---
title: nora
canonical_url: "https://www.modelscope.cn/models/declare-lab/nora"
md_url: "https://www.modelscope.cn/models/declare-lab/nora.md"
repository: declare-lab/nora
last_updated: 2025-08-28
pipeline_tag: robotics
tasks:
  - robotics
model_type:
  - qwen2_5_vl
architectures:
  - Qwen2_5_VLForConditionalGeneration
parameters: 3.8B
tensor_type:
  - BF16
library_name:
  - safetensors
  - pytorch
frameworks:
  - pytorch
inference_backends:
  - "deploy_task vlm/text/emb"
  - "lmdeploy 0.9.1"
  - "sglang 0.5.2"
  - "vllm 0.9.2"
downloads: 433
stars: 0
---

# nora

> nora - declare-lab 在 ModelScope 开源的模型。Nora is an open vision-language-action model trained on robot manipulation episodes from the Open X-Embodiment dataset. The model takes language instructions and camera images as input and generates robot actions. Nora…

declare-lab/nora 是 ModelScope 魔搭社区上的 3.8B 参数robotics模型，可用 deploy_task vlm/text/emb、lmdeploy 0.9.1、sglang 0.5.2 部署。

- **Repository**: declare-lab/nora
- **Tasks**: robotics
- **Parameters**: 3.8B
- **Inference backends**: deploy_task vlm/text/emb, lmdeploy 0.9.1, sglang 0.5.2, vllm 0.9.2
- **Downloads**: 433
- **Stars**: 0
- **Last updated**: 2025-08-28

Source: https://www.modelscope.cn/models/declare-lab/nora

---

# Nora

<!-- Provide a quick summary of what the model is/does. -->

Nora is an open vision-language-action model trained on robot manipulation episodes from the [Open X-Embodiment](https://robotics-transformer-x.github.io/) dataset. The model takes language instructions and camera images as input and generates robot actions. Nora is trained directly from Qwen 2.5 VL-3B.
All Nora checkpoints, as well as our [training codebase](https://github.com/declare-lab/nora) are released under an MIT License.




### Model Description

<!-- Provide a longer summary of what this model is. -->



- **Model type:**  Vision-language-action (language, image => robot actions)
- **Language(s) (NLP):** english
- **License:** MIT
- **Finetuned from model :** Qwen 2.5 VL-3B

### Model Sources 

<!-- Provide the basic links for the model. -->

- **Repository:** https://github.com/declare-lab/nora
- **Paper :** https://www.arxiv.org/abs/2504.19854
- **Demo:** https://declare-lab.github.io/nora

## Usage

Nora take a language instruction and a camera image of a robot workspace as input, and predict (normalized) robot actions consisting of 7-DoF end-effector deltas of the form (x, y, z, roll, pitch, yaw, gripper). 
To execute on an actual robot platform, actions need to be un-normalized subject to statistics computed on a per-robot, per-dataset basis. 


## Getting Started For Inference
To get started with loading and running Nora for inference, we provide a lightweight interface that with minimal dependencies.
```bash
git clone https://github.com/declare-lab/nora
cd inference
pip install -r requirements.txt
```
For example, to load Nora for zero-shot instruction following in the BridgeData V2 environments with a WidowX robot:
```python

# Load VLA
from inference.nora import Nora
nora = Nora(device='cuda')

# Get Inputs
image: Image.Image = camera(...)
instruction: str = <INSTRUCTION>
# Predict Action (7-DoF; un-normalize for BridgeData V2)
actions = nora.inference(
    image=image,  # Dummy image
    instruction=instruction,
    unnorm_key='bridge_orig'  # Optional, specify if needed
)
# Execute...
robot.act(action, ...)
```