Text Generation
GGUF
multilingual
llama.cpp
darkit-2.0
DarkAI Company
programming
reasoning
conversational
Instructions to use darkai-1/darkit-v2.0 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- llama-cpp-python
How to use darkai-1/darkit-v2.0 with llama-cpp-python:
# !pip install llama-cpp-python from llama_cpp import Llama llm = Llama.from_pretrained( repo_id="darkai-1/darkit-v2.0", filename="Q4_K_M.gguf", )
llm.create_chat_completion( messages = [ { "role": "user", "content": "What is the capital of France?" } ] ) - Notebooks
- Google Colab
- Kaggle
- Local Apps
- llama.cpp
How to use darkai-1/darkit-v2.0 with llama.cpp:
Install from brew
brew install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama-server -hf darkai-1/darkit-v2.0:Q4_K_M # Run inference directly in the terminal: llama-cli -hf darkai-1/darkit-v2.0:Q4_K_M
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama-server -hf darkai-1/darkit-v2.0:Q4_K_M # Run inference directly in the terminal: llama-cli -hf darkai-1/darkit-v2.0: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 darkai-1/darkit-v2.0:Q4_K_M # Run inference directly in the terminal: ./llama-cli -hf darkai-1/darkit-v2.0: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 darkai-1/darkit-v2.0:Q4_K_M # Run inference directly in the terminal: ./build/bin/llama-cli -hf darkai-1/darkit-v2.0:Q4_K_M
Use Docker
docker model run hf.co/darkai-1/darkit-v2.0:Q4_K_M
- LM Studio
- Jan
- vLLM
How to use darkai-1/darkit-v2.0 with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "darkai-1/darkit-v2.0" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "darkai-1/darkit-v2.0", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/darkai-1/darkit-v2.0:Q4_K_M
- Ollama
How to use darkai-1/darkit-v2.0 with Ollama:
ollama run hf.co/darkai-1/darkit-v2.0:Q4_K_M
- Unsloth Studio
How to use darkai-1/darkit-v2.0 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 darkai-1/darkit-v2.0 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 darkai-1/darkit-v2.0 to start chatting
Using HuggingFace Spaces for Unsloth
# No setup required # Open https://huggingface.co/spaces/unsloth/studio in your browser # Search for darkai-1/darkit-v2.0 to start chatting
- Pi
How to use darkai-1/darkit-v2.0 with Pi:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama-server -hf darkai-1/darkit-v2.0: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": "darkai-1/darkit-v2.0:Q4_K_M" } ] } } }Run Pi
# Start Pi in your project directory: pi
- Hermes Agent new
How to use darkai-1/darkit-v2.0 with Hermes Agent:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama-server -hf darkai-1/darkit-v2.0: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 darkai-1/darkit-v2.0:Q4_K_M
Run Hermes
hermes
- Docker Model Runner
How to use darkai-1/darkit-v2.0 with Docker Model Runner:
docker model run hf.co/darkai-1/darkit-v2.0:Q4_K_M
- Lemonade
How to use darkai-1/darkit-v2.0 with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull darkai-1/darkit-v2.0:Q4_K_M
Run and chat with the model
lemonade run user.darkit-v2.0-Q4_K_M
List all available models
lemonade list
| # DarkIT-1.5-Pro | |
| ## π§ Overview | |
| DarkIT-1.5-Pro is a high-performance large language model designed for **advanced programming, reasoning, and natural conversation**. | |
| It is optimized to deliver strong results in: | |
| - Code generation and debugging | |
| - Logical reasoning and problem solving | |
| - Multilingual chat (Arabic / English) | |
| - Instruction following in complex tasks | |
| --- | |
| ## βοΈ Key Specifications | |
| - **Model Size:** 4B parameters (optimized inference build) | |
| - **Context Length:** 128K tokens | |
| - **Format:** GGUF (quantized for efficient local deployment) | |
| - **Target Use:** Local AI inference (CPU / GPU) | |
| - **Optimization:** Fine-tuned + merged high-quality training pipeline | |
| --- | |
| ## π Capabilities | |
| ### π» Programming | |
| - Strong performance in Python, JavaScript, C++, Bash | |
| - Code explanation, debugging, and refactoring | |
| - Handles multi-file reasoning and structured code tasks | |
| ### π§ Reasoning | |
| - Multi-step logical thinking | |
| - Algorithm design and optimization | |
| - Analytical problem solving | |
| ### π¬ Conversation | |
| - Natural dialogue flow | |
| - Context-aware responses across long conversations (up to 128K tokens) | |
| - Strong Arabic + English understanding | |
| --- | |
| ## π¦ Context Window | |
| DarkIT-1.5-Pro supports up to: | |
| > πͺ **128,000 tokens context length** | |
| This enables: | |
| - Long conversations without losing context | |
| - Codebase-level reasoning | |
| - Document-level understanding | |
| --- | |
| ## β‘ Performance Notes | |
| - Optimized for speed and memory efficiency | |
| - Stable output generation across long prompts | |
| - Strong balance between creativity and correctness | |
| - Suitable for both chat and developer workflows | |
| --- | |
| ## π Official Links | |
| - π Website: [https://sii3.top](https://sii3.top) | |
| - π¬ Telegram: [https://t.me/sii_3](https://t.me/sii_3) | |
| --- | |
| ## π§ͺ Usage Example | |
| ```bash | |
| ./main -m darkit-1.5-pro.gguf -p "Write a full REST API in FastAPI with authentication" | |
| ``` | |
| --- | |
| ## β οΈ Notes | |
| - Designed for inference-only deployment | |
| - Performance may vary depending on hardware and quantization level | |
| - Best results with structured prompts | |
| --- | |
| ## π’ About DarkAI | |
| DarkAI is an independent AI research initiative focused on building efficient, powerful, and scalable language models for real-world applications. | |
| --- | |
| ## π Model File | |
| - darkit-1.5-pro.gguf |