Update README.md
Browse files
README.md
CHANGED
|
@@ -228,21 +228,57 @@ Lance is a lightweight native unified multimodal model that supports **image and
|
|
| 228 |
</table>
|
| 229 |
</div>
|
| 230 |
|
| 231 |
-
##
|
| 232 |
|
| 233 |
-
|
| 234 |
|
| 235 |
-
|
| 236 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
| 237 |
|
| 238 |
-
### Installation Steps
|
| 239 |
```bash
|
| 240 |
bash ./setup_env.sh
|
|
|
|
| 241 |
```
|
| 242 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 243 |
### Download Model Weights
|
| 244 |
|
| 245 |
-
Please download all
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 246 |
|
| 247 |
## 📚 Usage
|
| 248 |
|
|
|
|
| 228 |
</table>
|
| 229 |
</div>
|
| 230 |
|
| 231 |
+
### Installation Steps
|
| 232 |
|
| 233 |
+
First, clone the repository:
|
| 234 |
|
| 235 |
+
```bash
|
| 236 |
+
git clone https://github.com/bytedance-seed/Lance.git
|
| 237 |
+
cd Lance
|
| 238 |
+
```
|
| 239 |
+
|
| 240 |
+
#### Option 1: Automated Setup
|
| 241 |
|
|
|
|
| 242 |
```bash
|
| 243 |
bash ./setup_env.sh
|
| 244 |
+
pip install flash-attn==2.8.3 --no-build-isolation
|
| 245 |
```
|
| 246 |
|
| 247 |
+
#### Option 2: Manual Setup (Recommended)
|
| 248 |
+
```bash
|
| 249 |
+
conda create -n Lance python=3.11
|
| 250 |
+
pip3 install torch==2.5.1+cu124 torchvision==0.20.1+cu124 torchaudio==2.5.1+cu124 --index-url https://download.pytorch.org/whl/cu124
|
| 251 |
+
pip install -r requirements_full.txt
|
| 252 |
+
pip install flash-attn==2.8.3 --no-build-isolation
|
| 253 |
+
```
|
| 254 |
+
|
| 255 |
+
> **Note:** If installing `flash-attn` from source fails, you can install the prebuilt wheel instead:
|
| 256 |
+
>
|
| 257 |
+
> ```bash
|
| 258 |
+
> pip install --no-cache-dir --no-deps --force-reinstall \
|
| 259 |
+
> "https://github.com/Dao-AILab/flash-attention/releases/download/v2.8.3/flash_attn-2.8.3%2Bcu12torch2.5cxx11abiFALSE-cp311-cp311-linux_x86_64.whl"
|
| 260 |
+
> ```
|
| 261 |
+
|
| 262 |
+
|
| 263 |
### Download Model Weights
|
| 264 |
|
| 265 |
+
Please download all necessary model checkpoints from [Lance-3B on Hugging Face](https://huggingface.co/bytedance-research/Lance) and place them in the `downloads/` directory.
|
| 266 |
+
|
| 267 |
+
```bash
|
| 268 |
+
from huggingface_hub import snapshot_download
|
| 269 |
+
|
| 270 |
+
save_dir = "./downloads/"
|
| 271 |
+
repo_id = "bytedance-research/Lance"
|
| 272 |
+
cache_dir = save_dir + "/cache"
|
| 273 |
+
|
| 274 |
+
snapshot_download(cache_dir=cache_dir,
|
| 275 |
+
local_dir=save_dir,
|
| 276 |
+
repo_id=repo_id,
|
| 277 |
+
local_dir_use_symlinks=False,
|
| 278 |
+
resume_download=True,
|
| 279 |
+
allow_patterns=["*.json", "*.safetensors", "*.bin", "*.py", "*.md", "*.txt","*.pth",],
|
| 280 |
+
)
|
| 281 |
+
```
|
| 282 |
|
| 283 |
## 📚 Usage
|
| 284 |
|