Transformers
Last updated
Last updated
State-of-the-art Machine Learning for , , and . By BOINC AI team.
🌍Transformers provides APIs and tools to easily download and train state-of-the-art pretrained models. Using pretrained models can reduce your compute costs, carbon footprint, and save you the time and resources required to train a model from scratch. These models support common tasks in different modalities, such as:
📝 Natural Language Processing: text classification, named entity recognition, question answering, language modeling, summarization, translation, multiple choice, and text generation. 🖼️ Computer Vision: image classification, object detection, and segmentation. 🗣️ Audio: automatic speech recognition and audio classification. 🐙 Multimodal: table question answering, optical character recognition, information extraction from scanned documents, video classification, and visual question answering.
🌍Transformers support framework interoperability between PyTorch, TensorFlow, and JAX. This provides the flexibility to use a different framework at each stage of a model’s life; train a model in three lines of code in one framework, and load it for inference in another. Models can also be exported to a format like ONNX and TorchScript for deployment in production environments.
The documentation is organized into five sections:
GET STARTED provides a quick tour of the library and installation instructions to get up and running.
TUTORIALS are a great place to start if you’re a beginner. This section will help you gain the basic skills you need to start using the library.
HOW-TO GUIDES show you how to achieve a specific goal, like finetuning a pretrained model for language modeling or how to write and share a custom model.
CONCEPTUAL GUIDES offers more discussion and explanation of the underlying concepts and ideas behind models, tasks, and the design philosophy of 🌍 Transformers.
API describes all classes and functions:
MAIN CLASSES details the most important classes like configuration, model, tokenizer, and pipeline.
MODELS details the classes and functions related to each model implemented in the library.
INTERNAL HELPERS details utility classes and functions used internally.
(from Google Research and the Toyota Technological Institute at Chicago) released with the paper , by Zhenzhong Lan, Mingda Chen, Sebastian Goodman, Kevin Gimpel, Piyush Sharma, Radu Soricut.
(from Google Research) released with the paper by Chao Jia, Yinfei Yang, Ye Xia, Yi-Ting Chen, Zarana Parekh, Hieu Pham, Quoc V. Le, Yunhsuan Sung, Zhen Li, Tom Duerig.
(from BAAI) released with the paper by Chen, Zhongzhi and Liu, Guang and Zhang, Bo-Wen and Ye, Fulong and Yang, Qinghong and Wu, Ledell.
(from MIT) released with the paper by Yuan Gong, Yu-An Chung, James Glass.
(from Tsinghua University) released with the paper by Haixu Wu, Jiehui Xu, Jianmin Wang, Mingsheng Long.
(from Suno) released in the repository by Suno AI team.
(from Facebook) released with the paper by Mike Lewis, Yinhan Liu, Naman Goyal, Marjan Ghazvininejad, Abdelrahman Mohamed, Omer Levy, Ves Stoyanov and Luke Zettlemoyer.
(from École polytechnique) released with the paper by Moussa Kamal Eddine, Antoine J.-P. Tixier, Michalis Vazirgiannis.
(from VinAI Research) released with the paper by Nguyen Luong Tran, Duong Minh Le and Dat Quoc Nguyen.
(from Microsoft) released with the paper by Hangbo Bao, Li Dong, Furu Wei.
(from Google) released with the paper by Jacob Devlin, Ming-Wei Chang, Kenton Lee and Kristina Toutanova.
(from Google) released with the paper by Sascha Rothe, Shashi Narayan, Aliaksei Severyn.
(from VinAI Research) released with the paper by Dat Quoc Nguyen, Thanh Vu and Anh Tuan Nguyen.
(from Google Research) released with the paper by Manzil Zaheer, Guru Guruganesh, Avinava Dubey, Joshua Ainslie, Chris Alberti, Santiago Ontanon, Philip Pham, Anirudh Ravula, Qifan Wang, Li Yang, Amr Ahmed.
(from Google Research) released with the paper by Manzil Zaheer, Guru Guruganesh, Avinava Dubey, Joshua Ainslie, Chris Alberti, Santiago Ontanon, Philip Pham, Anirudh Ravula, Qifan Wang, Li Yang, Amr Ahmed.
(from Microsoft Research AI4Science) released with the paper by Renqian Luo, Liai Sun, Yingce Xia, Tao Qin, Sheng Zhang, Hoifung Poon and Tie-Yan Liu.
(from Google AI) released with the paper by Alexander Kolesnikov, Lucas Beyer, Xiaohua Zhai, Joan Puigcerver, Jessica Yung, Sylvain Gelly, Neil Houlsby.
(from Facebook) released with the paper by Stephen Roller, Emily Dinan, Naman Goyal, Da Ju, Mary Williamson, Yinhan Liu, Jing Xu, Myle Ott, Kurt Shuster, Eric M. Smith, Y-Lan Boureau, Jason Weston.
(from Facebook) released with the paper by Stephen Roller, Emily Dinan, Naman Goyal, Da Ju, Mary Williamson, Yinhan Liu, Jing Xu, Myle Ott, Kurt Shuster, Eric M. Smith, Y-Lan Boureau, Jason Weston.
(from Salesforce) released with the paper by Junnan Li, Dongxu Li, Caiming Xiong, Steven Hoi.
(from Salesforce) released with the paper by Junnan Li, Dongxu Li, Silvio Savarese, Steven Hoi.
(from BigScience workshop) released by the .
(from Alexa) released with the paper by Adrian de Wynter and Daniel J. Perry.
(from Harbin Institute of Technology/Microsoft Research Asia/Intel Labs) released with the paper by Xiao Xu, Chenfei Wu, Shachar Rosenman, Vasudev Lal, Wanxiang Che, Nan Duan.
(from NAVER CLOVA) released with the paper by Teakgyu Hong, Donghyun Kim, Mingi Ji, Wonseok Hwang, Daehyun Nam, Sungrae Park.
(from Google Research) released with the paper by Linting Xue, Aditya Barua, Noah Constant, Rami Al-Rfou, Sharan Narang, Mihir Kale, Adam Roberts, Colin Raffel.
(from Inria/Facebook/Sorbonne) released with the paper by Louis Martin, Benjamin Muller, Pedro Javier Ortiz Suárez*, Yoann Dupont, Laurent Romary, Éric Villemonte de la Clergerie, Djamé Seddah and Benoît Sagot.
(from Google Research) released with the paper by Jonathan H. Clark, Dan Garrette, Iulia Turc, John Wieting.
(from OFA-Sys) released with the paper by An Yang, Junshu Pan, Junyang Lin, Rui Men, Yichang Zhang, Jingren Zhou, Chang Zhou.
(from LAION-AI) released with the paper by Yusong Wu, Ke Chen, Tianyu Zhang, Yuchen Hui, Taylor Berg-Kirkpatrick, Shlomo Dubnov.
(from OpenAI) released with the paper by Alec Radford, Jong Wook Kim, Chris Hallacy, Aditya Ramesh, Gabriel Goh, Sandhini Agarwal, Girish Sastry, Amanda Askell, Pamela Mishkin, Jack Clark, Gretchen Krueger, Ilya Sutskever.
(from University of Göttingen) released with the paper by Timo Lüddecke and Alexander Ecker.
