Upload README.md with huggingface_hub

README.md

@@ -0,0 +1,80 @@
+---
+library_name: mlx
+license: apache-2.0
+base_model: mlx-community/gemma-4-e2b-it-4bit
+tags:
+- mlx
+- lora
+- gemma4
+- pentesting
+- kali-linux
+- nethunter
+- security
+language:
+- en
+pipeline_tag: text-generation
+---
+
+# Gemma 4 E2B-IT — Kali NetHunter Pentest LoRA
+
+LoRA adapters for [mlx-community/gemma-4-e2b-it-4bit](https://huggingface.co/mlx-community/gemma-4-e2b-it-4bit) finetuned on Kali NetHunter penetration testing data for use on a rooted OnePlus 8T.
+
+## What it does
+
+Teaches the model to respond like an expert pentester with structured output:
+- Nmap scan analysis with risk-rated tables
+- Attack plans with exact bash commands
+- WiFi, SMB, DNS enumeration workflows
+- NetHunter + Termux specific tooling
+
+## Training
+
+- **Base model:** `mlx-community/gemma-4-e2b-it-4bit` (Gemma 4 E2B instruction-tuned, 4-bit quantized)
+- **Method:** LoRA (rank 8, alpha 16, 4 layers)
+- **Data:** 18 pentest examples + 2 validation (chat format with system/user/assistant)
+- **Iterations:** 200 @ batch_size=1, lr=1e-5, grad_checkpoint=true
+- **Hardware:** Apple Silicon 8GB (peak memory: 4.8GB)
+- **Final loss:** Train 0.54, Val 2.13
+
+## Usage
+
+> **Note:** Requires mlx-lm installed from the `gemma4` branch (Gemma 4 support not yet in the stable release).
+
+```bash
+# Install mlx-lm with Gemma 4 support
+git clone https://github.com/ml-explore/mlx-lm.git
+cd mlx-lm && git checkout gemma4
+pip install -e .
+```
+
+```python
+from mlx_lm import load, generate
+
+model, tokenizer = load(
+    "mlx-community/gemma-4-e2b-it-4bit",
+    adapter_path="0xsoftboi/gemma-4-e2b-it-kali-nethunter-lora"
+)
+
+messages = [
+    {"role": "system", "content": "Expert pentester on rooted OnePlus 8T with Kali NetHunter + Termux. Give exact commands. Be concise."},
+    {"role": "user", "content": "Generate an attack plan for SMB"}
+]
+
+prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
+response = generate(model, tokenizer, prompt=prompt, max_tokens=300)
+print(response)
+```
+
+## Bug fix required
+
+The upstream `gemma4` branch has a bug in `mlx_lm/models/gemma4.py` that prevents loading multimodal Gemma 4 checkpoints. The weight sanitizer adds a double `model.` prefix. Fix: [0xSoftBoi/mlx-lm@gemma4-fixes](https://github.com/0xSoftBoi/mlx-lm/tree/gemma4-fixes)
+
+## Limitations
+
+- Small training set (18 examples) — good at matching the pentest output style but may hallucinate specific CVEs or command flags
+- E2B is a 2B-parameter model — works great on-device but less capable than larger variants
+- Some safety guardrails from the base instruct model remain active
+
+## License
+
+Apache 2.0 (same as base model)