|
Download README.md from vernerobotics/v0.5-base: direct link, hf CLI and curl.
- Browser
- Download file 7.22 kB
-
https://huggingface.co/vernerobotics/v0.5-base/resolve/main/README.md
- Command line
-
hf download hf://vernerobotics/v0.5-base/README.md
-
curl -L -H "Authorization: Bearer $HF_TOKEN" -o README.md https://huggingface.co/vernerobotics/v0.5-base/resolve/main/README.md
7.22 kB
| license: other | |
| license_name: verne-v0.5-model-license | |
| license_link: LICENSE | |
| pipeline_tag: robotics | |
| language: | |
| - en | |
| tags: | |
| - robotics | |
| - world-action-model | |
| - flow-matching | |
| - manipulation | |
| - verne | |
| extra_gated_heading: Request access to Verne V0.5 | |
| extra_gated_description: >- | |
| Verne reviews each request before it gives access. Verne uses your answers to | |
| manage your license and to contact you about Verne V0.5. The | |
| [Verne Privacy Notice](https://vernerobotics.com/privacy-policy.html) | |
| describes how Verne processes this information. | |
| extra_gated_prompt: >- | |
| The [Verne V0.5 Model License](https://huggingface.co/vernerobotics/v0.5-base/blob/main/LICENSE), | |
| version 1.0, governs the use of Verne V0.5. Read the license before you request | |
| access. When you submit this form, you accept the license. For commercial use, | |
| please contact partnership@vernerobotics.com. We would love to work with you! | |
| The license does not permit use in a country or region under | |
| comprehensive US sanctions, or use by a person on a US restricted-party list. | |
| extra_gated_fields: | |
| First name: text | |
| Last name: text | |
| Email: text | |
| Organization or affiliation: text | |
| Country: country | |
| geo: ip_location | |
| Intended use: | |
| type: select | |
| options: | |
| - Academic research | |
| - Commercial | |
| I have read the license in the LICENSE file and I accept it: checkbox | |
| I accept that the Materials come as is, with no warranty, and that Verne is not liable for damages from their use (Sections 11 and 12): checkbox | |
| I am not in a country or region under comprehensive US sanctions, and I am not on a US restricted-party list: checkbox | |
| extra_gated_button_content: Accept and request access | |
| # Verne V0.5 base | |
| Verne V0.5 is an open-weight world action model for general-purpose robotics, made | |
| by [Verne](https://vernerobotics.com). It learns to predict both future observations | |
| and robot actions. Learning how a scene changes helps the model learn how to act in | |
| it. | |
| This is the pretrained base checkpoint. It is the start point for fine-tuning on | |
| demonstrations from your robot and task. | |
| ## Model details | |
| | | | | |
| |---|---| | |
| | Developed by | Verne Team | | |
| | Model type | World action model (WAM): a video transformer and an action transformer, trained with flow matching | | |
| | Inputs | Current camera frames, memory of past observations, robot state, and a language instruction | | |
| | Output | A chunk of 32 targets at 30 Hz: tool poses, gripper openings, base poses, and progress | | |
| | Instruction language | English | | |
| | Parameters | 8.2 billion in `model.safetensors`. The Wan2.2 VAE and text encoder load separately. | | |
| | Initialized from | [Wan2.2-TI2V-5B](https://huggingface.co/Wan-AI/Wan2.2-TI2V-5B), with a deeper video transformer and a new action transformer, then pretrained by Verne | | |
| | License | [Verne V0.5 Model License](LICENSE) | | |
| ## Checkpoints | |
| | Checkpoint | Description | | |
| |---|---| | |
| | [v0.5-base](https://huggingface.co/vernerobotics/v0.5-base) | Pretrained base. Start here to fine-tune. | | |
| | [v0.5-libero](https://huggingface.co/vernerobotics/v0.5-libero) | Fine-tuned on LIBERO. 99.3% average success. | | |
| | [v0.5-robotwin](https://huggingface.co/vernerobotics/v0.5-robotwin) | Fine-tuned on RoboTwin 2.0. 81.0% clean, 73.4% randomized. | | |
| ## Model | |
| A video transformer and an action transformer share information through masked | |
| attention. During training, they learn together with video and action flow-matching | |
