Zobrazeno 1 - 10
of 2 804
pro vyhledávání: '"Harris, Ian"'
This study introduces an approach to optimize Parameter Efficient Fine Tuning (PEFT) for Pretrained Language Models (PLMs) by implementing a Shared Low Rank Adaptation (ShareLoRA). By strategically deploying ShareLoRA across different layers and adap
Externí odkaz:
http://arxiv.org/abs/2406.10785
Deploying Large Language Models (LLMs) locally on mobile devices presents a significant challenge due to their extensive memory requirements. In this paper, we introduce LinguaLinked, a system for decentralized, distributed LLM inference on mobile de
Externí odkaz:
http://arxiv.org/abs/2312.00388
Optically dense clouds in the interstellar medium composed predominantly of molecular hydrogen, known as molecular clouds, are sensitive to energy injection in the form of photon absorption, cosmic-ray scattering, and dark matter (DM) scattering. The
Externí odkaz:
http://arxiv.org/abs/2311.00740
Large Language Models' safety remains a critical concern due to their vulnerability to adversarial attacks, which can prompt these systems to produce harmful responses. In the heart of these systems lies a safety classifier, a computational model tra
Externí odkaz:
http://arxiv.org/abs/2311.00172
Jailbreak vulnerabilities in Large Language Models (LLMs), which exploit meticulously crafted prompts to elicit content that violates service guidelines, have captured the attention of research communities. While model owners can defend against indiv
Externí odkaz:
http://arxiv.org/abs/2309.05274
Autor:
Harris, Ian R.
Publikováno v:
Carpathian Journal of Mathematics, 2024 Jan 01. 40(1), 37-45.
Externí odkaz:
https://www.jstor.org/stable/27259295
Nuclear scattering events with large momentum transfer in atomic, molecular, or solid-state systems may result in electronic excitations. In the context of atomic scattering by dark matter (DM), this is known as the Migdal effect, but the same effect
Externí odkaz:
http://arxiv.org/abs/2208.09002
Autor:
Kurennoy, Alexey, Coleman, John, Harris, Ian, Lynch, Alice, Mac Fhearai, Oisin, Tsatsoulis, Daphne
Pairwise debiasing is one of the most effective strategies in reducing position bias in learning-to-rank (LTR) models. However, limiting the scope of this strategy, are the underlying assumptions required by many pairwise debiasing approaches. In thi
Externí odkaz:
http://arxiv.org/abs/2207.08537