Zobrazeno 1 - 10
of 582
pro vyhledávání: '"Ma, Liqun"'
This work presents a Fully BInarized Large Language Model (FBI-LLM), demonstrating for the first time how to train a large-scale binary language model from scratch (not the partial binary or ternary LLM like BitNet b1.58) to match the performance of
Externí odkaz:
http://arxiv.org/abs/2407.07093
Large Language Models (LLMs) with billions of parameters are prime targets for network pruning, removing some model weights without hurting performance. Prior approaches such as magnitude pruning, SparseGPT, and Wanda, either concentrated solely on w
Externí odkaz:
http://arxiv.org/abs/2311.04902
Autor:
Shen, Zhiqiang, Tao, Tianhua, Ma, Liqun, Neiswanger, Willie, Liu, Zhengzhong, Wang, Hongyi, Tan, Bowen, Hestness, Joel, Vassilieva, Natalia, Soboleva, Daria, Xing, Eric
This paper aims to understand the impacts of various data combinations (e.g., web text, Wikipedia, GitHub, books) on the pretraining of large language models using SlimPajama. SlimPajama is a rigorously deduplicated, multi-source dataset, which has b
Externí odkaz:
http://arxiv.org/abs/2309.10818
Dialogue summarization has drawn much attention recently. Especially in the customer service domain, agents could use dialogue summaries to help boost their works by quickly knowing customer's issues and service progress. These applications require s
Externí odkaz:
http://arxiv.org/abs/2108.13139
Autor:
Ma, Liqun, Deng, Wei, Hu, Xun, Xu, Kai, Xu, Jun, Jiang, Long, Wang, Yi, Su, Sheng, Hu, Song, Xiang, Jun
Publikováno v:
In Fuel Processing Technology January 2024 253
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.
Autor:
Ma, Liqun, Syed-Hassan, Syed Shatir A., Zhou, Junbo, Deng, Wei, Xiong, Yimin, Wang, Xuepeng, Hu, Xun, Xu, Jun, Jiang, Long, Su, Sheng, Hu, Song, Wang, Yi, Xiang, Jun
Publikováno v:
In Fuel Processing Technology November 2023 250
Multi-Task Learning (MTL) aims at boosting the overall performance of each individual task by leveraging useful information contained in multiple related tasks. It has shown great success in natural language processing (NLP). Currently, a number of M
Externí odkaz:
http://arxiv.org/abs/1908.07820
Publikováno v:
In Measurement 31 March 2023 210
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.