Transformers
Safetensors
PEFT
English
text-generation-inference
gemma4
lora
cybersecurity
docker
container-security
devsecops
Instructions to use rezaduty/gemma4-e2b-docker-container-security with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use rezaduty/gemma4-e2b-docker-container-security with Transformers:
# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("rezaduty/gemma4-e2b-docker-container-security", dtype="auto") - PEFT
How to use rezaduty/gemma4-e2b-docker-container-security with PEFT:
Task type is invalid.
- Notebooks
- Google Colab
- Kaggle
Gemma 4 E2B โ Docker & Container Security Expert
A QLoRA fine-tuned version of Gemma 4 E2B Instruct specialized in docker & container security. Specialized in Docker and container security: image hardening, rootless containers, seccomp/AppArmor profiles, runtime threat detection, and container escape techniques and mitigations.
Part of the rezaduty cybersecurity model family.
Expertise
- Docker daemon security and socket exposure risks
- Image scanning, distroless images, and minimal base images
- Rootless containers, user namespaces, and capability dropping
- Runtime security with Falco, seccomp, and AppArmor
- Container escape techniques and kernel exploit mitigations
- Dockerfile best practices and supply-chain integrity
Model Details
| Property | Value |
|---|---|
| Base model | google/gemma-4-e2b-it (2B parameters) |
| Fine-tuning method | QLoRA (rank 16, ฮฑ 16) |
| Domain | Docker & Container Security |
| License | Apache 2.0 |
Usage
from transformers import AutoTokenizer, AutoModelForCausalLM
from peft import PeftModel
import torch
base_model = "google/gemma-4-e2b-it"
adapter = "rezaduty/gemma4-e2b-docker-container-security"
tokenizer = AutoTokenizer.from_pretrained(adapter)
model = AutoModelForCausalLM.from_pretrained(
base_model, torch_dtype=torch.bfloat16, device_map="auto"
)
model = PeftModel.from_pretrained(model, adapter)
messages = [
{"role": "system", "content": [{"type": "text", "text": "You are an expert in Docker and container security. You provide deep, production-level answers on container hardening, image security, runtime protection, and container escape prevention."}]},
{"role": "user", "content": [{"type": "text", "text": "Your question here"}]},
]
inputs = tokenizer.apply_chat_template(
messages, tokenize=True, add_generation_prompt=True, return_tensors="pt"
).to(model.device)
output = model.generate(inputs, max_new_tokens=512, temperature=0.7, top_p=0.9)
print(tokenizer.decode(output[0][inputs.shape[-1]:], skip_special_tokens=True))
System Prompt
You are an expert in Docker and container security. You provide deep, production-level answers on container hardening, image security, runtime protection, and container escape prevention.
See Also
- General cybersecurity model โ full 646-example dataset
- All rezaduty models
Inference Providers NEW
This model isn't deployed by any Inference Provider. ๐ Ask for provider support