An English Qwen3.5 2B checkpoint associated with the Trendyol Cybersecurity Instruction Tuning Dataset and exported in Transformers / Safetensors format.
This release is intended for research and local experimentation. The repository does not currently publish benchmark or safety-evaluation results, so the model should not be treated as a validated cybersecurity authority.
The configuration identifies a Qwen3.5 conditional-generation architecture with text and vision components. Use a recent Transformers release that supports this architecture.
1from transformers import AutoModelForMultimodalLM, AutoProcessor
2
3model_id = "reaperdoesntknow/Qwen3.5-2B-CyberSec"
4
5processor = AutoProcessor.from_pretrained(model_id)
6model = AutoModelForMultimodalLM.from_pretrained(
7 model_id,
8 device_map="auto",
9)
10
11messages = [
12 {"role": "user", "content": [{"type": "text", "text": "Explain least privilege."}]}
13]
14inputs = processor.apply_chat_template(
15 messages,
16 add_generation_prompt=True,
17 tokenize=True,
18 return_dict=True,
19 return_tensors="pt",
20).to(model.device)
21
22outputs = model.generate(**inputs, max_new_tokens=256)
23answer = outputs[0][inputs["input_ids"].shape[-1]:]
24print(processor.decode(answer, skip_special_tokens=True))
Dependency and device behavior can vary across Transformers versions. Pin a tested environment for reproducible use.
No versioned benchmark report, baseline comparison, held-out test result, or safety evaluation is published in the repository reviewed for this card. Dataset association and a successful model export do not establish improved cybersecurity performance.