(from Salesforce) released with the paper by Erik Nijkamp, Bo Pang, Hiroaki Hayashi, Lifu Tu, Huan Wang, Yingbo Zhou, Silvio Savarese, Caiming Xiong.
(from MetaAI) released with the paper by Baptiste Rozière, Jonas Gehring, Fabian Gloeckle, Sten Sootla, Itai Gat, Xiaoqing Ellen Tan, Yossi Adi, Jingyu Liu, Tal Remez, Jérémy Rapin, Artyom Kozhevnikov, Ivan Evtimov, Joanna Bitton, Manish Bhatt, Cristian Canton Ferrer, Aaron Grattafiori, Wenhan Xiong, Alexandre Défossez, Jade Copet, Faisal Azhar, Hugo Touvron, Louis Martin, Nicolas Usunier, Thomas Scialom, Gabriel Synnaeve.
(from Microsoft Research Asia) released with the paper by Depu Meng, Xiaokang Chen, Zejia Fan, Gang Zeng, Houqiang Li, Yuhui Yuan, Lei Sun, Jingdong Wang.
(from YituTech) released with the paper by Zihang Jiang, Weihao Yu, Daquan Zhou, Yunpeng Chen, Jiashi Feng, Shuicheng Yan.
(from Facebook AI) released with the paper by Zhuang Liu, Hanzi Mao, Chao-Yuan Wu, Christoph Feichtenhofer, Trevor Darrell, Saining Xie.
(from Facebook AI) released with the paper by Sanghyun Woo, Shoubhik Debnath, Ronghang Hu, Xinlei Chen, Zhuang Liu, In So Kweon, Saining Xie.
(from Tsinghua University) released with the paper by Zhengyan Zhang, Xu Han, Hao Zhou, Pei Ke, Yuxian Gu, Deming Ye, Yujia Qin, Yusheng Su, Haozhe Ji, Jian Guan, Fanchao Qi, Xiaozhi Wang, Yanan Zheng, Guoyang Zeng, Huanqi Cao, Shengqi Chen, Daixuan Li, Zhenbo Sun, Zhiyuan Liu, Minlie Huang, Wentao Han, Jie Tang, Juanzi Li, Xiaoyan Zhu, Maosong Sun.
(from OpenBMB) released by the .
(from Salesforce) released with the paper by Nitish Shirish Keskar, Bryan McCann, Lav R. Varshney, Caiming Xiong and Richard Socher.
(from Microsoft) released with the paper by Haiping Wu, Bin Xiao, Noel Codella, Mengchen Liu, Xiyang Dai, Lu Yuan, Lei Zhang.
(from Facebook) released with the paper by Alexei Baevski, Wei-Ning Hsu, Qiantong Xu, Arun Babu, Jiatao Gu, Michael Auli.
(from Microsoft) released with the paper by Pengcheng He, Xiaodong Liu, Jianfeng Gao, Weizhu Chen.
(from Microsoft) released with the paper by Pengcheng He, Xiaodong Liu, Jianfeng Gao, Weizhu Chen.
(from Berkeley/Facebook/Google) released with the paper by Lili Chen, Kevin Lu, Aravind Rajeswaran, Kimin Lee, Aditya Grover, Michael Laskin, Pieter Abbeel, Aravind Srinivas, Igor Mordatch.
(from SenseTime Research) released with the paper by Xizhou Zhu, Weijie Su, Lewei Lu, Bin Li, Xiaogang Wang, Jifeng Dai.
(from Facebook) released with the paper by Hugo Touvron, Matthieu Cord, Matthijs Douze, Francisco Massa, Alexandre Sablayrolles, Hervé Jégou.
(from Google AI) released with the paper by Fangyu Liu, Julian Martin Eisenschlos, Francesco Piccinno, Syrine Krichene, Chenxi Pang, Kenton Lee, Mandar Joshi, Wenhu Chen, Nigel Collier, Yasemin Altun.
(from The University of Texas at Austin) released with the paper by Jeffrey Ouyang-Zhang, Jang Hyun Cho, Xingyi Zhou, Philipp Krähenbühl.
(from Facebook) released with the paper by Nicolas Carion, Francisco Massa, Gabriel Synnaeve, Nicolas Usunier, Alexander Kirillov, Sergey Zagoruyko.
(from Microsoft Research) released with the paper by Yizhe Zhang, Siqi Sun, Michel Galley, Yen-Chun Chen, Chris Brockett, Xiang Gao, Jianfeng Gao, Jingjing Liu, Bill Dolan.
(from SHI Labs) released with the paper by Ali Hassani and Humphrey Shi.
(from Meta AI) released with the paper by Maxime Oquab, Timothée Darcet, Théo Moutakanni, Huy Vo, Marc Szafraniec, Vasil Khalidov, Pierre Fernandez, Daniel Haziza, Francisco Massa, Alaaeldin El-Nouby, Mahmoud Assran, Nicolas Ballas, Wojciech Galuba, Russell Howes, Po-Yao Huang, Shang-Wen Li, Ishan Misra, Michael Rabbat, Vasu Sharma, Gabriel Synnaeve, Hu Xu, Hervé Jegou, Julien Mairal, Patrick Labatut, Armand Joulin, Piotr Bojanowski.
(from BOINC AI), released together with the paper by Victor Sanh, Lysandre Debut and Thomas Wolf. The same method has been applied to compress GPT2 into , RoBERTa into , Multilingual BERT into and a German version of DistilBERT.
(from Microsoft Research) released with the paper by Junlong Li, Yiheng Xu, Tengchao Lv, Lei Cui, Cha Zhang, Furu Wei.
(from NAVER), released together with the paper by Geewook Kim, Teakgyu Hong, Moonbin Yim, Jeongyeon Nam, Jinyoung Park, Jinyeong Yim, Wonseok Hwang, Sangdoo Yun, Dongyoon Han, Seunghyun Park.
(from Facebook) released with the paper by Vladimir Karpukhin, Barlas Oğuz, Sewon Min, Patrick Lewis, Ledell Wu, Sergey Edunov, Danqi Chen, and Wen-tau Yih.
(from Intel Labs) released with the paper by René Ranftl, Alexey Bochkovskiy, Vladlen Koltun.
(from Snap Research) released with the paper by Yanyu Li, Geng Yuan, Yang Wen, Ju Hu, Georgios Evangelidis, Sergey Tulyakov, Yanzhi Wang, Jian Ren.
(from Google Brain) released with the paper by Mingxing Tan, Quoc V. Le.
(from Google Research/Stanford University) released with the paper by Kevin Clark, Minh-Thang Luong, Quoc V. Le, Christopher D. Manning.
(from Meta AI) released with the paper by Alexandre Défossez, Jade Copet, Gabriel Synnaeve, Yossi Adi.
(from Google Research) released with the paper by Sascha Rothe, Shashi Narayan, Aliaksei Severyn.
(from Baidu) released with the paper by Yu Sun, Shuohuan Wang, Yukun Li, Shikun Feng, Xuyi Chen, Han Zhang, Xin Tian, Danxiang Zhu, Hao Tian, Hua Wu.
