Quantized GGUF version of
SecuCoder, a fine-tuned Llama 3.1 8B Instruct model for secure Python code generation and vulnerability remediation.
For full model details, training methodology, and evaluation results, see the
main model card.
1curl http://localhost:11434/api/generate -d '{
2 "model": "secucoder",
3 "prompt": "Fix the security vulnerability in this Python code.\n\n```python\nname = request.args.get(\"name\")\nresp = make_response(\"Your name is \" + name)\n```\n\nCWE: CWE-079",
4 "stream": false
5}'
1./llama-cli \
2 -m secucoder-Q4_K_M.gguf \
3 --ctx-size 4096 \
4 --temp 0.1 \
5 --top-p 0.9 \
6 -p "You are a secure Python assistant. Fix the vulnerability in this code: ..."
The full SecuCoder system (Q4 + structured prompting + RAG) achieves an overall score of 77.11 vs 60.34 for the untuned Llama 3.1 8B baseline — a +27.8% improvement measured by weighted static analysis findings (Bandit + Semgrep).
Released under
CC BY-NC-SA 4.0. Built on Llama 3.1, subject to
Meta's Llama 3 Community License.
