DeepSeek-V3 Technical Report

• URL: http://arxiv.org/abs/2412.19437v2
• Date: Tue, 18 Feb 2025 17:26:38 GMT
• Title: DeepSeek-V3 Technical Report
• Authors: DeepSeek-AI, Aixin Liu, Bei Feng, Bing Xue, Bingxuan Wang, Bochao Wu, Chengda Lu, Chenggang Zhao, Chengqi Deng, Chenyu Zhang, Chong Ruan, Damai Dai, Daya Guo, Dejian Yang, Deli Chen, Dongjie Ji, Erhang Li, Fangyun Lin, Fucong Dai, Fuli Luo, Guangbo Hao, Guanting Chen, Guowei Li, H. Zhang, Han Bao, Hanwei Xu, Haocheng Wang, Haowei Zhang, Honghui Ding, Huajian Xin, Huazuo Gao, Hui Li, Hui Qu, J. L. Cai, Jian Liang, Jianzhong Guo, Jiaqi Ni, Jiashi Li, Jiawei Wang, Jin Chen, Jingchang Chen, Jingyang Yuan, Junjie Qiu, Junlong Li, Junxiao Song, Kai Dong, Kai Hu, Kaige Gao, Kang Guan, Kexin Huang, Kuai Yu, Lean Wang, Lecong Zhang, Lei Xu, Leyi Xia, Liang Zhao, Litong Wang, Liyue Zhang, Meng Li, Miaojun Wang, Mingchuan Zhang, Minghua Zhang, Minghui Tang, Mingming Li, Ning Tian, Panpan Huang, Peiyi Wang, Peng Zhang, Qiancheng Wang, Qihao Zhu, Qinyu Chen, Qiushi Du, R. J. Chen, R. L. Jin, Ruiqi Ge, Ruisong Zhang, Ruizhe Pan, Runji Wang, Runxin Xu, Ruoyu Zhang, Ruyi Chen, S. S. Li, Shanghao Lu, Shangyan Zhou, Shanhuang Chen, Shaoqing Wu, Shengfeng Ye, Shengfeng Ye, Shirong Ma, Shiyu Wang, Shuang Zhou, Shuiping Yu, Shunfeng Zhou, Shuting Pan, T. Wang, Tao Yun, Tian Pei, Tianyu Sun, W. L. Xiao, Wangding Zeng, Wanjia Zhao, Wei An, Wen Liu, Wenfeng Liang, Wenjun Gao, Wenqin Yu, Wentao Zhang, X. Q. Li, Xiangyue Jin, Xianzu Wang, Xiao Bi, Xiaodong Liu, Xiaohan Wang, Xiaojin Shen, Xiaokang Chen, Xiaokang Zhang, Xiaosha Chen, Xiaotao Nie, Xiaowen Sun, Xiaoxiang Wang, Xin Cheng, Xin Liu, Xin Xie, Xingchao Liu, Xingkai Yu, Xinnan Song, Xinxia Shan, Xinyi Zhou, Xinyu Yang, Xinyuan Li, Xuecheng Su, Xuheng Lin, Y. K. Li, Y. Q. Wang, Y. X. Wei, Y. X. Zhu, Yang Zhang, Yanhong Xu, Yanhong Xu, Yanping Huang, Yao Li, Yao Zhao, Yaofeng Sun, Yaohui Li, Yaohui Wang, Yi Yu, Yi Zheng, Yichao Zhang, Yifan Shi, Yiliang Xiong, Ying He, Ying Tang, Yishi Piao, Yisong Wang, Yixuan Tan, Yiyang Ma, Yiyuan Liu, Yongqiang Guo, Yu Wu, Yuan Ou, Yuchen Zhu, Yuduan Wang, Yue Gong, Yuheng Zou, Yujia He, Yukun Zha, Yunfan Xiong, Yunxian Ma, Yuting Yan, Yuxiang Luo, Yuxiang You, Yuxuan Liu, Yuyang Zhou, Z. F. Wu, Z. Z. Ren, Zehui Ren, Zhangli Sha, Zhe Fu, Zhean Xu, Zhen Huang, Zhen Zhang, Zhenda Xie, Zhengyan Zhang, Zhewen Hao, Zhibin Gou, Zhicheng Ma, Zhigang Yan, Zhihong Shao, Zhipeng Xu, Zhiyu Wu, Zhongyu Zhang, Zhuoshu Li, Zihui Gu, Zijia Zhu, Zijun Liu, Zilin Li, Ziwei Xie, Ziyang Song, Ziyi Gao, Zizheng Pan,
• Abstract summary: We present DeepSeek-V3, a strong Mixture-of-Experts (MoE) language model with 671B total parameters with 37B activated for each token. We pre-train DeepSeek-V3 on 14.8 trillion diverse and high-quality tokens, followed by Supervised Fine-Tuning and Reinforcement Learning stages. Comprehensive evaluations reveal that DeepSeek-V3 outperforms other open-source models and achieves performance comparable to leading closed-source models.
• Score: 147.16121855209246
• License:
• Abstract: We present DeepSeek-V3, a strong Mixture-of-Experts (MoE) language model with 671B total parameters with 37B activated for each token. To achieve efficient inference and cost-effective training, DeepSeek-V3 adopts Multi-head Latent Attention (MLA) and DeepSeekMoE architectures, which were thoroughly validated in DeepSeek-V2. Furthermore, DeepSeek-V3 pioneers an auxiliary-loss-free strategy for load balancing and sets a multi-token prediction training objective for stronger performance. We pre-train DeepSeek-V3 on 14.8 trillion diverse and high-quality tokens, followed by Supervised Fine-Tuning and Reinforcement Learning stages to fully harness its capabilities. Comprehensive evaluations reveal that DeepSeek-V3 outperforms other open-source models and achieves performance comparable to leading closed-source models. Despite its excellent performance, DeepSeek-V3 requires only 2.788M H800 GPU hours for its full training. In addition, its training process is remarkably stable. Throughout the entire training process, we did not experience any irrecoverable loss spikes or perform any rollbacks. The model checkpoints are available at https://github.com/deepseek-ai/DeepSeek-V3.

