← Discover
GitHub · huggingface/transformers↑ +80 today

Training and running artificial intelligence models

Developed by Hugging Face, Transformers is a library used to train and run state-of-the-art machine learning models on different data types such as text, images, and audio. It provides developers with access to popular artificial intelligence models and the opportunity to fine-tune them.

Updates

  • October 20, 2026: Stars 167,782 → 167,893, latest release v5.20.2 (October 19, 2026).
  • October 17, 2026: Stars 167,756 → 167,782, latest release v5.20.1 (October 16, 2026).
  • October 16, 2026: Stars 167,017 → 167,756, latest release v5.20.0 (October 15, 2026).
  • October 7, 2026: Stars 166,876 → 167,017, latest release v5.19.0 (October 6, 2026).

What you get

  • Provides access to text, image and sound models.
  • It makes it easier to fine-tune models.
  • It offers rapid development with its wide model library.

Installation

Installation from source code
git clone https://github.com/huggingface/transformers.git
cd transformers

# pip
pip install '.[torch]'

# uv
uv pip install '.[torch]'

If you don't write code

Paste this into your AI agent (Claude Code · Codex · Antigravity)

I want to run a text rendering model using the Transformers library. How can I get started quickly using the Pipeline API? Can you help with step by step code example and explanation?

Repository: https://github.com/huggingface/transformers. Follow the official instructions in the README of this repository for setup and execution.

Before starting, check which OS we are on and if the necessary tools (e.g., Python, Node.js, Git, Docker) are installed. Install any missing ones step-by-step according to this system.

Create a new, empty folder to work in. Do not touch any files outside this folder and do not delete anything. Tell me what you are going to do in one sentence before running each command.

Tell me what I should see on the screen at the end of each step. If an error occurs, I will paste the error message to you exactly as it is, and we will fix it together.

Related dictionary terms

Who it is forIt is suitable for software developers and artificial intelligence researchers who want to work with machine learning models.
LicenseApache-2.0

Links

TreScout did not build this tool · we found it in GitHub trends and wrote it up. This page describes the repository as of 2026-08-12: The star count and our text belong to that day, the repository may have changed since. Check the repository link for the current state. The introductory text was prepared with AI from the repository's own documentation, and this page was machine-translated from the Turkish original · the Turkish version prevails.