Upload README.md

README.md

@@ -1,26 +1,71 @@
+# 🔐 Ethical Hacking LLM Fine-Tuning Collection
+
+> **Public collection of Colab-ready notebooks for fine-tuning cybersecurity/ethical hacking LLMs on Google Colab Free Tier (T4 GPU).**
+
+---
+
+## 📦 What's Included
+
+| File | Model | Description |
+|------|-------|-------------|
+| `EthicalHacking_Qwen3-4B_Ultimate_Colab.ipynb` | **Qwen3-4B-Instruct-2507** (🥇 recommended) | Best coding/reasoning scores among sub-10B models with confirmed Unsloth support |
+| `EthicalHacking_Qwen3-8B_Colab.ipynb` | Qwen3-8B-bnb-4bit | Larger capacity, less VRAM headroom on T4 |
+
+---
+
+## 🏆 Why Qwen3-4B-Instruct-2507?
+
+After researching the **latest small models** as of May/June 2026, here's the verdict for T4 16GB:
+
+| Model | 4-bit Size | T4 Fit | Coding Benchmarks | Unsloth Support | Verdict |
+|-------|-----------|--------|------------------|-----------------|---------|
+| **Qwen3-4B-Instruct-2507** 🥇 | **3.3 GB** | ✅✅✅ Excellent | LiveCodeBench 35.1, MultiPL-E 76.8 | ✅ Confirmed | **Use this** |
+| Qwen3-8B | 7.0 GB | ✅✅ Good | Stronger base model | ✅ Confirmed | Viable but tighter |
+| Gemma-4-E2B-it | 7.6 GB | ✅✅ Good | Unverified coding scores | ✅ 4-bit exists | Multimodal option |
+| Gemma-4-E4B-it | 10.2 GB | ⚠️ Tight | — | ✅ 4-bit exists | **Avoid (OOM risk)** |
+| Bonsai (prism-ml) | ~1 GB | ✅✅✅ Excellent | Weak (MMLU 30%) | ❌ Custom arch | **Avoid** |
+| LFM2 (Liquid AI) | ~2.5 GB | ✅✅ Good | **Not for programming** (official disclaimer) | ❌ Unknown | **Avoid** |
+| Qwen3.5 series | — | — | — | ⚠️ Uncertain | Wait for Unsloth |
+
+### Key Datasets Used
+
+| Dataset | Rows | Focus |
+|---------|------|-------|
+| [AlicanKiraz0/Cybersecurity-Dataset-Fenrir-v2.1](https://huggingface.co/datasets/AlicanKiraz0/Cybersecurity-Dataset-Fenrir-v2.1) | 99,870 | Threat analysis, IR, offensive education |
+| [Trendyol/Trendyol-Cybersecurity-Instruction-Tuning-Dataset](https://huggingface.co/datasets/Trendyol/Trendyol-Cybersecurity-Instruction-Tuning-Dataset) | 53,202 | C2 analysis, forensics, 200+ topics |
+
 ---
-tags:
-- ml-intern
+
+## 🚀 Quick Start
+
+1. Open [Google Colab](https://colab.research.google.com)
+2. **Runtime → Change runtime type → GPU (T4)**
+3. Upload the `.ipynb` file from this repo
+4. **Run all cells** — training takes ~1.5–2.5 hours for 1 epoch
+
 ---
 
-# asdf98/ethical-hacking-llm-colab
+## ⚙️ T4 VRAM Optimizations Used
 
-<!-- ml-intern-provenance -->
-## Generated by ML Intern
+- `load_in_4bit=True` + LoRA (r=64)
+- `adamw_8bit` optimizer
+- `use_gradient_checkpointing="unsloth"`
+- `fp16=True` (T4 has no bf16)
+- Batch=2, Accum=4 → effective batch=8
 
-This model repository was generated by [ML Intern](https://github.com/huggingface/ml-intern), an agent for machine learning research and development on the Hugging Face Hub.
+---
 
-- Try ML Intern: https://smolagents-ml-intern.hf.space
-- Source code: https://github.com/huggingface/ml-intern
+## 🛡️ Disclaimer
 
-## Usage
+All datasets are **defensive/educational** (pentesting methodology, threat analysis, incident response). Intended for **ethical hacking education and security research** only.
 
-```python
-from transformers import AutoModelForCausalLM, AutoTokenizer
+---
 
-model_id = "asdf98/ethical-hacking-llm-colab"
-tokenizer = AutoTokenizer.from_pretrained(model_id)
-model = AutoModelForCausalLM.from_pretrained(model_id)
-```
+## 📚 References
 
-For non-causal architectures, replace `AutoModelForCausalLM` with the appropriate `AutoModel` class.
+- [Qwen3-4B-Instruct-2507](https://huggingface.co/Qwen/Qwen3-4B-Instruct-2507)
+- [Unsloth 4-bit](https://huggingface.co/unsloth/Qwen3-4B-Instruct-2507-unsloth-bnb-4bit)
+- [Unsloth Docs](https://unsloth.ai/docs)
+- [TRL SFTTrainer](https://huggingface.co/docs/trl/sft_trainer)
+- [Fenrir Dataset](https://huggingface.co/datasets/AlicanKiraz0/Cybersecurity-Dataset-Fenrir-v2.1)
+- [Trendyol Dataset](https://huggingface.co/datasets/Trendyol/Trendyol-Cybersecurity-Instruction-Tuning-Dataset)