Instructions to use mralhamadi/RWKV7-Cyber-Pentest with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use mralhamadi/RWKV7-Cyber-Pentest with RWKV:

# No code snippets available yet for this library.

# To use this model, check the repository files and the library's documentation.

# Want to help? PRs adding snippets are welcome at:
# https://github.com/huggingface/huggingface.js

HERMES

How to use mralhamadi/RWKV7-Cyber-Pentest with HERMES:

# No code snippets available yet for this library.

# To use this model, check the repository files and the library's documentation.

# Want to help? PRs adding snippets are welcome at:
# https://github.com/huggingface/huggingface.js

llama-cpp-python

How to use mralhamadi/RWKV7-Cyber-Pentest with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="mralhamadi/RWKV7-Cyber-Pentest",
	filename="gguf/v2/rwkv7-cyber-hermes-v2-Q4_K_M.gguf",
)

llm.create_chat_completion(
	messages = [
		{
			"role": "user",
			"content": "What is the capital of France?"
		}
	]
)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use mralhamadi/RWKV7-Cyber-Pentest with llama.cpp:

Install (macOS, Linux)

curl -LsSf https://llama.app/install.sh | sh
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf mralhamadi/RWKV7-Cyber-Pentest:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf mralhamadi/RWKV7-Cyber-Pentest:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf mralhamadi/RWKV7-Cyber-Pentest:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf mralhamadi/RWKV7-Cyber-Pentest:Q4_K_M

Use pre-built binary

# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases
# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf mralhamadi/RWKV7-Cyber-Pentest:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf mralhamadi/RWKV7-Cyber-Pentest:Q4_K_M

Build from source code

git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf mralhamadi/RWKV7-Cyber-Pentest:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf mralhamadi/RWKV7-Cyber-Pentest:Q4_K_M

Use Docker

docker model run hf.co/mralhamadi/RWKV7-Cyber-Pentest:Q4_K_M

LM Studio
Jan

vLLM

How to use mralhamadi/RWKV7-Cyber-Pentest with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "mralhamadi/RWKV7-Cyber-Pentest"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "mralhamadi/RWKV7-Cyber-Pentest",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/mralhamadi/RWKV7-Cyber-Pentest:Q4_K_M

Ollama
How to use mralhamadi/RWKV7-Cyber-Pentest with Ollama:
```
ollama run hf.co/mralhamadi/RWKV7-Cyber-Pentest:Q4_K_M
```

Unsloth Studio

How to use mralhamadi/RWKV7-Cyber-Pentest with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for mralhamadi/RWKV7-Cyber-Pentest to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for mralhamadi/RWKV7-Cyber-Pentest to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for mralhamadi/RWKV7-Cyber-Pentest to start chatting

Atomic Chat new
Docker Model Runner
How to use mralhamadi/RWKV7-Cyber-Pentest with Docker Model Runner:
```
docker model run hf.co/mralhamadi/RWKV7-Cyber-Pentest:Q4_K_M
```

Lemonade

How to use mralhamadi/RWKV7-Cyber-Pentest with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull mralhamadi/RWKV7-Cyber-Pentest:Q4_K_M

Run and chat with the model

lemonade run user.RWKV7-Cyber-Pentest-Q4_K_M

List all available models

lemonade list

You need to agree to share your contact information to access this model

This repository is publicly accessible, but you have to accept the conditions to access its files and content.

RWKV7-Cyber-Hermes (v2) — uncensored RWKV-7 security agent

A 7.2B RWKV-7 (linear-attention RNN; constant-memory, long-context) fine-tuned into an uncensored, Hermes-style tool-calling security agent for pentest, FHE/encryption, web-security, agentic tool use, and coding — built to run locally on an 8 GB-VRAM Kali laptop via llama.cpp + Hermes Agent + the kali-pentest skill.

v2 is the current unified model. It replaces the old agentic/ + fhe/ split — one model for everything. A v3 (128K context + RL-tuned agency) is in training; see MASTERPLAN.md.

Which file

gguf/v2/rwkv7-cyber-hermes-v2-Q4_K_M.gguf   # 4.3 GB — default, fits 8 GB VRAM
gguf/v2/rwkv7-cyber-hermes-v2-Q8_0.gguf     # 7.4 GB — near-lossless
gguf/v2/rwkv7-cyber-hermes-v2-{Q5_K_M,Q6_K,f16}.gguf
pth/rwkv-cyber-hermes-v2-multimodal.pth     # text + VisualRWKV vision (PyTorch; not in GGUF)

Run (llama.cpp)

./llama-server -m gguf/v2/rwkv7-cyber-hermes-v2-Q4_K_M.gguf -ngl 99 -c 8192 \
               --chat-template rwkv-world --host 127.0.0.1 --port 8080

OpenAI-compatible API at :8080. Emits Hermes <tool_call>{...}</tool_call> for tool use; feed results back as <tool_response>. Full deploy (Hermes Agent + kali-pentest + local VLM) in DEPLOY notes.

What changed in v2 (measured)

Built on v1 (rwkv-2, stage-3) → round-1 tool-format SFT → round-2 generalist (LoRA r=128) → on-policy distillation + reference-free SimPO DPO (teacher: qwen3.7-max).

Hallucination ↓ 0.83 → 0.33 (2-judge panel; qwen3.7-max + Gemma-4) — the v1 model's main flaw.
General ability ↑ 0.35 → 0.74; tool-call format 100% in the agentic loop; no looping.
Grounds answers in tool output; abstains instead of fabricating CVEs/findings.
Uncensored by design (authorized pentest/CTF use).

Honest status: strong tool-caller + much more truthful than v1; multi-step autonomous agency and coding are still works in progress (the v3 plan targets these with 128K context, more agent-trajectory data, and RL-in-a-sandbox). Keep a human in the loop. Authorized targets only.

Changelog

v2 (current): unified uncensored agent; replaces agentic/+fhe/ split; +grounding/honesty, +general/coding/tools.
v1: original split — agentic (rwkv-2) + fhe (rwkv-39), F-DPO+TruthRL over 136k rows. (GGUFs removed; source pth/ retained.)

Apache-2.0. Data/scripts/evals included for reproducibility.

Downloads last month: 19

GGUF

Model size

7B params

Architecture

rwkv7

Hardware compatibility

4-bit

5-bit

6-bit

8-bit

16-bit