Instructions to use zero2root/mythos-coder with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use zero2root/mythos-coder 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 zero2root/mythos-coder:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf zero2root/mythos-coder:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf zero2root/mythos-coder:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf zero2root/mythos-coder: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 zero2root/mythos-coder:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf zero2root/mythos-coder: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 zero2root/mythos-coder:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf zero2root/mythos-coder:Q4_K_M

Use Docker

docker model run hf.co/zero2root/mythos-coder:Q4_K_M

LM Studio
Jan
Ollama
How to use zero2root/mythos-coder with Ollama:
```
ollama run hf.co/zero2root/mythos-coder:Q4_K_M
```

Unsloth Studio

How to use zero2root/mythos-coder 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 zero2root/mythos-coder 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 zero2root/mythos-coder to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for zero2root/mythos-coder to start chatting

How to use zero2root/mythos-coder with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf zero2root/mythos-coder:Q4_K_M

Configure the model in Pi

# Install Pi:
npm install -g @mariozechner/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "zero2root/mythos-coder:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use zero2root/mythos-coder with Docker Model Runner:
```
docker model run hf.co/zero2root/mythos-coder:Q4_K_M
```

Lemonade

How to use zero2root/mythos-coder with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull zero2root/mythos-coder:Q4_K_M

Run and chat with the model

lemonade run user.mythos-coder-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use zero2root/mythos-coder with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf zero2root/mythos-coder:Q4_K_M

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 zero2root/mythos-coder:Q4_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use zero2root/mythos-coder with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf zero2root/mythos-coder:Q4_K_M

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 "zero2root/mythos-coder:Q4_K_M" \
  --custom-provider-id llama-cpp \
  --custom-compatibility openai \
  --custom-text-input \
  --accept-risk \
  --skip-health

Run OpenClaw

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

zero2root commited on 12 days ago

Commit

2496b27

verified ·

1 Parent(s): 820f5e0

Sync model card with repo version

Browse files

Files changed (1) hide show

README.md +41 -14

README.md CHANGED Viewed

@@ -2,28 +2,55 @@
 license: mit
 base_model: Qwen/Qwen2.5-Coder-1.5B
 tags:
-- ollama
-- gguf
-- cybersecurity
-- code-generation
 ---
-# mythos-coder
-Fine-tuned Qwen2.5-Coder-1.5B for security code generation in the MYTHOS autonomous security agent. Distributed as a single Ollama-ready GGUF (Q4_K_M, 941MB).
-## Use with Ollama
 ```bash
-curl -L -o mythos-coder-Q4_K_M.gguf https://huggingface.co/zero2root/mythos-coder/resolve/main/mythos-coder-Q4_K_M.gguf
-printf 'FROM ./mythos-coder-Q4_K_M.gguf\nSYSTEM You are MYTHOS, an autonomous offensive security coding agent.\n' > Modelfile
 ollama create mythos-coder -f Modelfile
-ollama run mythos-coder
 ```
-Or set `MYTHOS_GGUF_URL=https://huggingface.co/zero2root/mythos-coder/resolve/main/mythos-coder-Q4_K_M.gguf` and run `scripts/provision_models.sh` from the MYTHOS repo to auto-download and build.
-## Integrity
-- SHA-256: `58e8bbd6c22aac2fbb0daf921b1329d75d72a4a397197b01f19f039363b656a5`
-- Architecture: qwen2, 1.5B params, Q4_K_M, 32768 context

 license: mit
 base_model: Qwen/Qwen2.5-Coder-1.5B
 tags:
+  - cybersecurity
+  - offensive-security
+  - code-generation
+  - qwen2.5
+  - gguf
+  - ollama
 ---
+# mythos-coder — Q4_K_M (GGUF)
+Fine-tuned Qwen2.5-Coder-1.5B that writes Python exploit-detection code for the
+MYTHOS autonomous offensive security platform.
+- **Base model**: Qwen/Qwen2.5-Coder-1.5B
+- **Quantization**: Q4_K_M
+- **Size**: 941 MB (986,048,064 bytes)
+- **Context**: 32,768
+- **SHA-256**: `58e8bbd6c22aac2fbb0daf921b1329d75d72a4a397197b01f19f039363b656a5`
+## System prompt
+```
+You are MYTHOS, an autonomous offensive security AI that writes Python code to
+detect and exploit vulnerabilities. You output ONLY valid Python code.
+No explanations, no thinking tags.
+```
+## Usage with Ollama
 ```bash
 ollama create mythos-coder -f Modelfile
+# Modelfile:
+#   FROM mythos-coder-Q4_K_M.gguf
+#   PARAMETER temperature 0.1
+#   PARAMETER top_p 0.95
+#   PARAMETER num_ctx 2048
 ```
+## Usage in MYTHOS
+The MYTHOS project (`scripts/provision_models.sh`) consumes this file
+automatically via the URL below — set `MYTHOS_GGUF_URL` and the model builds
+itself during setup:
+```
+MYTHOS_GGUF_URL=https://huggingface.co/zero2root/mythos-coder/resolve/main/mythos-coder-Q4_K_M.gguf
+```
+## Ethical use
+For authorized penetration testing and defensive research only. Use only
+against systems you own or are explicitly permitted to test.