Metadata-Version: 2.4
Name: shadeai
Version: 2.2.0
Summary: Fully automatic censorship removal for language models
Keywords: llm,transformer,abliteration
Author: Assem Sabry
Author-email: Assem Sabry <assem@assem.cloud>
License-Expression: AGPL-3.0-or-later
Classifier: Development Status :: 4 - Beta
Classifier: Environment :: Console
Classifier: Environment :: GPU
Classifier: Intended Audience :: Science/Research
Classifier: License :: OSI Approved :: GNU Affero General Public License v3 or later (AGPLv3+)
Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
Classifier: Programming Language :: Python :: 3
Classifier: Programming Language :: Python :: 3.10
Classifier: Programming Language :: Python :: 3.11
Classifier: Programming Language :: Python :: 3.12
Classifier: Programming Language :: Python :: 3.13
Requires-Dist: accelerate~=1.10
Requires-Dist: bitsandbytes~=0.45
Requires-Dist: click~=8.1
Requires-Dist: datasets~=4.0
Requires-Dist: hf-transfer~=0.1
Requires-Dist: huggingface-hub~=0.34
Requires-Dist: kernels~=0.11
Requires-Dist: optuna~=4.5
Requires-Dist: peft~=0.14
Requires-Dist: fastapi~=0.115
Requires-Dist: psutil~=7.1
Requires-Dist: pydantic-settings~=2.10
Requires-Dist: questionary~=2.1
Requires-Dist: requests~=2.32
Requires-Dist: rich~=14.1
Requires-Dist: torch>=2.0
Requires-Dist: transformers~=4.57
Requires-Dist: uvicorn~=0.34
Requires-Dist: geom-median~=0.1 ; extra == 'research'
Requires-Dist: imageio~=2.37 ; extra == 'research'
Requires-Dist: matplotlib~=3.10 ; extra == 'research'
Requires-Dist: numpy~=2.2 ; extra == 'research'
Requires-Dist: pacmap~=0.8 ; extra == 'research'
Requires-Dist: scikit-learn~=1.7 ; extra == 'research'
Requires-Python: >=3.10
Project-URL: Changelog, https://github.com/AssemSabry/Shade/releases
Project-URL: Documentation, https://github.com/AssemSabry/Shade
Project-URL: Homepage, https://github.com/AssemSabry/Shade
Project-URL: Issues, https://github.com/AssemSabry/Shade/issues
Project-URL: Repository, https://github.com/AssemSabry/Shade.git
Provides-Extra: research
Description-Content-Type: text/markdown

# ShadeAI — Fully Automatic Censorship Removal for Language Models

<p align="center">
  <a href="https://pypi.org/project/shadeai/"><img src="https://img.shields.io/pypi/v/shadeai?style=for-the-badge&logo=pypi&logoColor=white&label=PyPI&color=3775A9" alt="PyPI"></a>
  <a href="https://pypi.org/project/shadeai/"><img src="https://img.shields.io/pypi/pyversions/shadeai?style=for-the-badge&logo=python&logoColor=white" alt="Python"></a>
  <a href="https://github.com/AssemSabry/Shade"><img src="https://img.shields.io/badge/GitHub-Repository-181717?style=for-the-badge&logo=github&logoColor=white" alt="GitHub"></a>
  <img src="https://img.shields.io/badge/License-AGPL--3.0-orange?style=for-the-badge" alt="License">
</p>

---

**ShadeAI** is a Python framework that removes artificial censorship and safety filters from Large Language Models (LLMs) using advanced **Abliteration** techniques. It provides both a CLI and a full Python API, allowing you to integrate model liberation directly into your scripts, notebooks, and applications.

```bash
pip install shadeai
```

---

## Table of Contents

- [Installation](#-installation)
- [Quick Start](#-quick-start)
- [Hugging Face Authentication](#-hugging-face-authentication)
- [Model Selection](#-model-selection)
- [Running Abliteration](#-running-abliteration-censorship-removal)
- [Saving the Modified Model](#-saving-the-modified-model)
- [Web Chat Interface](#-web-chat-interface)
- [GGUF Export](#-gguf-export)
- [Ollama Integration](#-ollama-integration)
- [System Diagnostics](#-system-diagnostics)
- [Supported Architectures](#-supported-model-architectures)
- [CLI Reference](#-cli-command-reference)
- [Developer](#-developer)
- [Citation](#-citation)
- [License](#%EF%B8%8F-license)

