Zobrazeno 1 - 10
of 588
pro vyhledávání: '"He, PengCheng"'
Auto-regressive generation models achieve competitive performance across many different NLP tasks such as summarization, question answering, and classifications. However, they are also known for being slow in inference, which makes them challenging t
Externí odkaz:
http://arxiv.org/abs/2405.04513
Large Language Models (LLMs) inherently encode a wealth of knowledge within their parameters through pre-training on extensive corpora. While prior research has delved into operations on these parameters to manipulate the underlying implicit knowledg
Externí odkaz:
http://arxiv.org/abs/2310.11451
Autor:
Li, Yixiao, Yu, Yifan, Liang, Chen, He, Pengcheng, Karampatziakis, Nikos, Chen, Weizhu, Zhao, Tuo
Quantization is an indispensable technique for serving Large Language Models (LLMs) and has recently found its way into LoRA fine-tuning. In this work we focus on the scenario where quantization and LoRA fine-tuning are applied together on a pre-trai
Externí odkaz:
http://arxiv.org/abs/2310.08659
Autor:
Zheng, Huangjie, Wang, Zhendong, Yuan, Jianbo, Ning, Guanghan, He, Pengcheng, You, Quanzeng, Yang, Hongxia, Zhou, Mingyuan
Diffusion models excel at generating photo-realistic images but come with significant computational costs in both training and sampling. While various techniques address these computational challenges, a less-explored issue is designing an efficient
Externí odkaz:
http://arxiv.org/abs/2310.06389
Despite their impressive capabilities, large language models (LLMs) are prone to hallucinations, i.e., generating content that deviates from facts seen during pretraining. We propose a simple decoding strategy for reducing hallucinations with pretrai
Externí odkaz:
http://arxiv.org/abs/2309.03883
Reward design is a fundamental, yet challenging aspect of reinforcement learning (RL). Researchers typically utilize feedback signals from the environment to handcraft a reward function, but this process is not always effective due to the varying sca
Externí odkaz:
http://arxiv.org/abs/2309.02632
Large Language Models (LLMs) have shown remarkable proficiency in following instructions, making them valuable in customer-facing applications. However, their impressive capabilities also raise concerns about the amplification of risks posed by adver
Externí odkaz:
http://arxiv.org/abs/2308.10819
Meetings play a critical infrastructural role in the coordination of work. In recent years, due to shift to hybrid and remote work, more meetings are moving to online Computer Mediated Spaces. This has led to new problems (e.g. more time spent in les
Externí odkaz:
http://arxiv.org/abs/2307.15793
LoSparse: Structured Compression of Large Language Models based on Low-Rank and Sparse Approximation
Transformer models have achieved remarkable results in various natural language tasks, but they are often prohibitively large, requiring massive memories and computational resources. To reduce the size and complexity of these models, we propose LoSpa
Externí odkaz:
http://arxiv.org/abs/2306.11222
Summarizing lengthy documents is a common and essential task in our daily lives. Although recent advancements in neural summarization models can assist in crafting general-purpose summaries, human writers often have specific requirements that call fo
Externí odkaz:
http://arxiv.org/abs/2306.03067