Open-Pi-Zero
Visit Toolopen-pi-zero is an open-source AI Agents & Automation tool that re-implements the pi0 vision-language-action (VLA) model. It features a MoE-like architecture and uses a pre-trained 3B PaliGemma VLM.
At a glance
Trending
open-pi-zero is an open-source AI Agents & Automation tool that re-implements the pi0 vision-language-action (VLA) model. It features a MoE-like architecture and uses a pre-trained 3B PaliGemma VLM.
Trending
About
open-pi-zero is an open-source re-implementation of the pi0 vision-language-action (VLA) model from Physical Intelligence. This project aims to replicate the model's architecture, which adopts a Mixture-of-Experts (MoE) like design, where each expert has its own parameters and interacts through attention. The model integrates a pre-trained 3B PaliGemma VLM and a new set of action expert parameters (0.315B). It employs block-wise causal masking for efficient attention mechanisms and is trained using flow matching loss on the action chunk output. The repository provides installation instructions, details on testing with pre-trained weights, training specifics, and evaluation results, making it a valuable resource for researchers and developers in the field of VLA models.
Capabilities
Pricing & Plans
Open Source
Free
FAQs
Trending