Results for “Hugging Face Hub”

Not everyone wants a CLI. LM Studio gives you a desktop app for browsing, downloading, and chatting with local models — and a server mode when you outgrow the GUI.

Hugging Face Text Generation Inference is a useful teaching example for production model serving: router, model server, streaming, and operational controls.

If you build a dataset, how you license it determines who can use it and how. Picking the right license matters as much as the data itself.

CSV is the plainest, ugliest, most universal data format. It has survived every trend because it does one thing well: it works everywhere.

A data card is like a nutrition label for a dataset: who collected it, how, what is in it, and what it should not be used for.

If you ship AI, ethics is not abstract. It is a set of decisions you make with real trade-offs. Here is the working checklist serious builders actually use.

SmolLM-style models are perfect for classroom experiments because students can see speed, limitations, and task fit quickly.

Quantization is the art of making models fit local hardware by using fewer bits, while watching how quality changes.

AI moves so fast that staying current is its own skill. Here is a sustainable system.

Fine-tune, evaluate, serve, monitor. The ML engineer is the person who ships the models that now power medicine, law, and design. It is the highest-leverage engineering role.

You don't need an internship to have a portfolio. AI lets you ship real projects from your bedroom.

Granite code models are a useful contrast to Qwen Coder, Codestral, and StarCoder2 because they emphasize enterprise-friendly workflows.

Nemotron gives students a way to discuss open models built for NVIDIA-accelerated deployment, agents, and enterprise AI stacks.

StarCoder2 gives students an open-science code model family to compare against general chat models and newer coder families.

A model file's quantization decides how big it is, how fast it runs, and how good it sounds. Learn the formats, the trade-offs, and how to pick the right one.

There are too many open-weight models. A short, opinionated tour of the major families and what each is actually good at.

Why some AI you can download and run yourself, and others you can only rent.

The core ideas — what AI is, how it learns, what it can and can't do. 566 lessons.

Every family in the industry. Variants, strengths, limits, pricing. 357 lessons.

ML engineers train, fine-tune, and ship the models that power AI products. They're the people who build the tools everyone else in this list uses.

Hugging Face — Developers wanting to train agents with RL

Hugging Face — Developers building speech, ASR, or audio-gen apps

Hugging Face — Developers and students building AI agents

Hugging Face — Students learning transformers and modern NLP

Hugging Face — Developers adding MCP-compatible tools to AI agents

Hugging Face — Game developers embedding ML agents in Unity/Godot

Hugging Face — Developers doing image classification, detection, generation

Hugging Face — Creators and engineers training image/video diffusion models

IBM / Coursera — High school students and beginners wanting to build AI apps

The GitHub of AI — a hub for open-weights models, datasets, and demos.

A collection of pre-trained models — Hugging Face Hub is the biggest.

Text Generation Inference — Hugging Face's production LLM serving stack.

Hugging Face's open-source library that makes using and fine-tuning LLMs straightforward.

Hugging Face's library for running and training diffusion models like Stable Diffusion.

EleutherAI's toolkit for running standard LLM benchmarks reproducibly.

Custom-silicon inference provider competing on tokens-per-second and latency.

A short document describing what a model does, how it was trained, and its limits.

A short document describing a dataset — what's in it, where it came from, and its limits.

A public ranking of models on a benchmark.

A benchmark for general AI assistants, with multi-step real-world questions.

A post-training quantization method for LLMs based on second-order information.

Meta's open-weights LLM family, a staple of the open-source AI ecosystem.

Microsoft's open-source library for scaling deep learning training and inference.