@misc{glassllm_transformer_2017,
  title = {Attention Is All You Need},
  author = {Ashish Vaswani and Noam Shazeer and Niki Parmar and Jakob Uszkoreit and Llion Jones and Aidan N. Gomez and Lukasz Kaiser and Illia Polosukhin},
  year = {2017},
  eprint = {1706.03762},
  archivePrefix = {arXiv},
  doi = {10.48550/arXiv.1706.03762},
  url = {https://arxiv.org/abs/1706.03762}
}

@misc{glassllm_bpe_2015,
  title = {Neural Machine Translation of Rare Words with Subword Units},
  author = {Rico Sennrich and Barry Haddow and Alexandra Birch},
  year = {2015},
  eprint = {1508.07909},
  archivePrefix = {arXiv},
  doi = {10.48550/arXiv.1508.07909},
  url = {https://arxiv.org/abs/1508.07909}
}

@misc{glassllm_sentencepiece_2018,
  title = {SentencePiece: A simple and language independent subword tokenizer and detokenizer for Neural Text Processing},
  author = {Taku Kudo and John Richardson},
  year = {2018},
  eprint = {1808.06226},
  archivePrefix = {arXiv},
  doi = {10.48550/arXiv.1808.06226},
  url = {https://arxiv.org/abs/1808.06226}
}

@misc{glassllm_rope_2021,
  title = {RoFormer: Enhanced Transformer with Rotary Position Embedding},
  author = {Jianlin Su and Yu Lu and Shengfeng Pan and Ahmed Murtadha and Bo Wen and Yunfeng Liu},
  year = {2021},
  eprint = {2104.09864},
  archivePrefix = {arXiv},
  doi = {10.48550/arXiv.2104.09864},
  url = {https://arxiv.org/abs/2104.09864}
}

@misc{glassllm_gqa_2023,
  title = {GQA: Training Generalized Multi-Query Transformer Models from Multi-Head Checkpoints},
  author = {Joshua Ainslie and James Lee-Thorp and Michiel de Jong and Yury Zemlyanskiy and Federico Lebrón and Sumit Sanghai},
  year = {2023},
  eprint = {2305.13245},
  archivePrefix = {arXiv},
  doi = {10.48550/arXiv.2305.13245},
  url = {https://arxiv.org/abs/2305.13245}
}

@misc{glassllm_rmsnorm_2019,
  title = {Root Mean Square Layer Normalization},
  author = {Biao Zhang and Rico Sennrich},
  year = {2019},
  eprint = {1910.07467},
  archivePrefix = {arXiv},
  doi = {10.48550/arXiv.1910.07467},
  url = {https://arxiv.org/abs/1910.07467}
}

@misc{glassllm_prenorm_2020,
  title = {On Layer Normalization in the Transformer Architecture},
  author = {Ruibin Xiong and Yunchang Yang and Di He and Kai Zheng and Shuxin Zheng and Chen Xing and Huishuai Zhang and Yanyan Lan and Liwei Wang and Tie-Yan Liu},
  year = {2020},
  eprint = {2002.04745},
  archivePrefix = {arXiv},
  doi = {10.48550/arXiv.2002.04745},
  url = {https://arxiv.org/abs/2002.04745}
}

@misc{glassllm_residual_2015,
  title = {Deep Residual Learning for Image Recognition},
  author = {Kaiming He and Xiangyu Zhang and Shaoqing Ren and Jian Sun},
  year = {2015},
  eprint = {1512.03385},
  archivePrefix = {arXiv},
  doi = {10.48550/arXiv.1512.03385},
  url = {https://arxiv.org/abs/1512.03385}
}

@misc{glassllm_swiglu_2020,
  title = {GLU Variants Improve Transformer},
  author = {Noam Shazeer},
  year = {2020},
  eprint = {2002.05202},
  archivePrefix = {arXiv},
  doi = {10.48550/arXiv.2002.05202},
  url = {https://arxiv.org/abs/2002.05202}
}

@misc{glassllm_tied_2016,
  title = {Using the Output Embedding to Improve Language Models},
  author = {Ofir Press and Lior Wolf},
  year = {2016},
  eprint = {1608.05859},
  archivePrefix = {arXiv},
  doi = {10.48550/arXiv.1608.05859},
  url = {https://arxiv.org/abs/1608.05859}
}

@misc{glassllm_autodiff_2015,
  title = {Automatic differentiation in machine learning: a survey},
  author = {Atilim Gunes Baydin and Barak A. Pearlmutter and Alexey Andreyevich Radul and Jeffrey Mark Siskind},
  year = {2015},
  eprint = {1502.05767},
  archivePrefix = {arXiv},
  doi = {10.48550/arXiv.1502.05767},
  url = {https://arxiv.org/abs/1502.05767}
}

@misc{glassllm_adam_2014,
  title = {Adam: A Method for Stochastic Optimization},
  author = {Diederik P. Kingma and Jimmy Ba},
  year = {2014},
  eprint = {1412.6980},
  archivePrefix = {arXiv},
  doi = {10.48550/arXiv.1412.6980},
  url = {https://arxiv.org/abs/1412.6980}
}

@misc{glassllm_adamw_2017,
  title = {Decoupled Weight Decay Regularization},
  author = {Ilya Loshchilov and Frank Hutter},
  year = {2017},
  eprint = {1711.05101},
  archivePrefix = {arXiv},
  doi = {10.48550/arXiv.1711.05101},
  url = {https://arxiv.org/abs/1711.05101}
}

@misc{glassllm_cosine_2016,
  title = {SGDR: Stochastic Gradient Descent with Warm Restarts},
  author = {Ilya Loshchilov and Frank Hutter},
  year = {2016},
  eprint = {1608.03983},
  archivePrefix = {arXiv},
  doi = {10.48550/arXiv.1608.03983},
  url = {https://arxiv.org/abs/1608.03983}
}
