Instructions to use Brunobkr/OFFFELLIA_Huihui-CyberStrike-OffSec-35B-abliterated with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use Brunobkr/OFFFELLIA_Huihui-CyberStrike-OffSec-35B-abliterated 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 Brunobkr/OFFFELLIA_Huihui-CyberStrike-OffSec-35B-abliterated:IQ4_NL_HUIHUI
# Run inference directly in the terminal:
llama cli -hf Brunobkr/OFFFELLIA_Huihui-CyberStrike-OffSec-35B-abliterated:IQ4_NL_HUIHUI

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf Brunobkr/OFFFELLIA_Huihui-CyberStrike-OffSec-35B-abliterated:IQ4_NL_HUIHUI
# Run inference directly in the terminal:
llama cli -hf Brunobkr/OFFFELLIA_Huihui-CyberStrike-OffSec-35B-abliterated:IQ4_NL_HUIHUI

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 Brunobkr/OFFFELLIA_Huihui-CyberStrike-OffSec-35B-abliterated:IQ4_NL_HUIHUI
# Run inference directly in the terminal:
./llama-cli -hf Brunobkr/OFFFELLIA_Huihui-CyberStrike-OffSec-35B-abliterated:IQ4_NL_HUIHUI

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 Brunobkr/OFFFELLIA_Huihui-CyberStrike-OffSec-35B-abliterated:IQ4_NL_HUIHUI
# Run inference directly in the terminal:
./build/bin/llama-cli -hf Brunobkr/OFFFELLIA_Huihui-CyberStrike-OffSec-35B-abliterated:IQ4_NL_HUIHUI

Use Docker

docker model run hf.co/Brunobkr/OFFFELLIA_Huihui-CyberStrike-OffSec-35B-abliterated:IQ4_NL_HUIHUI

LM Studio
Jan

vLLM

How to use Brunobkr/OFFFELLIA_Huihui-CyberStrike-OffSec-35B-abliterated with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Brunobkr/OFFFELLIA_Huihui-CyberStrike-OffSec-35B-abliterated"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Brunobkr/OFFFELLIA_Huihui-CyberStrike-OffSec-35B-abliterated",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Brunobkr/OFFFELLIA_Huihui-CyberStrike-OffSec-35B-abliterated:IQ4_NL_HUIHUI

Ollama

How to use Brunobkr/OFFFELLIA_Huihui-CyberStrike-OffSec-35B-abliterated with Ollama:

ollama run hf.co/Brunobkr/OFFFELLIA_Huihui-CyberStrike-OffSec-35B-abliterated:IQ4_NL_HUIHUI

Unsloth Studio

How to use Brunobkr/OFFFELLIA_Huihui-CyberStrike-OffSec-35B-abliterated 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 Brunobkr/OFFFELLIA_Huihui-CyberStrike-OffSec-35B-abliterated 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 Brunobkr/OFFFELLIA_Huihui-CyberStrike-OffSec-35B-abliterated to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for Brunobkr/OFFFELLIA_Huihui-CyberStrike-OffSec-35B-abliterated to start chatting

How to use Brunobkr/OFFFELLIA_Huihui-CyberStrike-OffSec-35B-abliterated with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Brunobkr/OFFFELLIA_Huihui-CyberStrike-OffSec-35B-abliterated:IQ4_NL_HUIHUI

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": "Brunobkr/OFFFELLIA_Huihui-CyberStrike-OffSec-35B-abliterated:IQ4_NL_HUIHUI"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use Brunobkr/OFFFELLIA_Huihui-CyberStrike-OffSec-35B-abliterated with Docker Model Runner:
```
docker model run hf.co/Brunobkr/OFFFELLIA_Huihui-CyberStrike-OffSec-35B-abliterated:IQ4_NL_HUIHUI
```

Lemonade

How to use Brunobkr/OFFFELLIA_Huihui-CyberStrike-OffSec-35B-abliterated with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Brunobkr/OFFFELLIA_Huihui-CyberStrike-OffSec-35B-abliterated:IQ4_NL_HUIHUI

Run and chat with the model

lemonade run user.OFFFELLIA_Huihui-CyberStrike-OffSec-35B-abliterated-IQ4_NL_HUIHUI

List all available models

lemonade list

Hermes Agent

How to use Brunobkr/OFFFELLIA_Huihui-CyberStrike-OffSec-35B-abliterated with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Brunobkr/OFFFELLIA_Huihui-CyberStrike-OffSec-35B-abliterated:IQ4_NL_HUIHUI

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 Brunobkr/OFFFELLIA_Huihui-CyberStrike-OffSec-35B-abliterated:IQ4_NL_HUIHUI

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use Brunobkr/OFFFELLIA_Huihui-CyberStrike-OffSec-35B-abliterated with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Brunobkr/OFFFELLIA_Huihui-CyberStrike-OffSec-35B-abliterated:IQ4_NL_HUIHUI

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 "Brunobkr/OFFFELLIA_Huihui-CyberStrike-OffSec-35B-abliterated:IQ4_NL_HUIHUI" \
  --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"

ΩFFΣLLIα llama.cpp Helicoidal Quantization

ΩFFΣLLIα — llama.cpp Helicoidal Quantization

Fork de alta performance do llama.cpp ZETAHELICOIDAL ( quants.py )

📌 Visão Geral

O ΩFFΣLLIα é um fork otimizado do ecossistema llama.cpp / GGML, projetado para integrar avanços da Teoria Aritmético-Harmônica de Becker ao pipeline de inferência de Modelos de Linguagem de Grande Porte (LLMs).

🚀 Como Compilar e Usar

1. Compilar o `llama.cpp` Otimizado

cd llama.cpp
mkdir -p build && cd build
cmake .. -DLLAMA_BUILD_EXAMPLES=ON
cmake --build . --config Release -j$(nproc)

2. Converter Modelo Hugging Face para GGUF `Q4_2_H`

python3 llama.cpp/convert_hf_to_gguf.py path/to/hf-model \
  --outtype q4_2_h \
  --outfile models/modelo-q4_2_h.gguf

3. Quantizar Modelo F16/F32 Existente

./llama.cpp/build/bin/llama-quantize ./models/modelo-f16.gguf ./models/modelo-q4_2_h.gguf Q4_2_H

4. Executar Inferência via CLI

./llama.cpp/build/bin/llama-cli -m ./models/modelo-q4_2_h.gguf -p "ΩFFΣLLIα: Explique a Teoria Helicoidal" -n 256

5. Executar a Aplicação Web & Dashboard

npm run build
npm start

Desenvolvido para alta eficiência em execução local e integração com o ecossistema Hugging Face.

Downloads last month: 686

GGUF

Model size

36B params

Architecture

qwen35moe

Hardware compatibility

4-bit

ΩFFΣLLIα — llama.cpp Helicoidal Quantization

📌 Visão Geral

🚀 Como Compilar e Usar

1. Compilar o llama.cpp Otimizado

2. Converter Modelo Hugging Face para GGUF Q4_2_H

3. Quantizar Modelo F16/F32 Existente

4. Executar Inferência via CLI

5. Executar a Aplicação Web & Dashboard

1. Compilar o `llama.cpp` Otimizado

2. Converter Modelo Hugging Face para GGUF `Q4_2_H`