---
title: RynnVLA-001-7B-Base
canonical_url: "https://www.modelscope.cn/models/DAMO_Academy/RynnVLA-001-7B-Base"
md_url: "https://www.modelscope.cn/models/DAMO_Academy/RynnVLA-001-7B-Base.md"
repository: DAMO_Academy/RynnVLA-001-7B-Base
last_updated: 2025-11-26
license: apache-2.0
parameters: 7.0B
tensor_type:
  - BF16
library_name:
  - safetensors
  - pytorch
frameworks:
  - Pytorch
downloads: 210
stars: 1
---

# RynnVLA-001-7B-Base

> RynnVLA-001-7B-Base - DAMO_Academy 在 ModelScope 开源的模型。Alibaba DAMO Academy - RynnVLA-001-7B-Base

DAMO_Academy/RynnVLA-001-7B-Base 是 ModelScope 魔搭社区上的 7.0B 参数机器学习模型，采用 apache-2.0 许可。

- **Repository**: DAMO_Academy/RynnVLA-001-7B-Base
- **License**: apache-2.0
- **Parameters**: 7.0B
- **Downloads**: 210
- **Stars**: 1
- **Last updated**: 2025-11-26

Source: https://www.modelscope.cn/models/DAMO_Academy/RynnVLA-001-7B-Base

---

### Alibaba DAMO Academy - RynnVLA-001-7B-Base

Github Repo: https://github.com/alibaba-damo-academy/RynnVLA-001

🔥 We release RynnVLA-001-7B-Base (Stage 1: Ego-Centric Video Generative Pretraining), which is pretrained on large-scale ego-centric manipulation videos.

## 🌟 Overview of RynnVLA-001

RynnVLA-001 is a VLA model based on pretrained video generation model. The key insight is to implicitly transfer manipulation skills learned from human demonstrations in ego-centric videos to the manipulation of robot arms.


![image/png](https://cdn-uploads.huggingface.co/production/uploads/629c95b7a5d6f5fe10e6ed45/zbmq3CClK__Q87zqfba26.png)