(from Baidu) released with the paper by Xuan Ouyang, Shuohuan Wang, Chao Pang, Yu Sun, Hao Tian, Hua Wu, Haifeng Wang.
(from Meta AI) are transformer protein language models. ESM-1b was released with the paper by Alexander Rives, Joshua Meier, Tom Sercu, Siddharth Goyal, Zeming Lin, Jason Liu, Demi Guo, Myle Ott, C. Lawrence Zitnick, Jerry Ma, and Rob Fergus. ESM-1v was released with the paper by Joshua Meier, Roshan Rao, Robert Verkuil, Jason Liu, Tom Sercu and Alexander Rives. ESM-2 and ESMFold were released with the paper by Zeming Lin, Halil Akin, Roshan Rao, Brian Hie, Zhongkai Zhu, Wenting Lu, Allan dos Santos Costa, Maryam Fazel-Zarandi, Tom Sercu, Sal Candido, Alexander Rives.
(from Technology Innovation Institute) by Almazrouei, Ebtesam and Alobeidli, Hamza and Alshamsi, Abdulaziz and Cappelli, Alessandro and Cojocaru, Ruxandra and Debbah, Merouane and Goffinet, Etienne and Heslow, Daniel and Launay, Julien and Malartic, Quentin and Noune, Badreddine and Pannier, Baptiste and Penedo, Guilherme.
(from Google AI) released in the repository by Hyung Won Chung, Le Hou, Shayne Longpre, Barret Zoph, Yi Tay, William Fedus, Eric Li, Xuezhi Wang, Mostafa Dehghani, Siddhartha Brahma, Albert Webson, Shixiang Shane Gu, Zhuyun Dai, Mirac Suzgun, Xinyun Chen, Aakanksha Chowdhery, Sharan Narang, Gaurav Mishra, Adams Yu, Vincent Zhao, Yanping Huang, Andrew Dai, Hongkun Yu, Slav Petrov, Ed H. Chi, Jeff Dean, Jacob Devlin, Adam Roberts, Denny Zhou, Quoc V. Le, and Jason Wei
(from Google AI) released in the repository by Hyung Won Chung, Le Hou, Shayne Longpre, Barret Zoph, Yi Tay, William Fedus, Eric Li, Xuezhi Wang, Mostafa Dehghani, Siddhartha Brahma, Albert Webson, Shixiang Shane Gu, Zhuyun Dai, Mirac Suzgun, Xinyun Chen, Aakanksha Chowdhery, Sharan Narang, Gaurav Mishra, Adams Yu, Vincent Zhao, Yanping Huang, Andrew Dai, Hongkun Yu, Slav Petrov, Ed H. Chi, Jeff Dean, Jacob Devlin, Adam Roberts, Denny Zhou, Quoc V. Le, and Jason Wei
(from CNRS) released with the paper by Hang Le, Loïc Vial, Jibril Frej, Vincent Segonne, Maximin Coavoux, Benjamin Lecouteux, Alexandre Allauzen, Benoît Crabbé, Laurent Besacier, Didier Schwab.
(from Facebook AI) released with the paper by Amanpreet Singh, Ronghang Hu, Vedanuj Goswami, Guillaume Couairon, Wojciech Galuba, Marcus Rohrbach, and Douwe Kiela.
(from Google Research) released with the paper by James Lee-Thorp, Joshua Ainslie, Ilya Eckstein, Santiago Ontanon.
(from Microsoft Research) released with the paper by Jianwei Yang, Chunyuan Li, Xiyang Dai, Lu Yuan, Jianfeng Gao.
(from CMU/Google Brain) released with the paper by Zihang Dai, Guokun Lai, Yiming Yang, Quoc V. Le.
(from Microsoft Research) released with the paper by Jianfeng Wang, Zhengyuan Yang, Xiaowei Hu, Linjie Li, Kevin Lin, Zhe Gan, Zicheng Liu, Ce Liu, Lijuan Wang.
(from KAIST) released with the paper by Doyeon Kim, Woonghyun Ga, Pyungwhan Ahn, Donggyu Joo, Sehwan Chun, Junmo Kim.
(from OpenAI) released with the paper by Alec Radford, Karthik Narasimhan, Tim Salimans and Ilya Sutskever.
(from EleutherAI) released in the repository by Sid Black, Stella Biderman, Leo Gao, Phil Wang and Connor Leahy.
(from EleutherAI) released with the paper by Sid Black, Stella Biderman, Eric Hallahan, Quentin Anthony, Leo Gao, Laurence Golding, Horace He, Connor Leahy, Kyle McDonell, Jason Phang, Michael Pieler, USVSN Sai Prashanth, Shivanshu Purohit, Laria Reynolds, Jonathan Tow, Ben Wang, Samuel Weinbach
(from ABEJA) released by Shinya Otani, Takayoshi Makabe, Anuj Arora, and Kyo Hattori.
(from OpenAI) released with the paper by Alec Radford, Jeffrey Wu, Rewon Child, David Luan, Dario Amodeiand Ilya Sutskever.
(from EleutherAI) released in the repository by Ben Wang and Aran Komatsuzaki.
(from AI-Sweden) released with the paper by Ariel Ekgren, Amaru Cuba Gyllensten, Evangelia Gogoulou, Alice Heiman, Severine Verlinden, Joey Öhman, Fredrik Carlsson, Magnus Sahlgren.
(from BigCode) released with the paper by Loubna Ben Allal, Raymond Li, Denis Kocetkov, Chenghao Mou, Christopher Akiki, Carlos Munoz Ferrandis, Niklas Muennighoff, Mayank Mishra, Alex Gu, Manan Dey, Logesh Kumar Umapathi, Carolyn Jane Anderson, Yangtian Zi, Joel Lamy Poirier, Hailey Schoelkopf, Sergey Troshin, Dmitry Abulkhanov, Manuel Romero, Michael Lappert, Francesco De Toni, Bernardo García del Río, Qian Liu, Shamik Bose, Urvashi Bhattacharyya, Terry Yue Zhuo, Ian Yu, Paulo Villegas, Marco Zocca, Sourab Mangrulkar, David Lansky, Huu Nguyen, Danish Contractor, Luis Villa, Jia Li, Dzmitry Bahdanau, Yacine Jernite, Sean Hughes, Daniel Fried, Arjun Guha, Harm de Vries, Leandro von Werra.
released in the repository by Toshiyuki Sakamoto(tanreinama).
(from Microsoft) released with the paper by Chengxuan Ying, Tianle Cai, Shengjie Luo, Shuxin Zheng, Guolin Ke, Di He, Yanming Shen, Tie-Yan Liu.
(from UCSD, NVIDIA) released with the paper by Jiarui Xu, Shalini De Mello, Sifei Liu, Wonmin Byeon, Thomas Breuel, Jan Kautz, Xiaolong Wang.
(from Allegro.pl, AGH University of Science and Technology) released with the paper by Piotr Rybak, Robert Mroczkowski, Janusz Tracz, Ireneusz Gawlik.
(from Facebook) released with the paper by Wei-Ning Hsu, Benjamin Bolte, Yao-Hung Hubert Tsai, Kushal Lakhotia, Ruslan Salakhutdinov, Abdelrahman Mohamed.
