Add specialized README for Kubernetes Security

README.md

@@ -1,22 +1,92 @@
 ---
-base_model: unsloth/gemma-4-e2b-it-unsloth-bnb-4bit
+base_model: google/gemma-4-e2b-it
 tags:
 - text-generation-inference
 - transformers
-- unsloth
 - gemma4
-- trl
+- peft
+- lora
+- cybersecurity
+- kubernetes
+- k8s
+- container-security
+- devsecops
+- cybersecurity
 license: apache-2.0
 language:
 - en
 ---
 
-# Uploaded  model
+# Gemma 4 E2B — Kubernetes Security Expert
 
-- **Developed by:** rezaduty
-- **License:** apache-2.0
-- **Finetuned from model :** unsloth/gemma-4-e2b-it-unsloth-bnb-4bit
+A QLoRA fine-tuned version of [Gemma 4 E2B Instruct](https://huggingface.co/google/gemma-4-e2b-it) specialized in **kubernetes security**.
+Specialized in **Kubernetes security**: RBAC design, Pod Security Standards, network policies, admission controllers, etcd encryption, and multi-tenant cluster hardening.
 
-This gemma4 model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth)
+Part of the [rezaduty cybersecurity model family](https://huggingface.co/rezaduty).
 
-[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
+---
+
+## Expertise
+
+- RBAC least-privilege design and audit logging
+- Pod Security Standards (Restricted, Baseline, Privileged)
+- Network policies and service mesh security (Istio/Linkerd)
+- Admission controllers: OPA Gatekeeper, Kyverno, Falco
+- Secrets encryption at rest and external secrets management
+- Supply-chain security: image signing, SBOM, admission control
+
+---
+
+## Model Details
+
+| Property | Value |
+|---|---|
+| **Base model** | google/gemma-4-e2b-it (2B parameters) |
+| **Fine-tuning method** | QLoRA (rank 16, α 16) |
+| **Domain** | Kubernetes 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-kubernetes-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 Kubernetes security. You provide deep answers on RBAC, Pod Security, network policies, admission controllers, secrets management, and cluster hardening."}]},
+    {"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 Kubernetes security. You provide deep answers on RBAC, Pod Security, network policies, admission controllers, secrets management, and cluster hardening.
+```
+
+---
+
+## 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)
+- [All rezaduty models](https://huggingface.co/rezaduty)