Instructions to use SurendraVB/Mahiru-MoE-CyberSec with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- llama.cpp
How to use SurendraVB/Mahiru-MoE-CyberSec 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 SurendraVB/Mahiru-MoE-CyberSec:Q4_K_M # Run inference directly in the terminal: llama cli -hf SurendraVB/Mahiru-MoE-CyberSec:Q4_K_M
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama serve -hf SurendraVB/Mahiru-MoE-CyberSec:Q4_K_M # Run inference directly in the terminal: llama cli -hf SurendraVB/Mahiru-MoE-CyberSec:Q4_K_M
Build from source code
git clone https://github.com/ggml-org/llama.cpp.git cd llama.cpp cmake -B build cmake --build build -j --target llama-app # Start a local OpenAI-compatible server with a web UI: ./build/bin/llama serve -hf SurendraVB/Mahiru-MoE-CyberSec:Q4_K_M # Run inference directly in the terminal: ./build/bin/llama cli -hf SurendraVB/Mahiru-MoE-CyberSec:Q4_K_M
Use Docker
docker model run hf.co/SurendraVB/Mahiru-MoE-CyberSec:Q4_K_M
- Llama new
- LM Studio
- Jan
- Ollama
How to use SurendraVB/Mahiru-MoE-CyberSec with Ollama:
ollama run hf.co/SurendraVB/Mahiru-MoE-CyberSec:Q4_K_M
- Unsloth Desktop
- Pi
How to use SurendraVB/Mahiru-MoE-CyberSec with Pi:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf SurendraVB/Mahiru-MoE-CyberSec:Q4_K_M
Configure the model in Pi
# Install Pi: npm install -g @earendil-works/pi-coding-agent # Add to ~/.pi/agent/models.json: { "providers": { "llama-cpp": { "baseUrl": "http://localhost:9931/v1", "api": "openai-completions", "apiKey": "none", "models": [ { "id": "SurendraVB/Mahiru-MoE-CyberSec:Q4_K_M" } ] } } }Run Pi
# Start Pi in your project directory: pi
- Docker Model Runner
How to use SurendraVB/Mahiru-MoE-CyberSec with Docker Model Runner:
docker model run hf.co/SurendraVB/Mahiru-MoE-CyberSec:Q4_K_M
- Lemonade
How to use SurendraVB/Mahiru-MoE-CyberSec with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull SurendraVB/Mahiru-MoE-CyberSec:Q4_K_M
Run and chat with the model
lemonade run user.Mahiru-MoE-CyberSec-Q4_K_M
List all available models
lemonade list
- Hermes Agent
How to use SurendraVB/Mahiru-MoE-CyberSec with Hermes Agent:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf SurendraVB/Mahiru-MoE-CyberSec: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://127.0.0.1:9931/v1 hermes config set model.default SurendraVB/Mahiru-MoE-CyberSec:Q4_K_M
Run Hermes
hermes
- Atomic Chat
- OpenClaw
How to use SurendraVB/Mahiru-MoE-CyberSec with OpenClaw:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf SurendraVB/Mahiru-MoE-CyberSec: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://127.0.0.1:9931/v1 \ --custom-model-id "SurendraVB/Mahiru-MoE-CyberSec: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"
Commit History
-
Upload intel_openvino_moe_failures.md
Verified signatureb0e8ac3
-
Update README.md
Verified signature4ba639d -
Upload mahiru_moe.gguf with huggingface_hub
Verified signature3a35ad2 -
Upload chat_template.jinja with huggingface_hub
Verified signature3171af5 -
Upload special_tokens_map.json with huggingface_hub
Verified signature61abde3 -
Upload tokenizer_config.json with huggingface_hub
Verified signature0e49019 -
Upload tokenizer.json with huggingface_hub
Verified signatureab779b4 -
Upload config.json with huggingface_hub
Verified signature3c8afc9 -
Upload mahiru_moe_q8_0.gguf with huggingface_hub
Verified signature36ea073 -
Upload mahiru_moe_q4_k_m.gguf
Verified signaturead2e056 -
Delete mahiru_moe_q8_0.gguf
Verified signature5f7f755 -
Delete mahiru_moe_q4_k_m.gguf
Verified signature093edc3 -
Upload mahiru_moe_q4_k_m.gguf with huggingface_hub
Verified signature5f52a6a -
Upload mahiru_moe_q8_0.gguf with huggingface_hub
Verified signature4205e06 -
Upload .gitattributes with huggingface_hub
Verified signature790247c
-
Upload CUSTOM_CONTRACTS.md with huggingface_hub
Verified signature61e3444 -
Upload HumanEval_benchmark.md with huggingface_hub
Verified signature1c14e99 -
Upload MMLU_benchmark.md with huggingface_hub
Verified signatureec7d0b9 -
Upload agent_benchmark.md with huggingface_hub
Verified signaturea6d4c8c -
Upload cyber_benchmark.md with huggingface_hub
Verified signature3777f44 -
Upload CUSTOM_CONTRACTS.md with huggingface_hub
Verified signaturefe8dd60 -
Upload ARCHITECTURE.md with huggingface_hub
Verified signaturefe82757 -
Upload README.md with huggingface_hub
Verified signature91d6b2b -
initial commit
Verified signaturec47fd3b