Mistral 7B Security Audit

Published by @secllm · Community adapter

Trained on 15 k annotated code security reviews covering OWASP Top 10. Identifies injection, IDOR, and auth bypass patterns. Outputs structured finding reports with severity ratings.

Usage

from peft import PeftModel
from transformers import AutoModelForCausalLM, AutoTokenizer

tokenizer = AutoTokenizer.from_pretrained("mistralai/Mistral-7B-Instruct-v0.3")
base = AutoModelForCausalLM.from_pretrained("mistralai/Mistral-7B-Instruct-v0.3")
model = PeftModel.from_pretrained(base, "modelforgelab/mistral-7b-security-audit-lora")

inputs = tokenizer("Your prompt here", return_tensors="pt")
outputs = model.generate(**inputs, max_new_tokens=256)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))

Compatibility

• transformers>=4.38
• vLLM