FlowerVLAPolicy-compatible packaged checkpoint. Source: Stage-2 joint training (text + optional vision LoRA on Florence-2, co-trained with action loss + pixel grounding regularizer). LoRA adapters have been merged into base Linear weights; head dropped. Source ckpt: /usr/itetnas04/data-scratch-01/yuchwang/data/workspace/robot_learning/Lerobot_flower/checkpoints/stage2_task3_all_v4_1_warmaction/20260518-163435_job2017885/final Stage 1 config: {'head_hidden': 256, 'lora_rank': 8, 'lora_alpha': 4, 'lora_dropout': 0.05, 'vision_lora_rank': 0, 'vision_lora_alpha': 4, 'vision_lora_dropout': 0.0, 'vision_lora_stages': []} Stage 2 config: {'lambda_pixel': 0.0, 'freeze_vlm_stack': True, 'proprio_dropout': 0.0}