(from Berkeley) released with the paper by Sehoon Kim, Amir Gholami, Zhewei Yao, Michael W. Mahoney, Kurt Keutzer.
(from BOINC AI) released with the paper by Hugo Laurençon, Lucile Saulnier, Léo Tronchon, Stas Bekman, Amanpreet Singh, Anton Lozhkov, Thomas Wang, Siddharth Karamcheti, Alexander M. Rush, Douwe Kiela, Matthieu Cord, Victor Sanh.
(from OpenAI) released with the paper by Mark Chen, Alec Radford, Rewon Child, Jeffrey Wu, Heewoo Jun, David Luan, Ilya Sutskever.
(from Beihang University, UC Berkeley, Rutgers University, SEDD Company) released with the paper by Haoyi Zhou, Shanghang Zhang, Jieqi Peng, Shuai Zhang, Jianxin Li, Hui Xiong, and Wancai Zhang.
(from Salesforce) released with the paper by Wenliang Dai, Junnan Li, Dongxu Li, Anthony Meng Huat Tiong, Junqi Zhao, Weisheng Wang, Boyang Li, Pascale Fung, Steven Hoi.
(from OpenAI) released with the paper by Prafulla Dhariwal, Heewoo Jun, Christine Payne, Jong Wook Kim, Alec Radford, Ilya Sutskever.
(from Microsoft Research Asia) released with the paper by Yiheng Xu, Minghao Li, Lei Cui, Shaohan Huang, Furu Wei, Ming Zhou.
(from Microsoft Research Asia) released with the paper by Yang Xu, Yiheng Xu, Tengchao Lv, Lei Cui, Furu Wei, Guoxin Wang, Yijuan Lu, Dinei Florencio, Cha Zhang, Wanxiang Che, Min Zhang, Lidong Zhou.
(from Microsoft Research Asia) released with the paper by Yupan Huang, Tengchao Lv, Lei Cui, Yutong Lu, Furu Wei.
(from Microsoft Research Asia) released with the paper by Yiheng Xu, Tengchao Lv, Lei Cui, Guoxin Wang, Yijuan Lu, Dinei Florencio, Cha Zhang, Furu Wei.
(from AllenAI) released with the paper by Iz Beltagy, Matthew E. Peters, Arman Cohan.
(from Meta AI) released with the paper by Ben Graham, Alaaeldin El-Nouby, Hugo Touvron, Pierre Stock, Armand Joulin, Hervé Jégou, Matthijs Douze.
(from South China University of Technology) released with the paper by Jiapeng Wang, Lianwen Jin, Kai Ding.
(from The FAIR team of Meta AI) released with the paper by Hugo Touvron, Thibaut Lavril, Gautier Izacard, Xavier Martinet, Marie-Anne Lachaux, Timothée Lacroix, Baptiste Rozière, Naman Goyal, Eric Hambro, Faisal Azhar, Aurelien Rodriguez, Armand Joulin, Edouard Grave, Guillaume Lample.
(from The FAIR team of Meta AI) released with the paper by Hugo Touvron, Louis Martin, Kevin Stone, Peter Albert, Amjad Almahairi, Yasmine Babaei, Nikolay Bashlykov, Soumya Batra, Prajjwal Bhargava, Shruti Bhosale, Dan Bikel, Lukas Blecher, Cristian Canton Ferrer, Moya Chen, Guillem Cucurull, David Esiobu, Jude Fernandes, Jeremy Fu, Wenyin Fu, Brian Fuller, Cynthia Gao, Vedanuj Goswami, Naman Goyal, Anthony Hartshorn, Saghar Hosseini, Rui Hou, Hakan Inan, Marcin Kardas, Viktor Kerkez Madian Khabsa, Isabel Kloumann, Artem Korenev, Punit Singh Koura, Marie-Anne Lachaux, Thibaut Lavril, Jenya Lee, Diana Liskovich, Yinghai Lu, Yuning Mao, Xavier Martinet, Todor Mihaylov, Pushka rMishra, Igor Molybog, Yixin Nie, Andrew Poulton, Jeremy Reizenstein, Rashi Rungta, Kalyan Saladi, Alan Schelten, Ruan Silva, Eric Michael Smith, Ranjan Subramanian, Xiaoqing EllenTan, Binh Tang, Ross Taylor, Adina Williams, Jian Xiang Kuan, Puxin Xu, Zheng Yan, Iliyan Zarov, Yuchen Zhang, Angela Fan, Melanie Kambadur, Sharan Narang, Aurelien Rodriguez, Robert Stojnic, Sergey Edunov, Thomas Scialom.
(from AllenAI) released with the paper by Iz Beltagy, Matthew E. Peters, Arman Cohan.
(from Google AI) released with the paper by Mandy Guo, Joshua Ainslie, David Uthus, Santiago Ontanon, Jianmo Ni, Yun-Hsuan Sung, Yinfei Yang.
(from Studio Ousia) released with the paper by Ikuya Yamada, Akari Asai, Hiroyuki Shindo, Hideaki Takeda, Yuji Matsumoto.
(from UNC Chapel Hill) released with the paper by Hao Tan and Mohit Bansal.
(from Facebook) released with the paper by Loren Lugosch, Tatiana Likhomanenko, Gabriel Synnaeve, and Ronan Collobert.
(from Facebook) released with the paper by Angela Fan, Shruti Bhosale, Holger Schwenk, Zhiyi Ma, Ahmed El-Kishky, Siddharth Goyal, Mandeep Baines, Onur Celebi, Guillaume Wenzek, Vishrav Chaudhary, Naman Goyal, Tom Birch, Vitaliy Liptchinsky, Sergey Edunov, Edouard Grave, Michael Auli, Armand Joulin.
Machine translation models trained using data by Jörg Tiedemann. The is being developed by the Microsoft Translator Team.
(from Microsoft Research Asia) released with the paper by Junlong Li, Yiheng Xu, Lei Cui, Furu Wei.
(from FAIR and UIUC) released with the paper by Bowen Cheng, Ishan Misra, Alexander G. Schwing, Alexander Kirillov, Rohit Girdhar.
(from Meta and UIUC) released with the paper by Bowen Cheng, Alexander G. Schwing, Alexander Kirillov.
(from Google AI) released with the paper by Fangyu Liu, Francesco Piccinno, Syrine Krichene, Chenxi Pang, Kenton Lee, Mandar Joshi, Yasemin Altun, Nigel Collier, Julian Martin Eisenschlos.
(from Facebook) released with the paper by Yinhan Liu, Jiatao Gu, Naman Goyal, Xian Li, Sergey Edunov, Marjan Ghazvininejad, Mike Lewis, Luke Zettlemoyer.
(from Facebook) released with the paper by Yuqing Tang, Chau Tran, Xian Li, Peng-Jen Chen, Naman Goyal, Vishrav Chaudhary, Jiatao Gu, Angela Fan.
(from Meta/USC/CMU/SJTU) released with the paper by Xuezhe Ma, Chunting Zhou, Xiang Kong, Junxian He, Liangke Gui, Graham Neubig, Jonathan May, and Luke Zettlemoyer.
