Hugging Face
Hugging Face is a platform and ecosystem for discovering, hosting, sharing, and using machine-learning models, datasets, applications, and related tools.
Natural Language Processing in Action, Second Edition
Hugging Face Hub is an online repository and collaboration platform for sharing machine-learning models, datasets, and applications.
- How it is used
- Deploys shared machine-learning models locally through downloads, authentication, and Python loading workflows.
- How deep it goes
- Explains authentication and model loading procedurally, but does not develop Hub-wide collaboration or dataset workflows.
- Examples
- Uses Llama 2 7B downloads, HF_TOKEN environment loading, prompt tokenization, and generated answers.
- What you can do after
- Operate/configure authenticated local model use with Hugging Face Hub and Transformers.
Read how Natural Language Processing in Action, Second Edition explains Hugging Face →
Starting Data Analytics with Generative AI and Python
Hugging Face is a platform that hosts and distributes machine-learning models, datasets, and related development resources.
- How it is used
- Locates, downloads, and shares pretrained models for NLP and machine-learning tasks.
- How deep it goes
- Explains the Model Hub, documentation, tutorials, and community role, but stops short of detailing implementation steps.
- Examples
- Uses sentiment analysis, text generation, language translation, model downloads, documentation, tutorials, and community-shared models.
- What you can do after
- Apply via Hugging Face by selecting and downloading a pretrained model for an NLP task while checking its security.
Read how Starting Data Analytics with Generative AI and Python explains Hugging Face →
Hugging Face in Action
The Hugging Face Hub is a platform for hosting, discovering, sharing, and collaborating on machine learning models and datasets.
- How it is used
- Supports model and dataset discovery, browser evaluation, application development, sharing, and controlled artifact downloads.
- How deep it goes
- Explains discovery, browser inference, Transformers integration, and revision-pinned downloads without covering model internals.
- Examples
- Demonstrates DETR object detection, browser-uploaded images, Transformers code samples, and Pegasus configuration-file downloads.
- What you can do after
- Apply it via the Model Hub, Hosted Inference API, Transformers, and huggingface_hub to evaluate models and run selected artifacts.
Software Testing with Generative AI
Hugging Face is a platform and community hub for sharing, accessing, training, and documenting machine-learning models and datasets.
- How it is used
- Supports problem-driven discovery, access, adaptation, training, and documentation for machine-learning models.
- How deep it goes
- Defines the platform’s resources and selection rationale but defers detailed model adaptation and further training.
- Examples
- Uses a models index containing hundreds of thousands of differently trained models.
- What you can do after
- Apply via Hugging Face by finding pretrained models and related resources for a specific machine-learning problem.
Read how Software Testing with Generative AI explains Hugging Face →
Deep Learning with PyTorch, Second Edition
A repository service for discovering, sharing, and exchanging pretrained models and weights.
- How it is used
- Provides a model repository and high-level wrapper for applying pretrained transformer and diffusion models.
- How deep it goes
- Defines model zoos and demonstrates one text-generation pipeline, while deferring transformer mechanics to a later treatment.
- Examples
- Uses a GPT-2 pipeline to complete a nine-word prompt and produce a generated continuation.
- What you can do after
- Apply pretrained text-generation models through the transformers pipeline interface.
Read how Deep Learning with PyTorch, Second Edition explains Hugging Face →
Related concepts
- transformersuses · Hugging Face Transformers is an open-source library providing pretrained transformer models, tokenizers, and tools for using and training models across machine-learning tasks.
- Traineruses · Trainer is a Hugging Face Transformers API class that provides a high-level interface for configuring, running, and evaluating model training.
- diffusersproduces · Diffusers is an open-source Hugging Face library providing pretrained diffusion models, reusable components, and pipelines for generating or manipulating images, audio, video, and other data.
These guides are generated from the text of Manning books by Manning's knowledge graph and link to the sections they draw on. The full books are available on liveBook and at manning.com.