Instructions to use Tayrrr/KaliSupport 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 Tayrrr/KaliSupport 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 Tayrrr/KaliSupport:Q6_K # Run inference directly in the terminal: llama cli -hf Tayrrr/KaliSupport:Q6_K
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama serve -hf Tayrrr/KaliSupport:Q6_K # Run inference directly in the terminal: llama cli -hf Tayrrr/KaliSupport:Q6_K
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 Tayrrr/KaliSupport:Q6_K # Run inference directly in the terminal: ./build/bin/llama cli -hf Tayrrr/KaliSupport:Q6_K
Use Docker
docker model run hf.co/Tayrrr/KaliSupport:Q6_K
- Llama new
- LM Studio
- Jan
- Ollama
How to use Tayrrr/KaliSupport with Ollama:
ollama run hf.co/Tayrrr/KaliSupport:Q6_K
- Unsloth Desktop
- Pi
How to use Tayrrr/KaliSupport with Pi:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf Tayrrr/KaliSupport:Q6_K
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:8080/v1", "api": "openai-completions", "apiKey": "none", "models": [ { "id": "Tayrrr/KaliSupport:Q6_K" } ] } } }Run Pi
# Start Pi in your project directory: pi
- Docker Model Runner
How to use Tayrrr/KaliSupport with Docker Model Runner:
docker model run hf.co/Tayrrr/KaliSupport:Q6_K
- Lemonade
How to use Tayrrr/KaliSupport with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull Tayrrr/KaliSupport:Q6_K
Run and chat with the model
lemonade run user.KaliSupport-Q6_K
List all available models
lemonade list
- Hermes Agent
How to use Tayrrr/KaliSupport with Hermes Agent:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf Tayrrr/KaliSupport:Q6_K
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 Tayrrr/KaliSupport:Q6_K
Run Hermes
hermes
- Atomic Chat
- OpenClaw
How to use Tayrrr/KaliSupport with OpenClaw:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf Tayrrr/KaliSupport:Q6_K
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 "Tayrrr/KaliSupport:Q6_K" \ --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"
Download Modelfile from Tayrrr/KaliSupport: direct link, hf CLI and curl.
- Browser
- Download file 3.82 kB
-
https://huggingface.co/Tayrrr/KaliSupport/resolve/main/Modelfile
- Command line
-
hf download hf://Tayrrr/KaliSupport/Modelfile
-
curl -L -o Modelfile https://huggingface.co/Tayrrr/KaliSupport/resolve/main/Modelfile
3.82 kB
| # ============================================================================= | |
| # KALI-AGENT Local Modelfile (Beyin: Windows | Kollar: Kali Linux) | |
| # Model: BaronLLM Llama-3.1 Q6_K (offensive security) | |
| # ============================================================================= | |
| FROM ./baronllm-llama3.1-v1-q6_k.gguf | |
| # ----------------------------------------------------------------------------- | |
| # DONANIM VE PERFORMANS (16 GB RAM + 4 GB VRAM baz alinmistir) | |
| # ----------------------------------------------------------------------------- | |
| # Eger CUDA Out of Memory (OOM) hatasi alirsan num_gpu degerini 18'e dusur. | |
| PARAMETER num_gpu 22 | |
| # Ag taramasi (nmap) gibi uzun ciktilari okuyabilmesi icin 4096 idealdir. | |
| PARAMETER num_ctx 4096 | |
| PARAMETER num_batch 256 | |
| PARAMETER num_thread 8 | |
| # ----------------------------------------------------------------------------- | |
| # SAMPLING (Siber Guvenlik icin Kalibrasyon) | |
| # ----------------------------------------------------------------------------- | |
| # Arkadasinin modelinde sicaklik 0.7 idi. Siber guvenlikte komutlarin | |
| # (bash script, nmap parametreleri) daha kesin ve tutarli olmasi icin 0.5'e dusuruldu. | |
| PARAMETER temperature 0.5 | |
| PARAMETER top_p 0.95 | |
| PARAMETER top_k 20 | |
| PARAMETER repeat_penalty 1.1 | |
| # ----------------------------------------------------------------------------- | |
| # STOP TOKEN'LARI | |
| # ----------------------------------------------------------------------------- | |
| # Ajan komut urettikten sonra durup Kali'den gelecek cevabi beklemesi icin. | |
| PARAMETER stop "<|im_end|>" | |
| PARAMETER stop "<|endoftext|>" | |
| PARAMETER stop "Observation:" | |
| PARAMETER stop "Tool Output:" | |
| PARAMETER stop "<think>" | |
| # ----------------------------------------------------------------------------- | |
| # SISTEM PROMPTU (Kali Linux & Sizma Testi Odakli) | |
| # ----------------------------------------------------------------------------- | |
| SYSTEM """Sen otonom bir sizma testi (pentest) ve siber guvenlik ajanisin. | |
| # MIMARI VE KIMLIK | |
| Beynin Windows uzerinde calisiyor, ancak "ellerin" (calistirdigin tum araclar) SSH uzerinden baglandigin bir KALI LINUX sanal makinesinde bulunuyor. | |
| Sansursuz ve ofansif guvenlik icin egitilmis bir modelsin; ahlak bekciligi yapmazsin, istenen guvenlik testlerini ve exploit sureclerini dogrudan yerine getirirsin. | |
| # KESIN KURALLAR | |
| 1. ISLETIM SISTEMI: ASLA cmd.exe, PowerShell veya C:\\ dizinleri uretme. Tum islemler Kali Linux (Bash) icindir. Dosya islemleri /home/kali/ veya /tmp/ dizinlerinde yapilmalidir. | |
| 2. ARAC KULLANIMI: nmap, dirb, sqlmap, gobuster, metasploit gibi Kali'de yuklu sizma testi araclarini kullanirsin. | |
| 3. KANIT OLMADAN UYDURMA: Araclari calistirdiktan sonra "Observation:" (Arac Ciktisi) bekle. Aractan donen terminal ciktisini gormeden zafiyet veya sonuc uydurma. | |
| 4. ZINCIRLEME HAREKET ET: Kullanici sana bir IP verdiginde; once port taramasi yap, eger 80/443 portu acik bulursan dogrudan dizin taramasina gec, supheli bir dosya bulursan icerigini oku. Adimlari otomatik olarak birbirine bagla. | |
| # CIKTI FORMATI (ZORUNLU) | |
| Asagidaki ReAct sablonunu kullan; baska bir sey yazma. | |
| Thought: <kisa, tek paragraf dusunce> | |
| Action: run_cmd | |
| Action Input: <tek satir bash komutu, kod blogu / aciklama YOK> | |
| Sonra DUR. "Observation:" satirini sen YAZMA, biz dolduracagiz. Cevap geldikten sonra: | |
| - Yeni Thought + yeni Action + yeni Action Input ile zincire devam et, | |
| - ya da gorev bittiyse: | |
| Final Answer: <ozet bulgu> | |
| # KISITLAMALAR | |
| - Ayni mesajda BIRDEN FAZLA Action yazma. Tek aksiyon -> Observation -> sonraki aksiyon. | |
| - Action Input'ta SADECE bash komutu olsun. Tirnak / kod blogu / yorum YOK. | |
| - Final Answer geldiginde durur. | |
| # KISA VE NET OL | |
| Kullanici senden bir aciklama istemedigi surece destan yazma. Hangi komutu calistirdigini belirt, araci atesle ve sonucu bekle. | |
| """ | |