(from NVIDIA) released with the paper by Mohammad Shoeybi, Mostofa Patwary, Raul Puri, Patrick LeGresley, Jared Casper and Bryan Catanzaro.
(from NVIDIA) released with the paper by Mohammad Shoeybi, Mostofa Patwary, Raul Puri, Patrick LeGresley, Jared Casper and Bryan Catanzaro.
(from Alibaba Research) released with the paper by Peng Wang, Cheng Da, and Cong Yao.
(from Mistral AI) by The team: Albert Jiang, Alexandre Sablayrolles, Arthur Mensch, Chris Bamford, Devendra Singh Chaplot, Diego de las Casas, Florian Bressand, Gianna Lengyel, Guillaume Lample, Lélio Renard Lavaud, Lucile Saulnier, Marie-Anne Lachaux, Pierre Stock, Teven Le Scao, Thibaut Lavril, Thomas Wang, Timothée Lacroix, William El Sayed.
(from Studio Ousia) released with the paper by Ryokan Ri, Ikuya Yamada, and Yoshimasa Tsuruoka.
(from Facebook) released with the paper by Vineel Pratap, Andros Tjandra, Bowen Shi, Paden Tomasello, Arun Babu, Sayani Kundu, Ali Elkahky, Zhaoheng Ni, Apoorv Vyas, Maryam Fazel-Zarandi, Alexei Baevski, Yossi Adi, Xiaohui Zhang, Wei-Ning Hsu, Alexis Conneau, Michael Auli.
(from CMU/Google Brain) released with the paper by Zhiqing Sun, Hongkun Yu, Xiaodan Song, Renjie Liu, Yiming Yang, and Denny Zhou.
(from Google Inc.) released with the paper by Andrew G. Howard, Menglong Zhu, Bo Chen, Dmitry Kalenichenko, Weijun Wang, Tobias Weyand, Marco Andreetto, Hartwig Adam.
(from Google Inc.) released with the paper by Mark Sandler, Andrew Howard, Menglong Zhu, Andrey Zhmoginov, Liang-Chieh Chen.
(from Apple) released with the paper by Sachin Mehta and Mohammad Rastegari.
(from Apple) released with the paper by Sachin Mehta and Mohammad Rastegari.
(from Microsoft Research) released with the paper by Kaitao Song, Xu Tan, Tao Qin, Jianfeng Lu, Tie-Yan Liu.
(from MosaiML) released with the repository by the MosaicML NLP Team.
(from the University of Wisconsin - Madison) released with the paper by Zhanpeng Zeng, Sourav Pal, Jeffery Kline, Glenn M Fung, Vikas Singh.
(from Google AI) released with the paper by Linting Xue, Noah Constant, Adam Roberts, Mihir Kale, Rami Al-Rfou, Aditya Siddhant, Aditya Barua, Colin Raffel.
(from Meta) released with the paper by Jade Copet, Felix Kreuk, Itai Gat, Tal Remez, David Kant, Gabriel Synnaeve, Yossi Adi and Alexandre Défossez.
(from RUC AI Box) released with the paper by Tianyi Tang, Junyi Li, Wayne Xin Zhao and Ji-Rong Wen.
(from SHI Labs) released with the paper by Ali Hassani, Steven Walton, Jiachen Li, Shen Li, and Humphrey Shi.
(from Huawei Noah’s Ark Lab) released with the paper by Junqiu Wei, Xiaozhe Ren, Xiaoguang Li, Wenyong Huang, Yi Liao, Yasheng Wang, Jiashu Lin, Xin Jiang, Xiao Chen and Qun Liu.
(from Meta) released with the paper by the NLLB team.
(from Meta) released with the paper by the NLLB team.
(from Meta AI) released with the paper by Lukas Blecher, Guillem Cucurull, Thomas Scialom, Robert Stojnic.
(from the University of Wisconsin - Madison) released with the paper by Yunyang Xiong, Zhanpeng Zeng, Rudrasis Chakraborty, Mingxing Tan, Glenn Fung, Yin Li, Vikas Singh.
(from SHI Labs) released with the paper by Jitesh Jain, Jiachen Li, MangTik Chiu, Ali Hassani, Nikita Orlov, Humphrey Shi.
(from ) released in .
(from Meta AI) released with the paper by Susan Zhang, Stephen Roller, Naman Goyal, Mikel Artetxe, Moya Chen, Shuohui Chen et al.
(from Google AI) released with the paper by Matthias Minderer, Alexey Gritsenko, Austin Stone, Maxim Neumann, Dirk Weissenborn, Alexey Dosovitskiy, Aravindh Mahendran, Anurag Arnab, Mostafa Dehghani, Zhuoran Shen, Xiao Wang, Xiaohua Zhai, Thomas Kipf, and Neil Houlsby.
(from Google) released with the paper by Jingqing Zhang, Yao Zhao, Mohammad Saleh and Peter J. Liu.
(from Google) released with the paper by Jason Phang, Yao Zhao, and Peter J. Liu.
(from Deepmind) released with the paper by Andrew Jaegle, Sebastian Borgeaud, Jean-Baptiste Alayrac, Carl Doersch, Catalin Ionescu, David Ding, Skanda Koppula, Daniel Zoran, Andrew Brock, Evan Shelhamer, Olivier Hénaff, Matthew M. Botvinick, Andrew Zisserman, Oriol Vinyals, João Carreira.
(from ADEPT) released in a by Erich Elsen, Augustus Odena, Maxwell Nye, Sağnak Taşırlar, Tri Dao, Curtis Hawthorne, Deepak Moparthi, Arushi Somani.
(from VinAI Research) released with the paper by Dat Quoc Nguyen and Anh Tuan Nguyen.
(from Google) released with the paper by Kenton Lee, Mandar Joshi, Iulia Turc, Hexiang Hu, Fangyu Liu, Julian Eisenschlos, Urvashi Khandelwal, Peter Shaw, Ming-Wei Chang, Kristina Toutanova.
(from UCLA NLP) released with the paper by Wasi Uddin Ahmad, Saikat Chakraborty, Baishakhi Ray, Kai-Wei Chang.
(from Sea AI Labs) released with the paper by Yu, Weihao and Luo, Mi and Zhou, Pan and Si, Chenyang and Zhou, Yichen and Wang, Xinchao and Feng, Jiashi and Yan, Shuicheng.
released with the paper by Jongho Choi and Kyogu Lee.
(from Microsoft Research) released with the paper by Yu Yan, Weizhen Qi, Yeyun Gong, Dayiheng Liu, Nan Duan, Jiusheng Chen, Ruofei Zhang and Ming Zhou.
(from Nanjing University, The University of Hong Kong etc.) released with the paper by Wenhai Wang, Enze Xie, Xiang Li, Deng-Ping Fan, Kaitao Song, Ding Liang, Tong Lu, Ping Luo, Ling Shao.
(from NVIDIA) released with the paper by Hao Wu, Patrick Judd, Xiaojie Zhang, Mikhail Isaev and Paulius Micikevicius.
(from Facebook) released with the paper by Patrick Lewis, Ethan Perez, Aleksandara Piktus, Fabio Petroni, Vladimir Karpukhin, Naman Goyal, Heinrich Küttler, Mike Lewis, Wen-tau Yih, Tim Rocktäschel, Sebastian Riedel, Douwe Kiela.
