tutorials

10 items · ranked by signal, recency & corroboration

Profiling in PyTorch (Part 1): A Beginner's Guide to torch.profiler

PyTorch's torch.profiler module provides a built-in profiling tool for analyzing model performance. It helps identify performance bottlenecks and optimizes code. You can use it to profile PyTorch models and understand where time is spent during execution. This guide provides a beginner's introduction to using torch.profiler.

Key takeaways

torch.profiler is a built-in PyTorch module for profiling.
Helps identify performance bottlenecks in PyTorch models.
Optimizes code by understanding execution time distribution.

HHugging Face Blog#pytorch #profiling #performance

tutorialsJan 30

How to deploy and fine-tune DeepSeek models on AWS

DeepSeek models can be deployed and fine-tuned on AWS using Hugging Face's Transformers library and the SageMaker platform. This integration enables users to leverage the scalability and flexibility of AWS for their AI workloads. You can use pre-trained models or create custom models through fine-tuning. The solution provides a streamlined process for deploying and managing AI models in the cloud.

Key takeaways

DeepSeek models deployable on AWS via Hugging Face and SageMaker
Fine-tuning supported for custom model creation
Scalability and flexibility of AWS leveraged for AI workloads

HHugging Face Blog#cloud-deployment #fine-tuning #aws

tutorialsApr 5

StackLLaMA: A hands-on guide to train LLaMA with RLHF

The StackLLaMA project provides a step-by-step guide on training LLaMA models with Reinforcement Learning from Human Feedback (RLHF). The tutorial covers data preparation, model fine-tuning, and deployment. You can use this guide to train your own LLaMA models with RLHF. The guide is hands-on and includes code examples.

Key takeaways

StackLLaMA offers a step-by-step RLHF training guide.
Covers data prep, model fine-tuning, and deployment.
Includes code examples for hands-on learning.

HHugging Face Blog#rlhf #llama #fine-tuning

tutorialsJan 9

AI for Game Development: Creating a Farming Game in 5 Days. Part 2

The second part of a tutorial series shows how to build a farming game using AI. The tutorial covers using Hugging Face Transformers for text-to-image and text-to-speech models. You can build a simple game in just 5 days. The tutorial is designed for game developers and builders who want to leverage AI for game development.

Key takeaways

Build a simple farming game in 5 days using AI.
Hugging Face Transformers used for text-to-image and text-to-speech.
Tutorial series for game developers interested in AI.

HHugging Face Blog#ai-for-games #game-development #text-to-image #text-to-speech

tutorialsJan 2

AI for Game Development: Creating a Farming Game in 5 Days. Part 1

This tutorial series shows how to build a farming game using AI. The first part covers setting up the game environment and integrating AI models for game development. You can follow along and build your own game in just 5 days. The tutorial uses Hugging Face tools and models.

Key takeaways

Build a farming game in 5 days using AI.
Covers setting up the game environment and integrating AI models.
Uses Hugging Face tools and models.

HHugging Face Blog#ai-for-games #game-development #tutorial

tutorialsJul 13

Building a Playlist Generator with Sentence Transformers

You can build a music playlist generator using sentence transformers, which map song titles and descriptions to dense vector embeddings. This approach enables semantic search and recommendation capabilities. By leveraging pre-trained models and fine-tuning them on your dataset, you can create a personalized playlist generator. The Hugging Face Hub provides access to pre-trained models and a platform for sharing and deploying your application.

Key takeaways

Sentence transformers map text to dense vector embeddings for semantic search.
Pre-trained models can be fine-tuned on your dataset for personalized results.
Hugging Face Hub offers pre-trained models and deployment tools.

HHugging Face Blog#sentence-transformers #semantic-search #music-recommendation

tutorialsJun 30

Policy Gradient with PyTorch

The Hugging Face blog post explains how to implement policy gradient methods using PyTorch. Policy gradient is a type of reinforcement learning algorithm. You can use it to train agents to make decisions in complex environments. The post provides a practical example of training an agent using PyTorch.

Key takeaways

Policy gradient is a type of reinforcement learning algorithm.
PyTorch can be used to implement policy gradient methods.
The Hugging Face blog post provides a practical example of training an agent.

HHugging Face Blog#reinforcement-learning #pytorch

tutorialsJun 29

Liftoff! How to get started with your first ML project 🚀

The Hugging Face blog provides a step-by-step guide to launching your first machine learning project. You can explore popular open-source libraries like Transformers and Datasets. The post covers setting up your environment, choosing a dataset, and selecting a pre-trained model.

Key takeaways

Use Hugging Face's Transformers and Datasets libraries for ML projects.
Select a pre-trained model for faster development.
Environment setup and dataset choice are crucial initial steps.

HHugging Face Blog#machine-learning #open-source #hugging-face

tutorialsJun 23

Getting Started With Embeddings

This guide provides an introduction to embeddings, a technique for representing text as numerical vectors. Embeddings enable text search, clustering, and classification. You can use pre-trained models from Hugging Face for generating embeddings.

Key takeaways

Embeddings represent text as numerical vectors.
Pre-trained models are available for generating embeddings.
Embeddings enable text search, clustering, and classification.

HHugging Face Blog#embeddings #text-embeddings #pre-trained-models

tutorialsMar 18

My Journey to a serverless transformers pipeline on Google Cloud

A developer detailed building a serverless transformers pipeline on Google Cloud using Hugging Face Transformers and Cloud Run. The pipeline leverages pre-trained models and handles inference workloads efficiently. You can deploy similar pipelines using these steps. This approach allows for scalable and cost-effective model serving.

Key takeaways

Uses Hugging Face Transformers and Cloud Run for deployment.
Pipeline handles inference workloads efficiently.
Deployment process is scalable and cost-effective.

HHugging Face Blog#serverless #transformers #google-cloud