Instructions to use MK4-Research/LOREA-cyber-v5.4 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use MK4-Research/LOREA-cyber-v5.4 with MLX:

# Make sure mlx-lm is installed
# pip install --upgrade mlx-lm

# Generate text with mlx-lm
from mlx_lm import load, generate

model, tokenizer = load("MK4-Research/LOREA-cyber-v5.4")

prompt = "Write a story about Einstein"
messages = [{"role": "user", "content": prompt}]
prompt = tokenizer.apply_chat_template(
    messages, add_generation_prompt=True
)

text = generate(model, tokenizer, prompt=prompt, verbose=True)

Notebooks
Google Colab
Kaggle
Local Apps Settings
LM Studio

How to use MK4-Research/LOREA-cyber-v5.4 with Pi:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "MK4-Research/LOREA-cyber-v5.4"

Configure the model in Pi

# Install Pi:
npm install -g @mariozechner/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "mlx-lm": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "MK4-Research/LOREA-cyber-v5.4"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

OpenClaw new

How to use MK4-Research/LOREA-cyber-v5.4 with OpenClaw:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "MK4-Research/LOREA-cyber-v5.4"

Configure OpenClaw

# Install OpenClaw:
npm install -g openclaw@latest
# Register the local server and set it as the default model:
openclaw onboard --non-interactive --mode local \
  --auth-choice custom-api-key \
  --custom-base-url http://127.0.0.1:8080/v1 \
  --custom-model-id "MK4-Research/LOREA-cyber-v5.4" \
  --custom-provider-id mlx-lm \
  --custom-compatibility openai \
  --custom-text-input \
  --accept-risk \
  --skip-health

Run OpenClaw

openclaw agent --local --agent main --message "Hello from Hugging Face"

MLX LM

How to use MK4-Research/LOREA-cyber-v5.4 with MLX LM:

Generate or start a chat session

# Install MLX LM
uv tool install mlx-lm
# Interactive chat REPL
mlx_lm.chat --model "MK4-Research/LOREA-cyber-v5.4"

Run an OpenAI-compatible server

# Install MLX LM
uv tool install mlx-lm
# Start the server
mlx_lm.server --model "MK4-Research/LOREA-cyber-v5.4"
# Calling the OpenAI-compatible server with curl
curl -X POST "http://localhost:8000/v1/chat/completions" \
   -H "Content-Type: application/json" \
   --data '{
     "model": "MK4-Research/LOREA-cyber-v5.4",
     "messages": [
       {"role": "user", "content": "Hello"}
     ]
   }'

Hermes Agent

How to use MK4-Research/LOREA-cyber-v5.4 with Hermes Agent:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "MK4-Research/LOREA-cyber-v5.4"

Configure Hermes

# Install Hermes:
curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash
hermes setup
# Point Hermes at the local server:
hermes config set model.provider custom
hermes config set model.base_url http://127.0.0.1:8080/v1
hermes config set model.default MK4-Research/LOREA-cyber-v5.4

Run Hermes

hermes

LOREA-cyber v5.4

Qwythos 9B (Qwen3.5) with the v5.4 LoRA merged in, 4-bit MLX. No adapter needed at inference.

Superseded by LOREA-cyber-v5.5. Use that instead. v5.4 is kept here for reference and reproducibility.

Why it was replaced

v5.4 regressed against its own base on the knowledge benchmarks. Two causes, both found by inspecting the data and the training curve afterwards:

The knowledge MCQs were model-generated and never answer-verified, so some taught the wrong answer. CyberMetric dropped about 5 points.
It overtrained. Loss fell to 0.37 and general ability went with it, including coding.

v5.5 replaces the synthetic MCQs with real answer-keyed data (CyberMetric, WMDP-cyber, MMLU), trains more gently at 2.5e-5, and selects the checkpoint on full metrics rather than a small subset.

Run it

python3 -m mlx_lm.chat --model MK4-Research/LOREA-cyber-v5.4

Scope

Authorized security testing, CTF and reverse-engineering practice, and education. 4-bit 9B, so verify anything important.

Downloads last month: 50

Safetensors

Model size

1B params

Tensor type

BF16

U32

MLX

Hardware compatibility

4-bit

Model tree for MK4-Research/LOREA-cyber-v5.4

Base model

Qwen/Qwen3.5-9B-Base

Finetuned

Qwen/Qwen3.5-9B

Finetuned

empero-ai/Qwythos-9B-Claude-Mythos-5-1M

Quantized

(113)

this model