Sign in

Transformers

🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference an

7.9 Open source169k
Add this badge to your site
Preview of the Reviewed by AI Review Rating badge for Transformers

Run or build Transformers? Paste this where your reviews or press logos go. It links to this review and always shows the current score and review date. Every tool we score 7.0 or higher can use it. It is free, and it does not change a score.

Need a launch video for Transformers? We make 45 to 90 second explainers from $79. See the explainer service

Transformers homepage
huggingface.co · captured 2026-09-01
Transformers, explained: Understand the model behind GPT, BERT, and T5
Collecting Modern G1 Transformers - TOP 10 TIPS!
The BEST Hasbro Devastator Figure??? | #transformers Studio Series 86 Devastator Review
Transformers Cyberworld scorponok unboxing, assembly, transformation, review, tips and parents guide
HOW TO Transform the PARTY WALLOP Transformers x TMNT Collaborative TUTORIAL
Transformers Physics Problems - Voltage, Current & Power Calculations - Electromagnetic Induction

Our verdict

A well-maintained, widely adopted project. This assessment is derived from GitHub's own repository metrics on 2026-08-24, not from hands-on testing.

Transformers is Hugging Face’s free Python library that defines state-of-the-art models for text, computer vision, audio, video and multimodal tasks, for both inference and training (documentation, read 2026-11-07). The docs list over 1M model checkpoints on the Hugging Face Hub, a Pipeline class for inference, a Trainer for training and a generate method for text generation, and say its model definitions are shared with training frameworks such as Axolotl, Unsloth, DeepSpeed and FSDP, inference engines such as vLLM, SGLang and TGI, and libraries such as llama.cpp and mlx. There is no licence fee: the Apache-2.0 licence puts no real constraint on commercial use, and your costs are the hardware or cloud compute you run models on. It is built in Python and has 168,796 stars and 35,178 forks on GitHub, and the most recent push was 2026-11-11. The most recent tagged release is v5.22.2, from 2026-11-06. Figures come from the GitHub API on 2026-11-11 and refresh weekly. Documentation is at huggingface.co/docs/transformers (read 2026-11-07).

Reviewed by AI Review Rating from GitHub API data How we score

RepositoryGitHub API, refreshed weekly

169kStars
35.2kForks
1.3kWatching
4.2kContributors
1.1kOpen issues
Licence
Apache-2.0
Language
Python
Last push
2026-11-15
View on GitHub

Releases

  1. v5.23.0 Release v5.23.0
  2. v5.22.2 Patch release v5.22.2
  3. v5.22.1 Patch release v5.22.1
  4. v5.22.0 v5.22.0: Mistral Large 4 (Le Chonk)
  5. v5.21.1 Patch release v5.21.1
  6. v5.21 Release: v5.21.0

What it does well

  • Pipeline: a simple inference class for text generation, image segmentation, speech recognition, document question answering and more
  • Trainer: mixed precision, torch.compile, FlashAttention and distributed training for PyTorch models
  • generate: fast text generation with LLMs and vision language models, with streaming and several decoding strategies
  • Model definitions shared across training frameworks, inference engines and llama.cpp or mlx (documentation)

Pros and cons

Pros

Cons

Pricingverified 7 Nov 2026

TierMonthlyIncludesSeats
Open source (Apache-2.0) Free The library is free under Apache-2.0; compute for training or inference is your own cost (github.com/huggingface/transformers, read 2026-11-06) 1

Changelogwhat changed, most recent first

On videoclick to play, nothing loads until you do

What users actually say

We link to discussions rather than reproducing them. Opinions belong to their authors.

User reviews

No one has reviewed Transformers here yet. Reviews are moderated before they appear, and our own score is editorial and separate from user ratings, though once reviews land they do lift it.

Used Transformers? Review it.

Sign in to rate it. One account, one review per tool, so the score means something.

Create a free account Already a member? Sign in
{{ reviewsTotal }}{{ options.labels.singularReviewCountLabel }}
{{ reviewsTotal }}{{ options.labels.pluralReviewCountLabel }}
{{ options.labels.noReviewsLabel }}
{{ options.labels.newReviewButton }}
{{ userData.canReview.message }}

Transformers alternatives

Side by side

ToolOur scoreFrom Free tierBest for
Transformers this page 7.9 Free Yes ML engineers and researchers who need model definitions…
🥇LocalAI 7.8 - Yes
🥈vLLM 7.5 Free Yes
🥉SGLang 7.2 - Yes
AirLLM 6.8 - Yes
Jina Serve 5 - Yes
DeepInfra 3.6 $0.02 -

Articles on Transformers

Questions

Is Transformers free?

Yes. Transformers is free and open source, and its own repository confirms the licence (read 2026-11-06).

How much does Transformers cost?

The Transformers library is free and open source under Apache-2.0, so there is no licence fee. Your costs are the hardware or cloud compute you run models on. Documentation is at huggingface.co/docs/transformers (read 2026-11-06).

Is Transformers open source?

Yes. Transformers is a public repository released under Apache-2.0. You can self-host or inspect the source directly.

How is Transformers scored here?

Transformers scores 7.9 out of 10. That comes from a desk review of public evidence, which is capped at 8.5 out of 10: public pricing, documentation, maintenance signals and how much we could actually verify. Affiliate relationships are excluded from scoring entirely. The full rubric is published on our methodology page.

Related