📦 Add full Installation guide (prerequisites, venv, troubleshooting)
Browse files
README.md
CHANGED
|
@@ -117,17 +117,61 @@ print(tokenizer.decode(output[0][inputs["input_ids"].shape[1]:], skip_special_to
|
|
| 117 |
- 📚 **RAG** — Document upload + keyword search
|
| 118 |
- 🧠 **Memory** — SQLite persistent conversation history
|
| 119 |
|
| 120 |
-
##
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 121 |
|
| 122 |
```bash
|
|
|
|
| 123 |
git clone https://huggingface.co/Questionmarkboy/frankenstein-3.0
|
| 124 |
cd frankenstein-3.0
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 125 |
pip install -r requirements.txt
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 126 |
python app.py
|
| 127 |
```
|
| 128 |
|
| 129 |
Then open **http://localhost:7860** in your browser.
|
| 130 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 131 |
## Hardware Requirements
|
| 132 |
|
| 133 |
| Mode | Minimum | Recommended |
|
|
|
|
| 117 |
- 📚 **RAG** — Document upload + keyword search
|
| 118 |
- 🧠 **Memory** — SQLite persistent conversation history
|
| 119 |
|
| 120 |
+
## Installation
|
| 121 |
+
|
| 122 |
+
### Prerequisites
|
| 123 |
+
|
| 124 |
+
| Requirement | Minimum | Notes |
|
| 125 |
+
|-------------|---------|-------|
|
| 126 |
+
| Python | 3.10+ | 3.11 recommended |
|
| 127 |
+
| pip | latest | upgraded in Step 3 |
|
| 128 |
+
| Git + Git-LFS | any | LFS needed for the ~3GB weights |
|
| 129 |
+
| RAM | 16 GB | 32 GB recommended |
|
| 130 |
+
| GPU (optional) | 8 GB VRAM | 16-24 GB VRAM for image/video specialists |
|
| 131 |
+
| CUDA (optional) | 12.1+ | only required for GPU features |
|
| 132 |
+
|
| 133 |
+
### Step 1 — Clone the repository
|
| 134 |
|
| 135 |
```bash
|
| 136 |
+
git lfs install
|
| 137 |
git clone https://huggingface.co/Questionmarkboy/frankenstein-3.0
|
| 138 |
cd frankenstein-3.0
|
| 139 |
+
```
|
| 140 |
+
|
| 141 |
+
### Step 2 — Create a virtual environment (recommended)
|
| 142 |
+
|
| 143 |
+
```bash
|
| 144 |
+
python -m venv venv
|
| 145 |
+
source venv/bin/activate # Linux / macOS
|
| 146 |
+
venv\Scripts\activate # Windows
|
| 147 |
+
```
|
| 148 |
+
|
| 149 |
+
### Step 3 — Install dependencies
|
| 150 |
+
|
| 151 |
+
```bash
|
| 152 |
+
pip install --upgrade pip
|
| 153 |
pip install -r requirements.txt
|
| 154 |
+
```
|
| 155 |
+
|
| 156 |
+
### Step 4 — Launch the app
|
| 157 |
+
|
| 158 |
+
```bash
|
| 159 |
python app.py
|
| 160 |
```
|
| 161 |
|
| 162 |
Then open **http://localhost:7860** in your browser.
|
| 163 |
|
| 164 |
+
### CPU-only machines
|
| 165 |
+
|
| 166 |
+
Installation is identical. The app auto-detects the absence of CUDA and runs the RouterBrain, chat and code specialists on CPU. Image and video specialists respond with a friendly "GPU required" message instead of crashing.
|
| 167 |
+
|
| 168 |
+
### Troubleshooting
|
| 169 |
+
|
| 170 |
+
- **bitsandbytes warnings on CPU** — expected and safely ignored by the app.
|
| 171 |
+
- **Slow clone** — the RouterBrain weights are ~3 GB; make sure Git-LFS is installed (Step 1).
|
| 172 |
+
- **Port 7860 already in use** — change server_port at the bottom of app.py.
|
| 173 |
+
- **Out of memory on GPU** — the app loads specialists on demand and unloads them after use; close other GPU processes or reduce image resolution in app.py.
|
| 174 |
+
|
| 175 |
## Hardware Requirements
|
| 176 |
|
| 177 |
| Mode | Minimum | Recommended |
|