| Exploring the limits of transfer learning with a unified text-to-text transformer C Raffel, N Shazeer, A Roberts, K Lee, S Narang, M Matena, Y Zhou, W Li, ... Journal of machine learning research 21 (140), 1-67, 2020 | 18107 | 2020 |
| Llama 2: Open foundation and fine-tuned chat models H Touvron, L Martin, K Stone, P Albert, A Almahairi, Y Babaei, ... arXiv preprint arXiv:2307.09288, 2023 | 8384 | 2023 |
| Palm: Scaling language modeling with pathways A Chowdhery, S Narang, J Devlin, M Bosma, G Mishra, A Roberts, ... Journal of Machine Learning Research 24 (240), 1-113, 2023 | 4508 | 2023 |
| Deep speech 2: End-to-end speech recognition in english and mandarin D Amodei, S Ananthanarayanan, R Anubhai, J Bai, E Battenberg, C Case, ... International conference on machine learning, 173-182, 2016 | 3773 | 2016 |
| Scaling instruction-finetuned language models HW Chung, L Hou, S Longpre, B Zoph, Y Tay, W Fedus, Y Li, X Wang, ... Journal of Machine Learning Research 25 (70), 1-53, 2024 | 2502 | 2024 |
| Mixed precision training P Micikevicius, S Narang, J Alben, G Diamos, E Elsen, D Garcia, ... arXiv preprint arXiv:1710.03740, 2017 | 1907 | 2017 |
| Self-consistency improves chain of thought reasoning in language models X Wang, J Wei, D Schuurmans, Q Le, E Chi, S Narang, A Chowdhery, ... arXiv preprint arXiv:2203.11171, 2022 | 894 | 2022 |
| Deep voice 3: Scaling text-to-speech with convolutional sequence learning W Ping, K Peng, A Gibiansky, SO Arik, A Kannan, S Narang, J Raiman, ... arXiv preprint arXiv:1710.07654, 2017 | 882* | 2017 |
| Deep learning scaling is predictable, empirically J Hestness, S Narang, N Ardalani, G Diamos, H Jun, H Kianinejad, ... arXiv preprint arXiv:1712.00409, 2017 | 722 | 2017 |
| Byt5: Towards a token-free future with pre-trained byte-to-byte models L Xue, A Barua, N Constant, R Al-Rfou, S Narang, M Kale, A Roberts, ... Transactions of the Association for Computational Linguistics 10, 291-306, 2022 | 375 | 2022 |
| Exploring sparsity in recurrent neural networks S Narang, E Elsen, G Diamos, S Sengupta arXiv preprint arXiv:1704.05119, 2017 | 364 | 2017 |
| DSD: regularizing deep neural networks with dense-sparse-dense training flow S Han, J Pool, S Narang, H Mao, S Tang, E Elsen, B Catanzaro, J Tran, ... arXiv preprint arXiv:1607.04381 3 (6), 2016 | 336* | 2016 |
| The llama 3 herd of models A Dubey, A Jauhri, A Pandey, A Kadian, A Al-Dahle, A Letman, A Mathur, ... arXiv preprint arXiv:2407.21783, 2024 | 220 | 2024 |
| Wt5?! training text-to-text models to explain their predictions S Narang, C Raffel, K Lee, A Roberts, N Fiedel, K Malkan arXiv preprint arXiv:2004.14546, 2020 | 192 | 2020 |
| Block-sparse recurrent neural networks S Narang, E Undersander, G Diamos arXiv preprint arXiv:1711.02782, 2017 | 155 | 2017 |
| Scaling up models and data with t5x and seqio A Roberts, HW Chung, G Mishra, A Levskaya, J Bradbury, D Andor, ... Journal of Machine Learning Research 24 (377), 1-8, 2023 | 143 | 2023 |
| Scale efficiently: Insights from pre-training and fine-tuning transformers Y Tay, M Dehghani, J Rao, W Fedus, S Abnar, HW Chung, S Narang, ... arXiv preprint arXiv:2109.10686, 2021 | 125 | 2021 |
| Effective long-context scaling of foundation models W Xiong, J Liu, I Molybog, H Zhang, P Bhargava, R Hou, L Martin, ... arXiv preprint arXiv:2309.16039, 2023 | 103 | 2023 |
| Palm: Scaling language modeling with pathways. arXiv 2022 A Chowdhery, S Narang, J Devlin, M Bosma, G Mishra, A Roberts, ... arXiv preprint arXiv:2204.02311 10, 2022 | 103 | 2022 |
| Do transformer modifications transfer across implementations and applications? S Narang, HW Chung, Y Tay, W Fedus, T Fevry, M Matena, K Malkan, ... arXiv preprint arXiv:2102.11972, 2021 | 94 | 2021 |
