onnx-export

Convert JAX/Python ML models to ONNX format via Google Colab notebooks.

8|1|Updated Dec 24, 2025

Search Tags:#PyTorch #ONNX #model conversion #ML deployment #JAX

Ready to run

npx skills add https://github.com/HopeArtOrg/hope-re --skill onnx-export

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: onnx-export
Source: https://github.com/HopeArtOrg/hope-re/tree/main/.gemini/skills/onnx-export
Command: npx skills add https://github.com/HopeArtOrg/hope-re --skill onnx-export

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires jax, jaxlib, jax2onnx, onnx, onnxsim, onnxruntime, transformers, torch, numpy, and includes scripts (resource) components.

What problem does it solve?

This Skill helps users convert JAX/Python machine learning models to ONNX format, enabling them to be used in various environments that require ONNX compatibility.

Core Features & Use Cases

ONNX Conversion: Converts JAX/Python ML models to ONNX format, ensuring compatibility with different deployment environments.
Pipeline Automation: Automates the process of converting models through a series of predefined notebooks in Google Colab.
Use Case: Ideal for data scientists and ML engineers looking to deploy their models in environments that only support ONNX-compatible models.

Quick Start

Run the onnx-export skill to initiate the conversion process of your ML model into ONNX format following the Hope:RE pipeline.

Frequently Asked Questions about onnx-export

High-intent search queries and answers about installing and using this skill.

FAQPage Schema

How do I convert JAX models to ONNX format for deployment?▼

You can convert JAX models to ONNX format by running this skill, which automates weight extraction and ONNX export through predefined Google Colab notebooks using the Hope:RE pipeline.

Can I export PyTorch CLIP models to ONNX using this conversion pipeline?▼

Yes, you can export PyTorch CLIP models to ONNX as this skill requires PyTorch CLIP libraries alongside JAX. The pipeline is designed to handle JAX/Python ML models and convert them into ONNX format for broad deployment compatibility.

What dependencies do I need to set up before converting ML models to ONNX?▼

Before converting ML models to ONNX, you need JAX, jaxlib, jax2onnx, onnx, onnxsim, onnxruntime, transformers, torch, and numpy installed. These libraries provide the necessary environment for weight extraction and model format conversion.

Does this ONNX conversion process support automated execution in Google Colab?▼

Yes, this ONNX conversion process supports automated execution in Google Colab. It utilizes a series of predefined notebooks to automate the entire pipeline, from weight extraction and algorithm training to the final ONNX model export.

Why use jax2onnx for model conversion instead of other ONNX export tools?▼

Using jax2onnx for model conversion directly integrates with JAX and automates the pipeline via Google Colab notebooks. This streamlines weight extraction and ONNX export specifically for JAX/Python ML models, ensuring compatibility with ONNX runtime environments.