Hugging Face Transformers
| File:Hugging Face Transformers logo.png | |
| Developer(s) | Hugging Face |
|---|---|
| Initial release | November 17, 2018 |
| Stable release | Lua error in Module:Wd at line 2189: attempt to index field 'wikibase' (a nil value).
/ Lua error in Module:Wd at line 2189: attempt to index field 'wikibase' (a nil value). |
| Written in | Python |
| Engine | |
| Type | Deep learning library |
| License | Apache License 2.0 |
Search Hugging Face Transformers on Amazon.
Hugging Face Transformers is an open-source deep learning library developed by Hugging Face. It provides implementations of pretrained transformer and other neural network models for training and inference, including models for text, images, audio, video, and multimodal learning.[1][2]
History
Transformers was first released in November 2018 as pytorch-pretrained-bert, a PyTorch implementation of BERT.[3] It was later renamed pytorch-transformers as support expanded to additional transformer models, before becoming Transformers.[4]
By September 2019, its PyTorch version had been pip installed more than 500,000 times that year and was being used by more than 1,000 companies, according to VentureBeat.[5] Version 5, released in 2025, made PyTorch the library's sole machine learning backend, ending direct support for TensorFlow and JAX.[6]
Features
Transformers provides standardized model definitions and tools for downloading, running, and training pretrained machine learning models.[7] It is used for tasks including text generation, machine translation, text classification, question answering, image classification, object detection, speech synthesis, and speech recognition. Models can be downloaded from and shared through the Hugging Face Hub.[8]
See also
- Comparison of deep learning software
- Comparison of machine learning software
- Knowledge distillation
- Large language model
- Python deep learning and machine learning software
References
- ↑ Wolf, Thomas; Debut, Lysandre; Sanh, Victor; Chaumond, Julien; Delangue, Clement (2020). "Transformers: State-of-the-Art Natural Language Processing". Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing: System Demonstrations. Association for Computational Linguistics. pp. 38–45. doi:10.18653/v1/2020.emnlp-demos.6.
- ↑ "Hugging Face launches popular Transformers NLP library for TensorFlow". VentureBeat. September 26, 2019. Retrieved September 3, 2026.
- ↑ "pytorch-pretrained-bert". Python Package Index. Retrieved September 3, 2026.
- ↑ "Migrating from previous packages". Hugging Face. Retrieved September 3, 2026.
- ↑ "Hugging Face launches popular Transformers NLP library for TensorFlow". VentureBeat. September 26, 2019. Retrieved September 3, 2026.
- ↑ "Transformers v5: Simple model definitions powering the AI ecosystem". Hugging Face. December 1, 2025. Retrieved September 3, 2026.
- ↑ "Transformers". GitHub. Hugging Face. Retrieved September 3, 2026.
- ↑ "Using Transformers at Hugging Face". Hugging Face. Retrieved September 3, 2026.
External links
- Lua error in Module:Official_website at line 90: attempt to index field 'wikibase' (a nil value).
- transformers on GitHub
Template:Machine learning software
This article "Hugging Face Transformers" is from Wikipedia. The list of its authors can be seen in its historical and/or the page Edithistory:Hugging Face Transformers. Articles copied from Draft Namespace on Wikipedia could be seen on the Draft Namespace of Wikipedia and not main one.