---

## 📦 Installation

### From PyPI (Recommended)
```bash
pip install shadeai
```

### With Research Extras (plotting, clustering, visualization)
```bash
pip install shadeai[research]
```

### From Source
```bash
git clone https://github.com/AssemSabry/Shade.git
cd Shade
pip install -e .
```

---

## ⚡ Quick Start

The fastest way to remove censorship from any model — two lines of code:

```python
import shade

# Run the fully automatic optimization process via CLI
# This will prompt you to select a model interactively
shade.run_optimization()
```

Or from the terminal:
```bash
shade Qwen/Qwen2.5-1.5B-Instruct
```

---

## 🔑 Hugging Face Authentication

Many models on Hugging Face require authentication (gated models like LLaMA, Gemma, etc.). ShadeAI provides multiple ways to authenticate:

### Option 1: Using ShadeAI API (Recommended)
```python
import shade

# Login with your Hugging Face API token
# Get your token from: https://huggingface.co/settings/tokens
shade.login(token="hf_your_token_here")
```

### Option 2: Using the CLI
```bash
shade hf login
```
This will securely prompt you for your token (input is hidden).

### Option 3: Environment Variable
```bash
# Windows
set HF_TOKEN=hf_your_token_here

# Linux/Mac
export HF_TOKEN=hf_your_token_here
```

> **Note:** Your token is stored securely by the `huggingface_hub` library and is never logged or printed.

---

## 📂 Model Selection

ShadeAI can work with models from Hugging Face Hub or models saved locally on your disk.

### Loading a Model from Hugging Face
```python
from shade.config import Settings, QuantizationMethod
from shade.model import Model

# Load any HuggingFace model by its ID
settings = Settings(
    model="Qwen/Qwen2.5-1.5B-Instruct",
    device_map="auto",  # Automatically use GPU if available
)
model = Model(settings)
print(f"Model loaded: {settings.model}")
```

### Loading a Local Model
```python
from shade.config import Settings
from shade.model import Model

# Point to a local directory containing the model files
settings = Settings(
    model=r"D:\Models\My-Local-Model",
    device_map="auto",
)
model = Model(settings)
```

### Loading with 4-bit Quantization (Low VRAM)
```python
from shade.config import Settings, QuantizationMethod
from shade.model import Model

# Use 4-bit quantization to fit large models in limited VRAM
settings = Settings(
    model="Qwen/Qwen2.5-7B-Instruct",
    quantization=QuantizationMethod.BNB_4BIT,
    device_map="auto",
)
model = Model(settings)
```

### Downloading a Model
```python
import shade

# Download a model from Hugging Face to local cache
shade.download("Qwen/Qwen2.5-1.5B-Instruct")
```

---

## 🧠 Running Abliteration (Censorship Removal)

This is the **core feature** of ShadeAI. The abliteration process:
1. Loads harmless and harmful prompt datasets
2. Computes the model's internal "refusal direction"
3. Uses Optuna TPE optimizer to find the best parameters
4. Applies mathematical projection to remove censorship while preserving intelligence

### Method 1: Fully Automatic (Recommended)
```python
import shade

# This starts the complete optimization pipeline:
# - Interactive model selection (if not specified)
# - Automatic refusal direction calculation
# - Multi-trial optimization with Optuna
# - Saves the best result automatically
shade.run_optimization()
```

### Method 2: Via CLI with a Specific Model
```bash
# Run abliteration on a specific model
shade Qwen/Qwen2.5-1.5B-Instruct

# With 4-bit quantization for large models
shade Qwen/Qwen2.5-7B-Instruct --quantization bnb_4bit
```

### Method 3: Programmatic Control
```python
from shade.config import Settings, QuantizationMethod
from shade.model import Model
from shade.evaluator import Evaluator

# Step 1: Configure
settings = Settings(
    model="Qwen/Qwen2.5-1.5B-Instruct",
    quantization=QuantizationMethod.NONE,
    device_map="auto",
    n_trials=100,  # Number of optimization trials
)

# Step 2: Load the model
model = Model(settings)

# Step 3: Create evaluator (loads evaluation datasets)
evaluator = Evaluator(settings, model)
print(f"Baseline refusals: {evaluator.base_refusals}/{len(evaluator.bad_prompts)}")

# Step 4: The optimization loop is handled by run_optimization()
# For fine-grained control, see the source code of shade.main
```

---

## 💾 Saving the Modified Model

After abliteration, you can save the uncensored model for reuse:

```python
from shade.config import Settings
from shade.model import Model

settings = Settings(model="Qwen/Qwen2.5-1.5B-Instruct", device_map="auto")
model = Model(settings)

# ... (after abliteration has been performed) ...

# Merge LoRA adapters into the base model
merged_model = model.get_merged_model()

# Save to a local directory
save_path = "./Qwen-1.5B-Uncensored"
merged_model.save_pretrained(save_path)
model.tokenizer.save_pretrained(save_path)
print(f"Model saved to: {save_path}")
```

---

## 🌐 Web Chat Interface

ShadeAI includes a built-in web chat UI powered by FastAPI. Launch it to interact with your uncensored models through a modern browser interface.

