Reverting until I can test on my bigger machine

README.md

@@ -38,20 +38,27 @@ Due to the size of the combined weights (~48 GB), LFG-1 requires substantial uni
 
 ## Install
 
-Install `mlx-vlm`:
+Install `mlx-vlm`, then clone and install the LFG wrapper code:
 
 ```bash
 pip install mlx-vlm
+git clone https://github.com/codemadeio/LFG-1.git
+cd LFG-1
+pip install -e 
 ```
 
 ## Usage
 
-LFG-1 loads natively in mlx-vlm as a Gemma 4 model.
+LFG-1 is designed as a drop-in model type for `mlx-vlm`. Once the `lfg` module is registered, it can be loaded like any other Hugging Face model.
 
 ```python
+
+from lfg import register
+register()
+
 from mlx_vlm import load, generate
-model, processor = load("glenn2/LFG-1")
 
+model, processor = load("glenn2/LFG-1")
 
 response = generate(
     model, processor,