model-optimization

Name: model-optimization
Availability: InStock
Author: plugin

Optimize machine learning models with quantization, pruning, and ONNX export.

4|1|Updated Nov 18, 2025

Search Tags:#hyperparameter-tuning #onnx #automl #optuna #model-compression #inference-optimization

Ready to run

npx skills add https://github.com/pluginagentmarketplace/custom-plugin-ai-data-scientist --skill model-optimization

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: model-optimization
Source: https://github.com/pluginagentmarketplace/custom-plugin-ai-data-scientist/tree/main/skills/model-optimization
Command: npx skills add https://github.com/pluginagentmarketplace/custom-plugin-ai-data-scientist --skill model-optimization

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires optuna, numpy, scikit-learn, and includes scripts (resource) and references (resource) and assets (resource) components.

What problem does it solve?

Quantization, pruning, AutoML, and hyperparameter tuning are used to improve model performance, reduce size, and enable automated ML workflows.

Core Features & Use Cases

Hyperparameter tuning and AutoML to find optimal models efficiently.
Model compression and performance optimization for faster inference in production.
Use cases include deploying lean, accurate models in constrained environments.

Quick Start

Run the Optuna-based optimizer on your dataset to identify the best hyperparameters for your model.

Frequently Asked Questions about model-optimization

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

FAQPage Schema

How do I reduce machine learning model size and speed up inference for production?▼

Reduce model size and accelerate inference using model compression techniques like quantization, pruning, and distillation. This Skill applies these optimizations alongside ONNX export to deploy lean, accurate models in constrained environments.

What is the best way to run hyperparameter tuning with Optuna and scikit-learn?▼

Run hyperparameter tuning with Optuna and scikit-learn by executing the Optuna-based optimizer on your dataset. This identifies optimal hyperparameters efficiently, improving model accuracy through automated ML workflows.

Can I export optimized models to ONNX format after applying quantization and pruning?▼

Yes, you can export optimized models to ONNX format. The Skill supports ONNX export alongside quantization and pruning to ensure your compressed models achieve faster inference speeds in production.

Does hyperparameter tuning and AutoML work for models deployed in constrained environments?▼

Yes, hyperparameter tuning and AutoML work for constrained environments. The Skill optimizes models for speed, size, and accuracy, enabling the deployment of lean, accurate models where resources are limited.

When should I use model compression techniques instead of just hyperparameter tuning?▼

Use model compression instead of hyperparameter tuning when you need faster inference and smaller model size in production. While tuning improves accuracy, compression via quantization and pruning reduces deployment footprint.

Do I need numpy and scikit-learn to perform model compression and AutoML?▼

Yes, you need numpy and scikit-learn as dependencies to perform model compression and AutoML. These libraries provide the foundational data structures and algorithms required for the optimization process.