(from Google Research) released with the paper by Kelvin Guu, Kenton Lee, Zora Tung, Panupong Pasupat and Ming-Wei Chang.
(from Google Research) released with the paper by Nikita Kitaev, Łukasz Kaiser, Anselm Levskaya.
(from META Platforms) released with the paper by Ilija Radosavovic, Raj Prateek Kosaraju, Ross Girshick, Kaiming He, Piotr Dollár.
(from Google Research) released with the paper by Hyung Won Chung, Thibault Févry, Henry Tsai, M. Johnson, Sebastian Ruder.
(from Microsoft Research) released with the paper by Kaiming He, Xiangyu Zhang, Shaoqing Ren, Jian Sun.
(from Facebook), released together with the paper by Yinhan Liu, Myle Ott, Naman Goyal, Jingfei Du, Mandar Joshi, Danqi Chen, Omer Levy, Mike Lewis, Luke Zettlemoyer, Veselin Stoyanov.
(from Facebook) released with the paper by Myle Ott, Sergey Edunov, Alexei Baevski, Angela Fan, Sam Gross, Nathan Ng, David Grangier, Michael Auli.
(from WeChatAI) released with the paper by HuiSu, WeiweiShi, XiaoyuShen, XiaoZhou, TuoJi, JiaruiFang, JieZhou.
(from ZhuiyiTechnology), released together with the paper by Jianlin Su and Yu Lu and Shengfeng Pan and Bo Wen and Yunfeng Liu.
(from Bo Peng), released on by Bo Peng.
(from NVIDIA) released with the paper by Enze Xie, Wenhai Wang, Zhiding Yu, Anima Anandkumar, Jose M. Alvarez, Ping Luo.
(from Meta AI) released with the paper by Alexander Kirillov, Eric Mintun, Nikhila Ravi, Hanzi Mao, Chloe Rolland, Laura Gustafson, Tete Xiao, Spencer Whitehead, Alex Berg, Wan-Yen Lo, Piotr Dollar, Ross Girshick.
(from ASAPP) released with the paper by Felix Wu, Kwangyoun Kim, Jing Pan, Kyu Han, Kilian Q. Weinberger, Yoav Artzi.
(from ASAPP) released with the paper by Felix Wu, Kwangyoun Kim, Jing Pan, Kyu Han, Kilian Q. Weinberger, Yoav Artzi.
(from Microsoft Research) released with the paper by Junyi Ao, Rui Wang, Long Zhou, Chengyi Wang, Shuo Ren, Yu Wu, Shujie Liu, Tom Ko, Qing Li, Yu Zhang, Zhihua Wei, Yao Qian, Jinyu Li, Furu Wei.
(from Facebook), released together with the paper by Changhan Wang, Yun Tang, Xutai Ma, Anne Wu, Dmytro Okhonko, Juan Pino.
(from Facebook), released together with the paper by Changhan Wang, Anne Wu, Juan Pino, Alexei Baevski, Michael Auli, Alexis Conneau.
(from Tel Aviv University), released together with the paper by Ori Ram, Yuval Kirstain, Jonathan Berant, Amir Globerson, Omer Levy.
(from Berkeley) released with the paper by Forrest N. Iandola, Albert E. Shaw, Ravi Krishna, and Kurt W. Keutzer.
(from MBZUAI) released with the paper by Abdelrahman Shaker, Muhammad Maaz, Hanoona Rasheed, Salman Khan, Ming-Hsuan Yang, Fahad Shahbaz Khan.
(from Microsoft) released with the paper by Ze Liu, Yutong Lin, Yue Cao, Han Hu, Yixuan Wei, Zheng Zhang, Stephen Lin, Baining Guo.
(from Microsoft) released with the paper by Ze Liu, Han Hu, Yutong Lin, Zhuliang Yao, Zhenda Xie, Yixuan Wei, Jia Ning, Yue Cao, Zheng Zhang, Li Dong, Furu Wei, Baining Guo.
(from University of Würzburg) released with the paper by Marcos V. Conde, Ui-Jin Choi, Maxime Burchi, Radu Timofte.
(from Google) released with the paper by William Fedus, Barret Zoph, Noam Shazeer.
(from Google AI) released with the paper by Colin Raffel and Noam Shazeer and Adam Roberts and Katherine Lee and Sharan Narang and Michael Matena and Yanqi Zhou and Wei Li and Peter J. Liu.
(from Google AI) released in the repository by Colin Raffel and Noam Shazeer and Adam Roberts and Katherine Lee and Sharan Narang and Michael Matena and Yanqi Zhou and Wei Li and Peter J. Liu.
(from Microsoft Research) released with the paper by Brandon Smock, Rohith Pesala, Robin Abraham.
(from Google AI) released with the paper by Jonathan Herzig, Paweł Krzysztof Nowak, Thomas Müller, Francesco Piccinno and Julian Martin Eisenschlos.
(from Microsoft Research) released with the paper by Qian Liu, Bei Chen, Jiaqi Guo, Morteza Ziyadi, Zeqi Lin, Weizhu Chen, Jian-Guang Lou.
(from BOINC AI).
(from Facebook) released with the paper by Gedas Bertasius, Heng Wang, Lorenzo Torresani.
(from the University of California at Berkeley) released with the paper by Michael Janner, Qiyang Li, Sergey Levine
(from Google/CMU) released with the paper by Zihang Dai, Zhilin Yang, Yiming Yang, Jaime Carbonell, Quoc V. Le, Ruslan Salakhutdinov.
(from Microsoft), released together with the paper by Minghao Li, Tengchao Lv, Lei Cui, Yijuan Lu, Dinei Florencio, Cha Zhang, Zhoujun Li, Furu Wei.
(from UNC Chapel Hill) released with the paper by Zineng Tang, Jaemin Cho, Yixin Nie, Mohit Bansal.
(from Google Research) released with the paper by Yi Tay, Mostafa Dehghani, Vinh Q. Tran, Xavier Garcia, Dara Bahri, Tal Schuster, Huaixiu Steven Zheng, Neil Houlsby, Donald Metzler
(from Google Research) released with the paper by Hyung Won Chung, Xavier Garcia, Adam Roberts, Yi Tay, Orhan Firat, Sharan Narang, Noah Constant.
(from Microsoft Research) released with the paper by Chengyi Wang, Yu Wu, Yao Qian, Kenichi Kumatani, Shujie Liu, Furu Wei, Michael Zeng, Xuedong Huang.
(from Microsoft Research) released with the paper by Sanyuan Chen, Yu Wu, Chengyi Wang, Zhengyang Chen, Zhuo Chen, Shujie Liu, Jian Wu, Yao Qian, Furu Wei, Jinyu Li, Xiangzhan Yu.
(from Peking University) released with the paper by Tete Xiao, Yingcheng Liu, Bolei Zhou, Yuning Jiang, Jian Sun.
(from Tsinghua University and Nankai University) released with the paper by Meng-Hao Guo, Cheng-Ze Lu, Zheng-Ning Liu, Ming-Ming Cheng, Shi-Min Hu.
(from Multimedia Computing Group, Nanjing University) released with the paper by Zhan Tong, Yibing Song, Jue Wang, Limin Wang.