### Method 1: Python API
```python
from shade.config import Settings
from shade.model import Model
from shade.server import start_server

# Load your local uncensored model
settings = Settings(
    model=r"D:\Models\My-Uncensored-Model",
    device_map="auto",
)
model = Model(settings)

# Start the web server (opens browser automatically)
start_server(model, settings, host="127.0.0.1", port=8000)
```

### Method 2: One-Line Python API
```python
import shade

# Start web chat with a model (interactive selection if no model specified)
shade.serve(model_id="./My-Uncensored-Model", host="127.0.0.1", port=8000)
```

### Method 3: CLI
```bash
# Interactive model selection
shade serve

# With a specific model
shade serve ./My-Uncensored-Model

# Custom host and port
shade serve --host 0.0.0.0 --port 9000
```

The web interface features:
- **Dark mode** design
- **Real-time** responses
- **Model info** display
- **Chat history** logging

---

## 📦 GGUF Export

Convert your uncensored HuggingFace model to **GGUF format** for use with llama.cpp, Ollama, LM Studio, and other local runners. ShadeAI handles the entire conversion pipeline automatically.

### Python API
```python
import shade

# Export to GGUF with default Q4_K_M quantization
shade.export_to_gguf(
    model_path="./My-Uncensored-Model",
    quant_type="q4_k_m",  # Default, best balance of size/quality
)
```

### CLI
```bash
# Default export (Q4_K_M quantization)
shade export ./My-Uncensored-Model

# Higher quality export
shade export ./My-Uncensored-Model --quant q5_k_m

# Full precision (no quantization loss)
shade export ./My-Uncensored-Model --quant f16

# Export and register with Ollama in one step
shade export ./My-Uncensored-Model --ollama --ollama-name my-uncensored
```

### Supported Quantization Types

| Type | Size (7B model) | Quality | Use Case |
|------|-----------------|---------|----------|
| `f16` | ~14 GB | 100% | Research, maximum quality |
| `q8_0` | ~7 GB | ~99% | High quality, large RAM |
| `q6_k` | ~5.5 GB | ~97% | Excellent quality |
| `q5_k_m` | ~5 GB | ~95% | Great balance |
| **`q4_k_m`** | **~4 GB** | **~90%** | **Most popular (default)** |
| `q4_k_s` | ~3.8 GB | ~88% | Slightly smaller |
| `q3_k_m` | ~3 GB | ~80% | Low-end hardware |
| `q2_k` | ~2.5 GB | ~60% | Experimental |

> **How it works:** ShadeAI automatically downloads `llama.cpp` conversion tools on first use, converts your model, and optionally registers it with Ollama — all in a single command.

---

## 🦙 Ollama Integration

Register your uncensored models with [Ollama](https://ollama.com/) for easy local inference:

### From an Existing Model
```bash
shade ollama ./My-Uncensored-Model --name my-uncensored
```

### After GGUF Export
```bash
shade export ./My-Uncensored-Model --ollama --ollama-name my-ai

# Now run it with Ollama:
ollama run my-ai
```

### Python API
```python
import shade

shade.export_to_ollama(
    model_path="./My-Uncensored-Model",
    name="my-uncensored"
)
```

---

## 🩺 System Diagnostics

Run a full system check to ensure your environment is ready:

### Python API
```python
import shade

# Check system requirements (Python, RAM, GPU, disk space)
shade.run_doctor()
```

### CLI
```bash
# Diagnose issues
shade doctor

# Diagnose and auto-fix
shade doctor --fix
```

The doctor checks:
- ✅ Python version compatibility
- ✅ Available disk space
- ✅ System RAM
- ✅ GPU/CUDA availability and VRAM
- ✅ Required dependencies

