DJ的小网站

DeepSeek-Prover

DeepSeek-Prover-V1.5: Harnessing Proof Assistant Feedback for Reinforcement Learning and Monte-Carlo Tree Search 1.介绍 尽管在自然语言领域取得了显著进展,但语言模型在形式化定理证明方面

dj-admin dj-admin Published on 2025-03-01

DeepSeek-Math

DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models 1.介绍 两个关键内容: 利用公开可用网络数据的数据选择管道,大规模数学预训练 创建了DeepSeekMath语料库:从Common

dj-admin dj-admin Published on 2025-03-01

论文汇报0:Retentive Network: A Successor to Transformer for Large Language Models

论文题目:Retentive Network: A Successor to Transformer for Large Language Models 发表时间:2023 arxiv 论文作者:Yutao Sun, Li Dong, Shaohan Huang, Shuming Ma, Yuqin

cdj cdj Published on 2024-11-03