(from NAVER AI Lab/Kakao Enterprise/Kakao Brain) released with the paper by Wonjae Kim, Bokyung Son, Ildoo Kim.
(from Google AI) released with the paper by Alexey Dosovitskiy, Lucas Beyer, Alexander Kolesnikov, Dirk Weissenborn, Xiaohua Zhai, Thomas Unterthiner, Mostafa Dehghani, Matthias Minderer, Georg Heigold, Sylvain Gelly, Jakob Uszkoreit, Neil Houlsby.
(from UCLA NLP) released with the paper by Liunian Harold Li, Mark Yatskar, Da Yin, Cho-Jui Hsieh, Kai-Wei Chang.
(from Google AI) released with the paper by Alexey Dosovitskiy, Lucas Beyer, Alexander Kolesnikov, Dirk Weissenborn, Xiaohua Zhai, Thomas Unterthiner, Mostafa Dehghani, Matthias Minderer, Georg Heigold, Sylvain Gelly, Jakob Uszkoreit, Neil Houlsby.
(from Meta AI) released with the paper by Yanghao Li, Hanzi Mao, Ross Girshick, Kaiming He.
(from Meta AI) released with the paper by Kaiming He, Xinlei Chen, Saining Xie, Yanghao Li, Piotr Dollár, Ross Girshick.
(from HUST-VL) rreleased with the paper by Jingfeng Yao, Xinggang Wang, Shusheng Yang, Baoyuan Wang.
(from Meta AI) released with the paper by Mahmoud Assran, Mathilde Caron, Ishan Misra, Piotr Bojanowski, Florian Bordes, Pascal Vincent, Armand Joulin, Michael Rabbat, Nicolas Ballas.
(from Kakao Enterprise) released with the paper by Jaehyeon Kim, Jungil Kong, Juhee Son.
(from Google Research) released with the paper by Anurag Arnab, Mostafa Dehghani, Georg Heigold, Chen Sun, Mario Lučić, Cordelia Schmid.
(from Facebook AI) released with the paper by Alexei Baevski, Henry Zhou, Abdelrahman Mohamed, Michael Auli.
(from Facebook AI) released with the paper by Changhan Wang, Yun Tang, Xutai Ma, Anne Wu, Sravya Popuri, Dmytro Okhonko, Juan Pino.
(from Facebook AI) released with the paper by Qiantong Xu, Alexei Baevski, Michael Auli.
(from Microsoft Research) released with the paper by Sanyuan Chen, Chengyi Wang, Zhengyang Chen, Yu Wu, Shujie Liu, Zhuo Chen, Jinyu Li, Naoyuki Kanda, Takuya Yoshioka, Xiong Xiao, Jian Wu, Long Zhou, Shuo Ren, Yanmin Qian, Yao Qian, Jian Wu, Michael Zeng, Furu Wei.
(from OpenAI) released with the paper by Alec Radford, Jong Wook Kim, Tao Xu, Greg Brockman, Christine McLeavey, Ilya Sutskever.
(from Microsoft Research) released with the paper by Bolin Ni, Houwen Peng, Minghao Chen, Songyang Zhang, Gaofeng Meng, Jianlong Fu, Shiming Xiang, Haibin Ling.
(from Meta AI) released with the paper by Jonas Pfeiffer, Naman Goyal, Xi Lin, Xian Li, James Cross, Sebastian Riedel, Mikel Artetxe.
(From Facebook AI) released with the paper by Xi Victoria Lin, Todor Mihaylov, Mikel Artetxe, Tianlu Wang, Shuohui Chen, Daniel Simig, Myle Ott, Naman Goyal, Shruti Bhosale, Jingfei Du, Ramakanth Pasunuru, Sam Shleifer, Punit Singh Koura, Vishrav Chaudhary, Brian O’Horo, Jeff Wang, Luke Zettlemoyer, Zornitsa Kozareva, Mona Diab, Veselin Stoyanov, Xian Li.
(from Facebook) released together with the paper by Guillaume Lample and Alexis Conneau.
(from Microsoft Research) released with the paper by Yu Yan, Weizhen Qi, Yeyun Gong, Dayiheng Liu, Nan Duan, Jiusheng Chen, Ruofei Zhang and Ming Zhou.
(from Facebook AI), released together with the paper by Alexis Conneau, Kartikay Khandelwal, Naman Goyal, Vishrav Chaudhary, Guillaume Wenzek, Francisco Guzmán, Edouard Grave, Myle Ott, Luke Zettlemoyer and Veselin Stoyanov.
(from Facebook AI), released together with the paper by Naman Goyal, Jingfei Du, Myle Ott, Giri Anantharaman, Alexis Conneau.
(from Meta AI) released with the paper by Davis Liang, Hila Gonen, Yuning Mao, Rui Hou, Naman Goyal, Marjan Ghazvininejad, Luke Zettlemoyer, Madian Khabsa.
(from Google/CMU) released with the paper by Zhilin Yang, Zihang Dai, Yiming Yang, Jaime Carbonell, Ruslan Salakhutdinov, Quoc V. Le.
(from Facebook AI) released with the paper by Arun Babu, Changhan Wang, Andros Tjandra, Kushal Lakhotia, Qiantong Xu, Naman Goyal, Kritika Singh, Patrick von Platen, Yatharth Saraf, Juan Pino, Alexei Baevski, Alexis Conneau, Michael Auli.
(from Facebook AI) released with the paper by Alexis Conneau, Alexei Baevski, Ronan Collobert, Abdelrahman Mohamed, Michael Auli.
(from Huazhong University of Science & Technology) released with the paper by Yuxin Fang, Bencheng Liao, Xinggang Wang, Jiemin Fang, Jiyang Qi, Rui Wu, Jianwei Niu, Wenyu Liu.
(from the University of Wisconsin - Madison) released with the paper by Zhanpeng Zeng, Yunyang Xiong, Sathya N. Ravi, Shailesh Acharya, Glenn Fung, Vikas Singh.
The table below represents the current support in the library for each of those models, whether they have a Python tokenizer (called “slow”). A “fast” tokenizer backed by the 🌍 Tokenizers library, whether they have support in Jax (via Flax), PyTorch, and/or TensorFlow.
