Výsledky vyhledávání

Report

Hammer: Robust Function-Calling for On-Device Language Models via Function Masking

Autor: Lin, Qiqiang, Wen, Muning, Peng, Qiuying, Nie, Guanyu, Liao, Junwei, Wang, Jun, Mo, Xiaoyun, Zhou, Jiamu, Cheng, Cheng, Zhao, Yin, Zhang, Weinan

Large language models have demonstrated impressive value in performing as autonomous agents when equipped with external tools and API calls. Nonetheless, effectively harnessing their potential for executing complex tasks crucially relies on enhanceme

Externí odkaz: http://arxiv.org/abs/2410.04587

Zobrazit plný text záznamu

Report

P3: A Policy-Driven, Pace-Adaptive, and Diversity-Promoted Framework for data pruning in LLM Training

Autor: Yang, Yingxuan, Wang, Huayi, Wen, Muning, Mo, Xiaoyun, Peng, Qiuying, Wang, Jun, Zhang, Weinan

In the rapidly advancing field of Large Language Models (LLMs), effectively leveraging existing datasets during fine-tuning to maximize the model's potential is of paramount importance. This paper introduces P3, an adaptive framework aimed at optimiz

Externí odkaz: http://arxiv.org/abs/2408.05541

Zobrazit plný text záznamu

Akademický článek

Study on enhanced bioremediation effect of oil-bearing dredging sediment

Autor: Chao Lei, Mo Xiaoyun, Meng Jia, Li Yafeng

Publikováno v: E3S Web of Conferences, Vol 252, p 02031 (2021)

To solve the problem of difficult treatment of oil-bearing dredging sediment, the effects of three methods of microbial remediation, phytoremediation and combined bioremediation on the treatment of oily river dredging sediments were compared and stud

Externí odkaz: https://doaj.org/article/8e508c9aae2449d09fc16a9ec49822c4