pi05-libero-int8

Community

8-bit quantized VLA policy for Franka Panda, tuned on LIBERO.

Authorbensonlee5
Version1.0.0
Installs0

System Documentation

What problem does it solve?

This Skill provides a compact, 8-bit quantized Vision-Language-Action policy for the Franka Panda robot, fine-tuned on the LIBERO benchmark, enabling high-performance manipulation in simulated environments.

Core Features & Use Cases

  • 8-bit Quantization: Utilizes LLM.int8 for efficient GPU deployment on 8 GB GPUs.
  • Franka Panda Support: Native training embodiment for Franka Panda with 7-DOF arm.
  • LIBERO Benchmark: Fine-tuned on LIBERO, covering spatial, object, goal, and long tasks.
  • Use Case: Automate complex robot tasks like picking up bowls, placing cups, or opening drawers in simulated tabletop and kitchen environments.

Quick Start

Run the following command to install the skill:

uv run openral skill install OpenRAL/rskill-pi05-libero-int8 --non-commercial --yes

Dependency Matrix

Required Modules

openralopenral_rskilllerobot/pi05_libero_finetuned_v044

Components

scriptsreferences

💻 Claude Code Installation

Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.

Please help me install this Skill:
Name: pi05-libero-int8
Download link: https://github.com/bensonlee5/openral/archive/main.zip#pi05-libero-int8

Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
View Source Repository

Agent Skills Search Helper

Install a tiny helper to your Agent, search and equip skill from 620,000+ vetted skills library on demand.