Initial Commir

app.py

@@ -0,0 +1,38 @@
+import gradio as gr
+from transformers import AutoTokenizer, AutoModelForSequenceClassification
+from huggingface_hub import hf_hub_download
+import torch
+import json
+
+def predict(text):
+    inputs = tokenizer(text, return_tensors="pt", truncation=True, padding=True, max_length=512)
+
+    with torch.no_grad():
+        outputs = model(**inputs)
+
+    probs = torch.nn.functional.softmax(outputs.logits, dim=-1)
+    predicted_class = torch.argmax(probs, dim=-1).item()
+    return label_dict[str(predicted_class)], probs[0][predicted_class].item()
+
+if __name__ == '__main__':
+    model_path = "Dunateo/roberta-cwe-classifier-kelemia-v0.2"
+
+    # init the model
+    tokenizer = AutoTokenizer.from_pretrained(model_path)
+    model = AutoModelForSequenceClassification.from_pretrained(model_path)
+
+    # get the dict file
+    label_dict_file = hf_hub_download(repo_id=model_path, filename="label_dict.json")
+    with open(label_dict_file, "r") as f:
+        label_dict = json.load(f)
+
+    # gradio specific to create an IHM
+    iface = gr.Interface(
+        fn=predict,
+        inputs=gr.Textbox(lines=5, label="Enter vulnerability description"),
+        outputs=[gr.Label(label="Predicted CWE"), gr.Number(label="Confidence")],
+        title="Vulnerability CWE Classification",
+        description="Enter a vulnerability description to classify it into a CWE category."
+    )
+
+    iface.launch()

requirements.txt

@@ -0,0 +1,3 @@
+torch
+transformers
+gradio