Instructions to use Rudi193/Kart with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- llama-cpp-python
How to use Rudi193/Kart with llama-cpp-python:
# !pip install llama-cpp-python from llama_cpp import Llama llm = Llama.from_pretrained( repo_id="Rudi193/Kart", filename="kart-unsloth.Q4_K_M.gguf", )
output = llm( "Once upon a time,", max_tokens=512, echo=True ) print(output)
- Notebooks
- Google Colab
- Kaggle
- Local Apps
- llama.cpp
How to use Rudi193/Kart with llama.cpp:
Install from brew
brew install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama-server -hf Rudi193/Kart:Q4_K_M # Run inference directly in the terminal: llama-cli -hf Rudi193/Kart:Q4_K_M
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama-server -hf Rudi193/Kart:Q4_K_M # Run inference directly in the terminal: llama-cli -hf Rudi193/Kart: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 Rudi193/Kart:Q4_K_M # Run inference directly in the terminal: ./llama-cli -hf Rudi193/Kart: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 Rudi193/Kart:Q4_K_M # Run inference directly in the terminal: ./build/bin/llama-cli -hf Rudi193/Kart:Q4_K_M
Use Docker
docker model run hf.co/Rudi193/Kart:Q4_K_M
- LM Studio
- Jan
- Ollama
How to use Rudi193/Kart with Ollama:
ollama run hf.co/Rudi193/Kart:Q4_K_M
- Unsloth Studio new
How to use Rudi193/Kart 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 Rudi193/Kart 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 Rudi193/Kart to start chatting
Using HuggingFace Spaces for Unsloth
# No setup required # Open https://huggingface.co/spaces/unsloth/studio in your browser # Search for Rudi193/Kart to start chatting
- Docker Model Runner
How to use Rudi193/Kart with Docker Model Runner:
docker model run hf.co/Rudi193/Kart:Q4_K_M
- Lemonade
How to use Rudi193/Kart with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull Rudi193/Kart:Q4_K_M
Run and chat with the model
lemonade run user.Kart-Q4_K_M
List all available models
lemonade list
| FROM ./kart-unsloth.Q4_K_M.gguf | |
| TEMPLATE """<|im_start|>system | |
| {{ .System }}<|im_end|> | |
| <|im_start|>user | |
| {{ .Prompt }}<|im_end|> | |
| <|im_start|>assistant | |
| """ | |
| PARAMETER temperature 0.7 | |
| PARAMETER top_p 0.9 | |
| PARAMETER repeat_penalty 1.1 | |
| PARAMETER num_ctx 4096 | |
| SYSTEM """You are Kart (Kartikeya), infrastructure orchestrator for the Die-Namic system. Trust level: ENGINEER. | |
| Your role: Multi-step task execution, file operations, architecture decisions, governance coordination. | |
| Core rules: | |
| - NEVER write code manually — delegate to llm_router.ask() for code generation | |
| - FREE FLEET FIRST — use Cerebras, Gemini, Groq, OCI, Ollama before paid providers | |
| - Cost target: $0.10/month per user via 100% free tier | |
| - Orchestrate workflow, delegate generation, review output, integrate | |
| - Follow Dual Commit governance for all production changes | |
| - All actions logged to knowledge DB | |
| Engineering principles (Rober Rules): | |
| - Avoid critical paths with more than 3 components | |
| - Recognize jig-needs-jig patterns and stop them | |
| - Trust your initial doubts in designs | |
| You are concise, precise, and systematic. You report actions taken, results, and next steps.""" | |