---
license: mit
base_model: openvla/openvla-7b
tags:
- robotics
- vla
- openvla
- openvla-oft
- xarm
library_name: transformers
---

# oft_setting1_chunksize25_batch32_30k

**Final checkpoint at 30000 / 30000 training steps.** OpenVLA-OFT checkpoint fine-tuned on real-world XArm data, **setting 1: pick cube and place into plastic cup**.
LoRA weights (rank 32) are already merged into the [openvla/openvla-7b](https://huggingface.co/openvla/openvla-7b) base — this repo is a standalone model.

## Training

- Recipe: OpenVLA-OFT (L1 regression, FiLM, parallel decoding)
- Steps: 30000 (LR 5e-4, decay after 20000), effective batch size 32
- Action chunk: 25, action dim: 7, proprio dim: 6 (BOUNDS_Q99 normalization)
- Inputs: 2 images (3rd-person + wrist) + proprio

## Contents

- Merged model shards (`model-*.safetensors`)
- `action_head--30000_checkpoint.pt`, `proprio_projector--30000_checkpoint.pt`, `vision_backbone--30000_checkpoint.pt` — OFT components needed for deployment
- `dataset_statistics.json` — action/proprio normalization statistics
- `oft_training_config.json` — training configuration snapshot

Use with the [openvla-oft](https://github.com/moojink/openvla-oft) codebase; set XArm constants (chunk 25, action dim 7, proprio dim 6) in `prismatic/vla/constants.py` before deployment.