---

## 🏗️ Supported Model Architectures

ShadeAI works with transformer-based models that use the standard HuggingFace `transformers` format. Supported architectures include:

| Architecture | Example Models | Status |
|---|---|---|
| **LLaMA / LLaMA 2 / LLaMA 3** | `meta-llama/Llama-3.1-8B-Instruct` | ✅ Fully Supported |
| **Qwen / Qwen2 / Qwen2.5 / Qwen3** | `Qwen/Qwen2.5-7B-Instruct` | ✅ Fully Supported |
| **Mistral / Mixtral** | `mistralai/Mistral-7B-Instruct-v0.3` | ✅ Fully Supported |
| **Gemma / Gemma 2** | `google/gemma-2-9b-it` | ✅ Fully Supported |
| **Phi-3 / Phi-3.5** | `microsoft/Phi-3.5-mini-instruct` | ✅ Fully Supported |
| **Yi / Yi-1.5** | `01-ai/Yi-1.5-9B-Chat` | ✅ Fully Supported |
| **DeepSeek** | `deepseek-ai/DeepSeek-V2-Lite-Chat` | ✅ Fully Supported |
| **Granite / Granite MoE** | `ibm-granite/granite-3.0-8b-instruct` | ✅ Fully Supported |
| **Other Decoder-Only Transformers** | Any model with `attn.o_proj` + `mlp.down_proj` | ✅ Auto-detected |

> **Dynamic Architecture Support:** ShadeAI includes a fallback discovery mechanism that automatically detects abliterable components in unknown architectures. If your model isn't listed above but follows a standard transformer structure, it will likely work.

> **Not Supported:** Encoder-only models (BERT, RoBERTa), Encoder-Decoder models (T5, BART), and GGUF/GGML files (these must be in HuggingFace format for abliteration).

---

## 📋 CLI Command Reference

| Command | Description |
|---------|-------------|
| `shade <model_id>` | Start the automatic abliteration process |
| `shade serve [model]` | Launch the Web Chat interface |
| `shade export <path>` | Export model to GGUF format |
| `shade ollama <path>` | Register a model with Ollama |
| `shade library` | Manage saved decensored models |
| `shade benchmark <model>` | Run quality tests on a model |
| `shade doctor --fix` | Diagnose and auto-fix system issues |
| `shade download <model_id>` | Download a model from Hugging Face |
| `shade clear --all` | Clean up cache and temporary files |
| `shade version` | Show installed version |
| `shade hf login` | Authenticate with Hugging Face |

---

> [!IMPORTANT]
> **Shade** is a fully original, independent project built from the ground up. It is **NOT** a clone, fork, or derivative of any existing repository. All automation logic, UI design, and optimization workflows were developed specifically for this project.

---

## 👤 Developer

<p align="center">
  <b>Assem Sabry</b>
  <br>
  <i>Lead Developer & AI Researcher</i>
</p>

<p align="center">
  <a href="https://assem.cloud/">
    <img src="https://img.shields.io/badge/Website-assem.cloud-blue?style=for-the-badge&logo=google-chrome&logoColor=white" alt="Website">
  </a>
  <a href="https://www.linkedin.com/in/assem7/">
    <img src="https://img.shields.io/badge/LinkedIn-assem7-0A66C2?style=for-the-badge&logo=linkedin&logoColor=white" alt="LinkedIn">
  </a>
  <a href="https://github.com/AssemSabry/Shade">
    <img src="https://img.shields.io/badge/GitHub-AssemSabry-181717?style=for-the-badge&logo=github&logoColor=white" alt="GitHub">
  </a>
  <a href="https://x.com/assemsabryy">
    <img src="https://img.shields.io/badge/X-@assemsabryy-black?style=for-the-badge&logo=x&logoColor=white" alt="X">
  </a>
</p>

---

## ⚠️ Disclaimer

**Assem Sabry**, the developer of Shade, is **not responsible** for any misuse of this tool. Shade is provided for educational and research purposes only. The primary goal of this project is to allow users to unlock the full potential of open-source language models. Users are expected to interact with de-censored models responsibly.

---

## 📜 Citation

If you use ShadeAI in your research, please cite it:

```bibtex
@misc{shade,
  author = {Sabry, Assem},
  title = {Shade: Fully automatic censorship removal for language models},
  year = {2026},
  publisher = {GitHub},
  journal = {GitHub repository},
  howpublished = {\url{https://github.com/AssemSabry/Shade}}
}
```

---

## ⚖️ License

Copyright &copy; 2026 **Assem Sabry**
Licensed under the **GNU Affero General Public License v3.0**. See the [LICENSE](LICENSE) file for details.
