skills.rest
doanchienthangdev
doanchienthangdevCOMMUNITY
Explore all skills by this author →
GitHub

ml-frameworks

Provides PyTorch, TensorFlow, scikit-learn and Hugging Face Transformers coding examples and best practices for ML pipelines.

4|1|Updated Dec 30, 2025
Search Tags:#mlops#machine learning#pytorch#tensorflow#scikit-learn#hugging face
One-click install
npx skills add https://github.com/doanchienthangdev/omgkit --skill ml-frameworks
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: ml-frameworks
Source: https://github.com/doanchienthangdev/omgkit/tree/main/plugin/skills/ml-systems/ml-frameworks
Command: npx skills add https://github.com/doanchienthangdev/omgkit --skill ml-frameworks

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill provides best practices and code examples for using popular machine learning frameworks, helping developers build and train models more effectively.

Core Features & Use Cases

  • Framework Examples: Demonstrates standard patterns for PyTorch, TensorFlow/Keras, and Scikit-learn.
  • Modern Libraries: Includes examples for Hugging Face Transformers.
  • Best Practices: Offers guidance on optimization techniques like mixed precision and learning rate scheduling.
  • Use Case: A data scientist needs to quickly implement a classification model using PyTorch and wants to ensure they are following industry best practices for training and optimization.

Quick Start

Use the ml-frameworks skill to train a model using PyTorch with mixed precision.

Frequently Asked Questions about ml-frameworks

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

FAQPage Schema
What are the best practices for training a PyTorch model with mixed precision?▼

Training models with mixed precision in PyTorch requires applying specific optimization techniques and learning rate scheduling. This Skill provides standard code examples to implement these efficient training patterns.

How do I implement model checkpointing in TensorFlow and PyTorch?▼

Model checkpointing in TensorFlow and PyTorch relies on standard training patterns and data loading techniques. This Skill provides code examples to implement robust checkpointing for efficient ML development.

Can I use Hugging Face Transformers with scikit-learn for a classification pipeline?▼

Yes, you can use Hugging Face Transformers and scikit-learn together to implement classification models. This Skill provides code examples and best practices covering both frameworks for robust machine learning development.

Does this Skill provide examples for data loading and optimization in machine learning frameworks?▼

Yes, this Skill provides examples for data loading and optimization techniques across popular machine learning frameworks. It covers training patterns, learning rate scheduling, and mixed precision for efficient ML development.

When should I use PyTorch versus TensorFlow for training machine learning models?▼

Choosing between PyTorch and TensorFlow depends on your specific project requirements, as this Skill provides standard training patterns and optimization techniques for both. It offers best practices to implement robust machine learning pipelines regardless of framework choice.

Related Skills

Explore More Software Engineering Skills→
cas-bigdatalabcas-bigdatalab
541

remote_formatter

Retrieve datasets from HuggingFace Hub and format them as JSONL.

Official
Intermediate
h4vzzh4vzz
33

model-deployment

Deploy trained ML models as REST services on Docker or Kubernetes.

Community
Advanced
twjarviszyra-webtwjarviszyra-web
3

weights-and-biases

Track ML experiments, metrics, and artifacts across training runs.

Community
Advanced
rezosndrezosnd

excel-generator

Generate styled Excel workbooks with formulas, charts, and data validation.

Community
Intermediate