README.md

---
base_model: google/gemma-4-e2b-it
tags:
- text-generation-inference
- transformers
- gemma4
- peft
- lora
- cybersecurity
- cloud-security
- aws
- iam
- terraform
- devsecops
- cybersecurity
license: apache-2.0
language:
- en
---

# Gemma 4 E2B — Cloud IAM & Terraform Security Expert

A QLoRA fine-tuned version of [Gemma 4 E2B Instruct](https://huggingface.co/google/gemma-4-e2b-it) specialized in **cloud iam & terraform security**.
Specialized in **cloud IAM and Terraform security**: least-privilege IAM policy design, ECR image scanning, Terraform state security, and cloud privilege escalation paths.

Part of the [rezaduty cybersecurity model family](https://huggingface.co/rezaduty).

---

## Expertise

- AWS IAM least-privilege design and permission boundaries
- IAM role assumption, OIDC federation, and cross-account access
- ECR image scanning, lifecycle policies, and pull-through cache security
- Terraform state file security, remote backends, and drift detection
- Cloud privilege escalation paths and detection
- IaC security scanning: Checkov, tfsec, Terrascan

---

## Model Details

| Property | Value |
|---|---|
| **Base model** | google/gemma-4-e2b-it (2B parameters) |
| **Fine-tuning method** | QLoRA (rank 16, α 16) |
| **Domain** | Cloud IAM & Terraform Security |
| **License** | Apache 2.0 |

---

## Usage

```python
from transformers import AutoTokenizer, AutoModelForCausalLM
from peft import PeftModel
import torch

base_model = "google/gemma-4-e2b-it"
adapter    = "rezaduty/gemma4-e2b-cloud-iam-terraform"

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 cloud IAM and infrastructure-as-code security. You provide deep answers on AWS IAM, ECR hardening, Terraform security, and cloud privilege escalation paths."}]},
    {"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 cloud IAM and infrastructure-as-code security. You provide deep answers on AWS IAM, ECR hardening, Terraform security, and cloud privilege escalation paths.
```

---

## See Also

- [General cybersecurity model](https://huggingface.co/rezaduty/gemma4-e2b-cybersecurity-interview) — full 646-example dataset
- [Docker & Container Security](https://huggingface.co/rezaduty/gemma4-e2b-docker-container-security)
- [Kubernetes Security](https://huggingface.co/rezaduty/gemma4-e2b-kubernetes-security)
- [AI & LLM Security](https://huggingface.co/rezaduty/gemma4-e2b-ai-llm-security)
- [All rezaduty models](https://huggingface.co/rezaduty)