SecureCoder 30B Pro v3 — LoRA adapter
LoRA adapter on unsloth/Qwen3-Coder-30B-A3B-Instruct
for code generation, tool calling and cybersecurity (offence and defence).
Licence: Apache-2.0, following the base model.
Most people want the ready-to-run version:
Taimwe/securecoder-30b-pro-v3-merged.
Results
Same prompts, same harness (eval_securecoder.py):
| Model | Valid Python (15 prompts) | Tool calls correct (80 prompts) |
|---|---|---|
| base Qwen3-Coder-30B-A3B-Instruct | 93.3% | 100% |
| v2 (deprecated) | 0.0% | 100% |
| v3 | 100% | 100% |
Full method and limitations are on the
merged model card;
training, merge and eval scripts are in
Taimwe/securecoder-scripts.
Load the adapter
from peft import PeftModel
from transformers import AutoModelForCausalLM, AutoTokenizer
base = AutoModelForCausalLM.from_pretrained(
"unsloth/Qwen3-Coder-30B-A3B-Instruct", torch_dtype="bfloat16", device_map="auto")
model = PeftModel.from_pretrained(base, "Taimwe/securecoder-30b-pro-v3")
tok = AutoTokenizer.from_pretrained("Taimwe/securecoder-30b-pro-v3")
Limitations
- Produces working offensive-security code. Use only against systems you own or have written permission to test; you are responsible for its use.
- Inherits Qwen3-Coder's biases; no independent safety red-teaming was run.
- The security multiple-choice eval did not run, so no security-knowledge score is claimed.
- Behaviour outside the training mix is unverified.
- Downloads last month
- -
Model tree for Taimwe/securecoder-30b-pro-v3
Base model
Qwen/Qwen3-Coder-30B-A3B-Instruct Finetuned
unsloth/Qwen3-Coder-30B-A3B-Instruct