{"name":"transformers","repo":"huggingface/transformers","url":"https://midorreal.com/project/huggingface-transformers","repository":"https://github.com/huggingface/transformers","description":"🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.","facts":{"license":{"value":"Apache-2.0","source":"https://github.com/huggingface/transformers","checked":"22 Nov 2026"},"language":{"value":"Python","source":"https://github.com/huggingface/transformers","checked":"22 Nov 2026"},"homepage":{"value":"https://huggingface.co/transformers","source":"https://huggingface.co/transformers","checked":"22 Nov 2026"},"last_release":{"value":"v5.23.0, 13 Nov 2026","source":"https://github.com/huggingface/transformers/releases","checked":"22 Nov 2026"},"releases":{"value":"283","source":"https://github.com/huggingface/transformers/releases","checked":"20 Nov 2026"},"contributors":{"value":"4,274","source":"https://github.com/huggingface/transformers/graphs/contributors","checked":"20 Nov 2026"},"archived":{"value":"no","source":"https://github.com/huggingface/transformers","checked":"22 Nov 2026"}},"stars":169348.0,"writeup":{"what_it_is":"Transformers is a model-definition framework for machine learning models in text, computer vision, audio, video, and multimodal tasks. It supports both inference and training, and provides a Pipeline API for running pretrained models.","audience":"Researchers, engineers, and developers working with pretrained machine learning models","claims":[{"kind":"specific","claim":"Provides access to over 1 million pretrained model checkpoints on the Hugging Face Hub","excerpt":"There are over 1M+ Transformers [model checkpoints]","status":"not_checked"},{"kind":"specific","claim":"Requires Python 3.11+ and PyTorch 2.6+","excerpt":"Transformers works with Python 3.11+, and [PyTorch](https://pytorch.org/get-started/locally/) 2.6+.","status":"not_checked"},{"kind":"specific","claim":"Includes a high-level Pipeline API that handles preprocessing and returns outputs for text, audio, vision, and multimodal tasks","excerpt":"The `Pipeline` is a high-level inference class that supports text, audio, vision, and multimodal tasks.","status":"not_checked"},{"kind":"specific","claim":"Offers hundreds of model architectures with 1M+ pretrained checkpoints across all modalities","excerpt":"Hundreds of model architectures with 1M+ pretrained checkpoints across all modalities.","status":"not_checked"},{"kind":"specific","claim":"Allows moving a single model between PyTorch, JAX, and TF2.0 frameworks","excerpt":"Move a single model between PyTorch/JAX/TF2.0 frameworks at will.","status":"not_checked"}],"alternatives":[],"written_by":"AI, from the project's README","date":"2026-10-30"},"why_now":null,"owner_supplied":null,"score":{"verdict":"real","hype":82,"reality":98,"gap":-16,"momentum":1.2,"confidence":85,"version":"score-2.0","rule":"verdict-2.0","calculated_at":"2026-11-22T08:00:00+00:00","verdict_source":"rule"},"early_read":null,"changes":[{"date":"2026-11-13T14:10:57+00:00","text":"Latest release v5.23.0","source":"https://github.com/huggingface/transformers/releases"},{"date":"2018-11-17T11:23:16+00:00","text":"First release","source":"https://github.com/huggingface/transformers/releases"},{"date":"2018-10-29T13:56:00+00:00","text":"Repository created","source":"https://github.com/huggingface/transformers"}],"cite":"transformers is a GitHub project at https://github.com/huggingface/transformers written mainly in Python, described there as \"🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training\".","attribution":"Data from Mid or Real, https://midorreal.com/project/huggingface-transformers, checked 22 November 2026. Attribution with a link is required.","still_real":null}