_id_58>",
+      "lstrip": true,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<extra_id_57>",
+      "lstrip": true,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<extra_id_56>",
+      "lstrip": true,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<extra_id_55>",
+      "lstrip": true,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<extra_id_54>",
+      "lstrip": true,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<extra_id_53>",
+      "lstrip": true,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<extra_id_52>",
+      "lstrip": true,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<extra_id_51>",
+      "lstrip": true,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<extra_id_50>",
+      "lstrip": true,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<extra_id_49>",
+      "lstrip": true,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<extra_id_48>",
+      "lstrip": true,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<extra_id_47>",
+      "lstrip": true,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<extra_id_46>",
+      "lstrip": true,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<extra_id_45>",
+      "lstrip": true,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<extra_id_44>",
+      "lstrip": true,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<extra_id_43>",
+      "lstrip": true,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<extra_id_42>",
+      "lstrip": true,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<extra_id_41>",
+      "lstrip": true,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<extra_id_40>",
+      "lstrip": true,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<extra_id_39>",
+      "lstrip": true,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<extra_id_38>",
+      "lstrip": true,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<extra_id_37>",
+      "lstrip": true,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<extra_id_36>",
+      "lstrip": true,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<extra_id_35>",
+      "lstrip": true,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<extra_id_34>",
+      "lstrip": true,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<extra_id_33>",
+      "lstrip": true,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<extra_id_32>",
+      "lstrip": true,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<extra_id_31>",
+      "lstrip": true,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<extra_id_30>",
+      "lstrip": true,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<extra_id_29>",
+      "lstrip": true,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<extra_id_28>",
+      "lstrip": true,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<extra_id_27>",
+      "lstrip": true,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<extra_id_26>",
+      "lstrip": true,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<extra_id_25>",
+      "lstrip": true,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<extra_id_24>",
+      "lstrip": true,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<extra_id_23>",
+      "lstrip": true,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<extra_id_22>",
+      "lstrip": true,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<extra_id_21>",
+      "lstrip": true,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<extra_id_20>",
+      "lstrip": true,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<extra_id_19>",
+      "lstrip": true,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<extra_id_18>",
+      "lstrip": true,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<extra_id_17>",
+      "lstrip": true,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<extra_id_16>",
+      "lstrip": true,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<extra_id_15>",
+      "lstrip": true,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<extra_id_14>",
+      "lstrip": true,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<extra_id_13>",
+      "lstrip": true,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<extra_id_12>",
+      "lstrip": true,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<extra_id_11>",
+      "lstrip": true,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<extra_id_10>",
+      "lstrip": true,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<extra_id_9>",
+      "lstrip": true,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<extra_id_8>",
+      "lstrip": true,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<extra_id_7>",
+      "lstrip": true,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<extra_id_6>",
+      "lstrip": true,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<extra_id_5>",
+      "lstrip": true,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<extra_id_4>",
+      "lstrip": true,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<extra_id_3>",
+      "lstrip": true,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<extra_id_2>",
+      "lstrip": true,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<extra_id_1>",
+      "lstrip": true,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<extra_id_0>",
+      "lstrip": true,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false
+    }
+  ],
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

utils/statement_t5_tokenizer/tokenizer_config.json

@@ -0,0 +1,64 @@
+{
+  "add_prefix_space": false,
+  "bos_token": {
+    "__type": "AddedToken",
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "__type": "AddedToken",
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "__type": "AddedToken",
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "errors": "replace",
+  "mask_token": {
+    "__type": "AddedToken",
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "model_max_length": 512,
+  "name_or_path": "Salesforce/codet5-base",
+  "pad_token": {
+    "__type": "AddedToken",
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "__type": "AddedToken",
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "special_tokens_map_file": "/home/michael/.cache/huggingface/transformers/5941df5e4315c5ab63b7b2ac791fb0bf0f209744a055c06b43b5274849137cdd.b9905d0575bde443a20834122b6e2d48e853b2e36444ce98ddeb43c38097eb3f",
+  "tokenizer_class": "RobertaTokenizer",
+  "unk_token": {
+    "__type": "AddedToken",
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

utils/t5_config.json

@@ -0,0 +1,68 @@
+{
+  "_name_or_path": "Salesforce/codet5-base",
+  "architectures": [
+    "T5ForConditionalGeneration"
+  ],
+  "bos_token_id": 1,
+  "d_ff": 3072,
+  "d_kv": 64,
+  "d_model": 768,
+  "decoder_start_token_id": 0,
+  "dense_act_fn": "relu",
+  "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,
+  "is_gated_act": false,
+  "label2id": {
+    "LABEL_0": 0
+  },
+  "layer_norm_epsilon": 1e-06,
+  "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_max_distance": 128,
+  "relative_attention_num_buckets": 32,
+  "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": "4.27.3",
+  "use_cache": true,
+  "vocab_size": 32100
+}

utils/tokenizer/special_tokens_map.json

@@ -0,0 +1 @@
+{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "sep_token": "</s>", "pad_token": "<pad>", "cls_token": "<s>", "mask_token": "<mask>"}

utils/tokenizer/tokenizer_config.json

@@ -0,0 +1 @@
+{"errors": "replace", "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"}, "unk_token": {"content": "<unk>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "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"}, "add_prefix_space": false, "model_max_length": 512, "special_tokens_map_file": "/home/michael/.cache/huggingface/transformers/4da22fec5578ecec5fbe32b80d5a43c6fb66b0f6ad5e359979463f0722ac3b5f.0dc5b1041f62041ebbd23b1297f2f573769d5c97d8b7c28180ec86b8f6185aa8", "name_or_path": "microsoft/codebert-base", "tokenizer_class": "RobertaTokenizer"}