| objectives. The video objective teaches the model how scenes change. The action | |
| objective teaches it the motion that the robot must do. | |
| At runtime, only the action path runs. The model does not generate future video. It | |
| reads the current camera frames, its memory of past observations, the robot state, | |
| and a language instruction. It outputs a chunk of actions at 30 Hz. | |
| ## Training data | |
| We pretrained V0.5 on over 1.7 million demonstrations from four sources: | |
| - Third-party vendors. | |
| - Open-source datasets. | |
| - Verne teleoperation, in the robot's own embodiment and action space. | |
| - Verne handheld grippers. | |
| Before training, we check the recording timing and the motion quality, cut bad | |
| segments, and align each language instruction with the demonstrated behavior. | |
| ## Training procedure | |
| V0.5 trains in three stages. This checkpoint completes stages 1 and 2. | |
| 1. **Robot-video pretraining.** Adapt a video model to robot observations, so it | |
| learns how manipulation changes a scene. | |
| 2. **Joint video and action pretraining.** Train the video and action transformers | |
| together on paired observations and actions. | |
| 3. **Task post-training.** Adapt the policy to one task with fine-tuning, human | |
| corrections, and reinforcement learning. The LIBERO and RoboTwin checkpoints | |
| complete this stage on their benchmarks. | |
| ## Evaluation | |
| For results after task post-training, see the | |
| [LIBERO](https://huggingface.co/vernerobotics/v0.5-libero) and | |
| [RoboTwin 2.0](https://huggingface.co/vernerobotics/v0.5-robotwin) cards. | |
| ## Uses | |
| **Intended uses** | |
| - Fine-tuning on your own demonstrations, for your own robot and task. | |
| - Research on robot learning and world action models. | |
| **Out of scope** | |
| - Deployment without fine-tuning. This checkpoint is not tuned to a specific robot | |
| or task. | |
| - Use on a physical robot without a risk assessment, an emergency stop, and | |
| supervision. | |
| - Any use that the license does not permit. This includes weapons, unlawful | |
| surveillance, and use in sanctioned countries and regions. | |
| ## Limitations | |
| - Performance on a new robot depends on the fine-tuning data. Collect demonstrations | |
| in the robot's own embodiment and action space. | |
| - The model can fail on objects, scenes, and instructions that are far from its | |
| training data. | |
| - This release contains the weights and a minimal inference package. It has no training | |
| or fine-tuning code. To fine-tune V0.5 on your own robot and tasks, sign up for the | |
| Verne fine-tuning platform at [app.vernerobotics.com](https://app.vernerobotics.com). | |
| ## Physical safety | |
| V0.5 outputs actions that move physical machines. A machine that moves can injure | |
| people and damage property. Before you run V0.5 on a robot, assess the risks, install | |
| an emergency stop and speed and force limits, and supervise the robot while it runs. | |
| Section 6 of the license makes you responsible for these measures. | |
| ## License | |
| The [Verne V0.5 Model License](LICENSE) governs the use of these weights. In short: | |
| - For commercial use, please contact partnership@vernerobotics.com. We would love | |
| to work with you! | |
| - Use in a country or region under comprehensive US sanctions, and use by a person on | |
| a US restricted-party list, is not permitted. | |
| - Weapons and unlawful surveillance are not permitted. | |
| This summary is not the license. The LICENSE file controls. See NOTICE for | |
| third-party notices. | |
| ## Citation | |
| ```bibtex | |
| @misc{verne2026v05, | |
| title = {Verne V0.5: An Open-Weight World Action Model to Accelerate Industrial Robot Deployments}, | |
| author = {{Verne Team}}, | |
| year = {2026}, | |
| url = {https://vernerobotics.com} | |
| } | |
| ``` | |
| ## Contact | |
| Fine-tuning platform: [app.vernerobotics.com](https://app.vernerobotics.com). Commercial use: | |
| partnership@vernerobotics.com. Website: [vernerobotics.com](https://vernerobotics.com). | |