期刊文献+
共找到2篇文章
< 1 >
每页显示 20 50 100
MOSS:An Open Conversational Large Language Model
1
作者 Tianxiang Sun Xiaotian Zhang +21 位作者 Zhengfu He Peng Li Qinyuan Cheng Xiangyang Liu Hang Yan Yunfan Shao Qiong Tang Shiduo Zhang Xingjian Zhao Ke Chen Yining Zheng Zhejian zhou Ruixiao Li Jun Zhan yunhua zhou Linyang Li Xiaogui Yang Lingling Wu Zhangyue Yin Xuanjing Huang Yu-Gang Jiang Xipeng Qiu 《Machine Intelligence Research》 EI CSCD 2024年第5期888-905,共18页
Conversational large language models(LLMs)such as ChatGPT and GPT-4 have recently exhibited remarkable capabilities across various domains,capturing widespread attention from the public.To facilitate this line of rese... Conversational large language models(LLMs)such as ChatGPT and GPT-4 have recently exhibited remarkable capabilities across various domains,capturing widespread attention from the public.To facilitate this line of research,in this paper,we report the development of MOSS,an open-sourced conversational LLM that contains 16 B parameters and can perform a variety of instructions in multi-turn interactions with humans.The base model of MOSS is pre-trained on large-scale unlabeled English,Chinese,and code data.To optimize the model for dialogue,we generate 1.1 M synthetic conversations based on user prompts collected through our earlier versions of the model API.We then perform preference-aware training on preference data annotated from AI feedback.Evaluation results on real-world use cases and academic benchmarks demonstrate the effectiveness of the proposed approaches.In addition,we present an effective practice to augment MOSS with several external tools.Through the development of MOSS,we have established a complete technical roadmap for large language models from pre-training,supervised fine-tuning to alignment,verifying the feasibility of chatGPT under resource-limited conditions and providing a reference for both the academic and industrial communities.Model weights and code are publicly available at https://github.com/OpenMOSS/MOSS. 展开更多
关键词 Large language models natural language processing pre-training ALIGNMENT chatGPT MOSS
原文传递
SRB measures for pointwise hyperbolic systems on open regions
2
作者 Jianyu Chen Huyi Hu yunhua zhou 《Science China Mathematics》 SCIE CSCD 2020年第9期1671-1720,共50页
A diffeomorphism f:M→M is pointwise partially hyperbolic on an open invariant subset N⊂M if there is an invariant decomposition TNM=Eu⊕Ec⊕Es such that Dxf is strictly expanding on Eu x and contracting on Esx at eac... A diffeomorphism f:M→M is pointwise partially hyperbolic on an open invariant subset N⊂M if there is an invariant decomposition TNM=Eu⊕Ec⊕Es such that Dxf is strictly expanding on Eu x and contracting on Esx at each x∈N.We show that under certain conditions f has unstable and stable manifolds,and admits a nite or an in nite u-Gibbs measure μ.If f is pointwise hyperbolic on N,then μ is a Sinai-Ruelle-Bowen(SRB)measure or an in nite SRB measure.As applications,we show that some almost Anosov di eomorphisms and gentle perturbations of Katok's map have the properties. 展开更多
关键词 pointwise hyperbolicity unstable manifold SRB measure almost Anosov di eomorphism Katok's map
原文传递
上一页 1 下一页 到第
使用帮助 返回顶部