# Decisive Dory — LoRA adapter

This rank-8 LoRA adapter uses the tensor format supported by the included `dory_lora.py` loader. It is not in PEFT format.
The BF16, NVFP4, and GGUF model files already include the adaptation. Use this standalone adapter only with the original NVIDIA BF16 weights.

To load the adapter with the supplied Python module, use the original BF16 snapshot:

```python
from pathlib import Path
from dory_lora import Dory

model = Dory.load(Path("/path/to/original-bf16"), rank=8, alpha=16, loops=2)
model.load_adapter(Path("adapter.safetensors"))
model.eval()
```