File size: 1,486 Bytes
95f0274 2163f78 95f0274 0517bb5 2163f78 95f0274 0517bb5 95f0274 2163f78 95f0274 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 |
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 id2label[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:
content = f.read()
label_dict = json.loads(content)
global id2label
id2label = {v: k for k, v in label_dict.items()}
# 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() |