# so101 FlowerVLA Stage-2 checkpoint

Vanilla `FlowerVLAPolicy`-compatible. Load with

```python
from src.flower.policy import FlowerVLAPolicy
policy = FlowerVLAPolicy.from_pretrained("<this dir>", device="cuda")
```

## How it was trained
1. Stage 1: Florence-2-base + text-encoder LoRA (rank 8 alpha 4 dropout 0.2) trained
   to predict the target bowl's pixel coordinates given (image, prompt). Within-condition
   val split. slot_acc ~0.96.
2. Stage 2: load Stage 1 ckpt, attach DiT action head, joint train with
   total = action_loss + 0.1 * pixel_loss (Stage 1 head kept as regularizer).
   Florence base frozen, LoRA adapters fine-tuned, DiT trained from scratch.
3. Package: text LoRA merged into Florence base weights so this checkpoint
   loads into vanilla FlowerVLAPolicy without LoRA support.