[HTML][HTML] A survey of GPT-3 family large language models including ChatGPT and GPT-4

KS Kalyan - Natural Language Processing Journal, 2024 - Elsevier
Large language models (LLMs) are a special class of pretrained language models (PLMs)
obtained by scaling model size, pretraining corpus and computation. LLMs, because of their …

[PDF][PDF] A survey of large language models

WX Zhao, K Zhou, J Li, T Tang… - arxiv preprint arxiv …, 2023 - paper-notes.zhjwpku.com
Ever since the Turing Test was proposed in the 1950s, humans have explored the mastering
of language intelligence by machine. Language is essentially a complex, intricate system of …

Efficient large language models: A survey

Z Wan, X Wang, C Liu, S Alam, Y Zheng, J Liu… - arxiv preprint arxiv …, 2023 - arxiv.org
Large Language Models (LLMs) have demonstrated remarkable capabilities in important
tasks such as natural language understanding and language generation, and thus have the …

Llama pro: Progressive llama with block expansion

C Wu, Y Gan, Y Ge, Z Lu, J Wang, Y Feng… - arxiv preprint arxiv …, 2024 - arxiv.org
Humans generally acquire new skills without compromising the old; however, the opposite
holds for Large Language Models (LLMs), eg, from LLaMA to CodeLLaMA. To this end, we …

[HTML][HTML] Large language models for intelligent transportation: A review of the state of the art and challenges

S Wandelt, C Zheng, S Wang, Y Liu, X Sun - Applied Sciences, 2024 - mdpi.com
Large Language Models (LLMs), based on their highly developed ability to comprehend and
generate human-like text, promise to revolutionize all aspects of society. These LLMs …

Not all layers of llms are necessary during inference

S Fan, X Jiang, X Li, X Meng, P Han, S Shang… - arxiv preprint arxiv …, 2024 - arxiv.org
Due to the large number of parameters, the inference phase of Large Language Models
(LLMs) is resource-intensive. However, not all requests posed to LLMs are equally difficult to …

Compressing llms: The truth is rarely pure and never simple

A Jaiswal, Z Gan, X Du, B Zhang, Z Wang… - arxiv preprint arxiv …, 2023 - arxiv.org
Despite their remarkable achievements, modern Large Language Models (LLMs) face
exorbitant computational and memory footprints. Recently, several works have shown …

A survey on model moerging: Recycling and routing among specialized experts for collaborative learning

P Yadav, C Raffel, M Muqeeth, L Caccia, H Liu… - arxiv preprint arxiv …, 2024 - arxiv.org
The availability of performant pre-trained models has led to a proliferation of fine-tuned
expert models that are specialized to a particular domain or task. Model MoErging methods …

On-device query intent prediction with lightweight llms to support ubiquitous conversations

M Dubiel, Y Barghouti, K Kudryavtseva, LA Leiva - Scientific reports, 2024 - nature.com
Abstract Conversational Agents (CAs) have made their way to providing interactive
assistance to users. However, the current dialogue modelling techniques for CAs are …

Tele-flm technical report

X Li, Y Yao, X Jiang, X Fang, C Wang, X Liu… - arxiv preprint arxiv …, 2024 - arxiv.org
Large language models (LLMs) have showcased profound capabilities in language
understanding and generation, facilitating a wide array of applications. However, there is a …