> ## Documentation Index
> Fetch the complete documentation index at: https://docs.cyberwave.com/llms.txt
> Use this file to discover all available pages before exploring further.

# OpenVLA-OFT Training

> Fine-tune OpenVLA-OFT models using the openvla (RLDS) dataset format

## Overview

OpenVLA-OFT is a LoRA-based fine-tuning framework for Vision-Language-Action models built on the `openvla-7b` base. Cyberwave supports training and deploying OpenVLA-OFT models on your custom datasets using the `openvla` (RLDS) dataset format.

<Info>
  OpenVLA-OFT uses the **openvla (RLDS) dataset format** for training, which differs from the LeRobot v3 format used by SmolVLA. The platform handles format selection automatically based on the model type.
</Info>

***

## Model Selection

When creating an ML model on Cyberwave, select **OpenVLA-OFT** as the model type to automatically route training and inference jobs to a cloud node with the `openvla-oft-policy` profile.

***

## Training

Training jobs are dispatched to a Cyberwave Cloud Node. The cloud node:

1. Downloads the dataset in RLDS format (`format=openvla`)
2. Downloads the base model weights (`openvla/openvla-7b` by default)
3. Runs the LoRA fine-tuning loop, routing all metrics to the Cyberwave dashboard
4. Compresses and uploads the final checkpoint to the platform

### Key training parameters

| Parameter             | Description                                                            | Default |
| --------------------- | ---------------------------------------------------------------------- | ------- |
| `max_steps`           | Number of training gradient steps                                      | 50 000  |
| `batch_size`          | Per-GPU batch size (auto-scaled to camera count if omitted)            | auto    |
| `lora_rank`           | LoRA adapter rank                                                      | 32      |
| `use_l1_regression`   | Use L1 regression action head instead of cross-entropy                 | `true`  |
| `use_proprio`         | Include proprioceptive state in observations                           | `true`  |
| `num_images_in_input` | Number of camera feeds used during training (auto-detected if omitted) | auto    |

***

## Inference

Trained checkpoints can be deployed directly from the Cyberwave platform. The cloud node loads the fine-tuned LoRA weights and streams predictions back to your robot via MQTT.

***

## Dataset format

OpenVLA-OFT requires datasets in the RLDS (TensorFlow Datasets) format. When you upload a dataset through the Cyberwave platform, it is automatically converted and made available for download in the `openvla` format.