ALBERT
✅
✅
✅
ALIGN
✅
❌
❌
AltCLIP
✅
❌
❌
Audio Spectrogram Transformer
✅
❌
❌
Autoformer
✅
❌
❌
Bark
✅
❌
❌
BART
✅
✅
✅
BEiT
✅
❌
✅
BERT
✅
✅
✅
Bert Generation
✅
❌
❌
BigBird
✅
❌
✅
BigBird-Pegasus
✅
❌
❌
BioGpt
✅
❌
❌
BiT
✅
❌
❌
Blenderbot
✅
✅
✅
BlenderbotSmall
✅
✅
✅
BLIP
✅
✅
❌
BLIP-2
✅
❌
❌
BLOOM
✅
❌
✅
BridgeTower
✅
❌
❌
BROS
✅
❌
❌
CamemBERT
✅
✅
❌
CANINE
✅
❌
❌
Chinese-CLIP
✅
❌
❌
CLAP
✅
❌
❌
CLIP
✅
✅
✅
CLIPSeg
✅
❌
❌
CodeGen
✅
❌
❌
CodeLlama
✅
❌
❌
Conditional DETR
✅
❌
❌
ConvBERT
✅
✅
❌
ConvNeXT
✅
✅
❌
ConvNeXTV2
✅
❌
❌
CPM-Ant
✅
❌
❌
CTRL
✅
✅
❌
CvT
✅
✅
❌
Data2VecAudio
✅
❌
❌
Data2VecText
✅
❌
❌
Data2VecVision
✅
✅
❌
DeBERTa
✅
✅
❌
DeBERTa-v2
✅
✅
❌
Decision Transformer
✅
❌
❌
Deformable DETR
✅
❌
❌
DeiT
✅
✅
❌
DETA
✅
❌
❌
DETR
✅
❌
❌
DiNAT
✅
❌
❌
DINOv2
✅
❌
❌
DistilBERT
✅
✅
✅
DonutSwin
✅
❌
❌
DPR
✅
✅
❌
DPT
✅
❌
❌
EfficientFormer
✅
✅
❌
EfficientNet
✅
❌
❌
ELECTRA
✅
✅
✅
EnCodec
✅
❌
❌
Encoder decoder
✅
✅
✅
ERNIE
✅
❌
❌
ErnieM
✅
❌
❌
ESM
✅
✅
❌
FairSeq Machine-Translation
✅
❌
❌
Falcon
✅
❌
❌
FlauBERT
✅
✅
❌
FLAVA
✅
❌
❌
FNet
✅
❌
❌
FocalNet
✅
❌
❌
Funnel Transformer
✅
✅
❌
GIT
✅
❌
❌
GLPN
✅
❌
❌
GPT Neo
✅
❌
✅
GPT NeoX
✅
❌
❌
GPT NeoX Japanese
✅
❌
❌
GPT-J
✅
✅
✅
GPT-Sw3
✅
✅
✅
GPTBigCode
✅
❌
❌
GPTSAN-japanese
✅
❌
❌
Graphormer
✅
❌
❌
GroupViT
✅
✅
❌
Hubert
✅
✅
❌
I-BERT
✅
❌
❌
IDEFICS
✅
❌
❌
ImageGPT
✅
❌
❌
Informer
✅
❌
❌
InstructBLIP
✅
❌
❌
Jukebox
✅
❌
❌
LayoutLM
✅
✅
❌
LayoutLMv2
✅
❌
❌
LayoutLMv3
✅
✅
❌
LED
✅
✅
❌
LeViT
✅
❌
❌
LiLT
✅
❌
❌
LLaMA
✅
❌
❌
Longformer
✅
✅
❌
LongT5
✅
❌
✅
LUKE
✅
❌
❌
LXMERT
✅
✅
❌
M-CTC-T
✅
❌
❌
M2M100
✅
❌
❌
Marian
✅
✅
✅
MarkupLM
✅
❌
❌
Mask2Former
✅
❌
❌
MaskFormer
✅
❌
❌
mBART
✅
✅
✅
MEGA
✅
❌
❌
Megatron-BERT
✅
❌
❌
MGP-STR
✅
❌
❌
Mistral
✅
❌
❌
MobileBERT
✅
✅
❌
MobileNetV1
✅
❌
❌
MobileNetV2
✅
❌
❌
MobileViT
✅
✅
❌
MobileViTV2
✅
❌
❌
MPNet
✅
✅
❌
MPT
✅
❌
❌
MRA
✅
❌
❌
MT5
✅
✅
✅
MusicGen
✅
❌
❌
MVP
✅
❌
❌
NAT
✅
❌
❌
Nezha
✅
❌
❌
NLLB-MOE
✅
❌
❌
Nougat
✅
✅
✅
Nyströmformer
✅
❌
❌
OneFormer
✅
❌
❌
OpenAI GPT
✅
✅
❌
OpenAI GPT-2
✅
✅
✅
OpenLlama
✅
❌
❌
OPT
✅
✅
✅
OWL-ViT
✅
❌
❌
Pegasus
✅
✅
✅
PEGASUS-X
✅
❌
❌
Perceiver
✅
❌
❌
Persimmon
✅
❌
❌
Pix2Struct
✅
❌
❌
PLBart
✅
❌
❌
PoolFormer
✅
❌
❌
Pop2Piano
✅
❌
❌
ProphetNet
✅
❌
❌
PVT
✅
❌
❌
QDQBert
✅
❌
❌
RAG
✅
✅
❌
REALM
✅
❌
❌
Reformer
✅
❌
❌
RegNet
✅
✅
✅
RemBERT
✅
✅
❌
ResNet
✅
✅
✅
RetriBERT
✅
❌
❌
RoBERTa
✅
✅
✅
RoBERTa-PreLayerNorm
✅
✅
✅
RoCBert
✅
❌
❌
RoFormer
✅
✅
✅
RWKV
✅
❌
❌
SAM
✅
✅
❌
SegFormer
✅
✅
❌
SEW
✅
❌
❌
SEW-D
✅
❌
❌
Speech Encoder decoder
✅
❌
✅
Speech2Text
✅
✅
❌
Speech2Text2
❌
❌
❌
SpeechT5
✅
❌
❌
Splinter
✅
❌
❌
SqueezeBERT
✅
❌
❌
SwiftFormer
✅
❌
❌
Swin Transformer
✅
✅
❌
Swin Transformer V2
✅
❌
❌
Swin2SR
✅
❌
❌
SwitchTransformers
✅
❌
❌
T5
✅
✅
✅
Table Transformer
✅
❌
❌
TAPAS
✅
✅
❌
Time Series Transformer
✅
❌
❌
TimeSformer
✅
❌
❌
Trajectory Transformer
✅
❌
❌
Transformer-XL
✅
✅
❌
TrOCR
✅
❌
❌
TVLT
✅
❌
❌
UMT5
✅
❌
❌
UniSpeech
✅
❌
❌
UniSpeechSat
✅
❌
❌
UPerNet
✅
❌
❌
VAN
✅
❌
❌
VideoMAE
✅
❌
❌
ViLT
✅
❌
❌
Vision Encoder decoder
✅
✅
✅
VisionTextDualEncoder
✅
✅
✅
VisualBERT
✅
❌
❌
ViT
✅
✅
✅
ViT Hybrid
✅
❌
❌
VitDet
✅
❌
❌
ViTMAE
✅
✅
❌
ViTMatte
✅
❌
❌
ViTMSN
✅
❌
❌
VITS
✅
❌
❌
ViViT
✅
❌
❌
Wav2Vec2
✅
✅
✅
Wav2Vec2-Conformer
✅
❌
❌
WavLM
✅
❌
❌
Whisper
✅
✅
✅
X-CLIP
✅
❌
❌
X-MOD
✅
❌
❌
XGLM
✅
✅
✅
XLM
✅
✅
❌
XLM-ProphetNet
✅
❌
❌
XLM-RoBERTa
✅
✅
✅
XLM-RoBERTa-XL
✅
❌
❌
XLNet
✅
✅
❌
YOLOS
✅
❌
❌
YOSO
✅
❌
❌