GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
MushiSenpai
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Run this model inference with full control and performance in your environment.
Model Details
Model Provider
MushiSenpai
Model Tree
Qwen/Qwen2.5-Coder-32B-Instruct
Input Modalities
Output Modalities
Supported Functionality
This project was built measurement-first, and the honest result matters:
Qwen2.5-Coder was ≈ 0.0.
The base model already detects as well; the adapter does not make it "smarter."FINDING: {"cwe": "...", "severity": "...", "confidence": ...} or {"no_finding": true})
instead of the base model's verbose, inconsistent JSON/prose. That consistency is what lets an
agent loop and downstream parsers consume the output reliably.We publish this for reproducibility and as an honest artifact — not as a "SOTA vuln detector." For numbers to trust, read the eval reports.
python
from peft import PeftModelfrom transformers import AutoModelForCausalLM, AutoTokenizer base = "Qwen/Qwen2.5-Coder-32B-Instruct"tok = AutoTokenizer.from_pretrained(base)model = AutoModelForCausalLM.from_pretrained(base, device_map="auto", load_in_4bit=True)model = PeftModel.from_pretrained(model, "MushiSenpai/SovereignSec-Auditor-LoRA-Qwen2.5-Coder-32B") msgs = [ {"role": "system", "content": "You are a security auditor. Trace taint and report findings as JSON, or say no finding when safe."}, {"role": "user", "content": "Audit:\n```python\nname = request.args.get('name')\nq = \"SELECT * FROM u WHERE n='%s'\" % name\ncur.execute(q)\n```"},]ids = tok.apply_chat_template(msgs, add_generation_prompt=True, return_tensors="pt").to(model.device)print(tok.decode(model.generate(ids, max_new_tokens=80)[0][ids.shape[1]:], skip_special_tokens=True))# -> FINDING: {"cwe": "CWE-89", "severity": "high", "confidence": 0.9}Qwen/Qwen2.5-Coder-32B-Instruct (Apache-2.0)Adapter: Apache-2.0. Base model: Apache-2.0. Training data derived from the GitHub Advisory
Database / CVEfixes (CC-BY-4.0). A 7B variant (Qwen2.5-Coder-7B, loss 0.686) was also trained —
see the 7B card.
from peft import PeftModelfrom transformers import AutoModelForCausalLM, AutoTokenizer base = "Qwen/Qwen2.5-Coder-32B-Instruct"tok = AutoTokenizer.from_pretrained(base)model = AutoModelForCausalLM.from_pretrained(base, device_map="auto", load_in_4bit=True)model = PeftModel.from_pretrained(model, "MushiSenpai/SovereignSec-Auditor-LoRA-Qwen2.5-Coder-32B") msgs = [ {"role": "system", "content": "You are a security auditor. Trace taint and report findings as JSON, or say no finding when safe."}, {"role": "user", "content": "Audit:\n```python\nname = request.args.get('name')\nq = \"SELECT * FROM u WHERE n='%s'\" % name\ncur.execute(q)\n```"},]ids = tok.apply_chat_template(msgs, add_generation_prompt=True, return_tensors="pt").to(model.device)print(tok.decode(model.generate(ids, max_new_tokens=80)[0][ids.shape[1]:], skip_special_tokens=True))# -> FINDING: {"cwe": "CWE-89", "severity": "high", "confidence": 0.9}