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.

Downloads last month: 11

Safetensors

Model size

7B params

Tensor type

BF16

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Collection including Alibaba-DAMO-Academy/RynnVLA-001-7B-Base

RynnVLA-001

Collection

Using Human Demonstrations to Improve Robot Manipulation • 3 items • Updated Sep 19 • 2