Views
No views yet
| Property | Value |
|---|---|
| Base model | google/gemma-4-e2b-it (2B parameters) |
| Fine-tuning method | QLoRA (rank 16, α 16) |
| Domain | Linux Privilege Escalation |
| Dataset | rezaduty/cybersecurity-qa-v2 |
| License | Apache 2.0 |
1from transformers import AutoTokenizer, AutoModelForCausalLM
2from peft import PeftModel
3import torch
4
5base_model = "google/gemma-4-e2b-it"
6adapter = "rezaduty/gemma4-e2b-privesc-linux"
7
8tokenizer = AutoTokenizer.from_pretrained(adapter)
9model = AutoModelForCausalLM.from_pretrained(
10 base_model, torch_dtype=torch.bfloat16, device_map="auto"
11)
12model = PeftModel.from_pretrained(model, adapter)
13
14messages = [
15 {"role": "system", "content": [{"type": "text", "text": "You are an expert in Linux privilege escalation techniques. Provide deep technical answers on Linux privesc methods, enumeration strategies, detection, and hardening with specific commands, tool names, and kernel CVE references."}]},
16 {"role": "user", "content": [{"type": "text", "text": "Your question here"}]},
17]
18inputs = tokenizer.apply_chat_template(
19 messages, tokenize=True, add_generation_prompt=True, return_tensors="pt"
20).to(model.device)
21output = model.generate(inputs, max_new_tokens=512, temperature=0.7, top_p=0.9)
22print(tokenizer.decode(output[0][inputs.shape[-1]:], skip_special_tokens=True))You are an expert in Linux privilege escalation techniques. Provide deep technical answers on Linux privesc methods, enumeration strategies, detection, and hardening with specific commands, tool names, and kernel CVE references.