Related papers

• Quantifying the Capability Boundary of DeepSeek Models: An Application-Driven Performance Analysis [7.912726229643101]
  We evaluate the DeepSeek-V3, DeepSeek-R1, DeepSeek-R1-Distill-Qwen series, and DeepSeek-R1-Distill-Llama series on A-Eval. By comparing original instruction-tuned models with their distilled counterparts, we analyze how reasoning enhancements impact performance.
  arXiv  Detail & Related papers  (2025-02-16T15:29:58Z)
• Memory Analysis on the Training Course of DeepSeek Models [5.482535254884105]
  We present a theoretical analysis of GPU memory consumption during the training of DeepSeek models such as DeepSeek-v2 and DeepSeek-v3. It is important to emphasize that the training policies discussed in this report are not representative of DeepSeek's official configurations.
  arXiv  Detail & Related papers  (2025-02-11T09:51:25Z)
• DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning [147.16121855209246]
  We introduce our first-generation reasoning models, DeepSeek-R1-Zero and DeepSeek-R1. DeepSeek-R1-Zero is trained via large-scale reinforcement learning. DeepSeek-R1 incorporates multi-stage training and cold-start data before RL.
  arXiv  Detail & Related papers  (2025-01-22T15:19:35Z)
• DeepSeek-VL2: Mixture-of-Experts Vision-Language Models for Advanced Multimodal Understanding [39.14141055325595]
  We present DeepSeek-VL2, an advanced series of large Mixture-of-Experts (MoE) Vision-Language Models. For the vision component, we incorporate a dynamic tiling vision encoding strategy designed for processing high-resolution images with different aspect ratios. For the language component, we leverage DeepSeekMoE models with the Multi-head Latent Attention mechanism.
  arXiv  Detail & Related papers  (2024-12-13T17:37:48Z)
• Depth Anything V2 [84.88796880335283]
  V2 produces much finer and more robust depth predictions through three key practices. We replace all labeled real images with synthetic images, scale up the capacity of our teacher model, and teach student models via the bridge of large-scale pseudo-labeled real images. Benefiting from their strong generalization capability, we fine-tune them with metric depth labels to obtain our metric depth models.
  arXiv  Detail & Related papers  (2024-06-13T17:59:56Z)
• DeepSeek-V2: A Strong, Economical, and Efficient Mixture-of-Experts Language Model [118.06260386652778]
  We present DeepSeek-V2, a strong Mixture-of-Experts (MoE) language model characterized by economical training and efficient inference. DeepSeek-V2 adopts innovative architectures including Multi-head Latent Attention (MLA) and DeepSeekMoE. Compared with DeepSeek 67B, DeepSeek-V2 achieves significantly stronger performance, and meanwhile saves 42.5% of training costs.
  arXiv  Detail & Related papers  (2024-05-07T15:56:43Z)
• Augmentation-Free Dense Contrastive Knowledge Distillation for Efficient Semantic Segmentation [16.957139277317005]
  Augmentation-free Dense Contrastive Knowledge Distillation (Af-DCD) is a new contrastive distillation learning paradigm. Af-DCD trains compact and accurate deep neural networks for semantic segmentation applications.
  arXiv  Detail & Related papers  (2023-12-07T09:37:28Z)
• For SALE: State-Action Representation Learning for Deep Reinforcement Learning [60.42044715596703]
  SALE is a novel approach for learning embeddings that model the nuanced interaction between state and action. We integrate SALE and an adaptation of checkpoints for RL into TD3 to form the TD7 algorithm. On OpenAI gym benchmark tasks, TD7 has an average performance gain of 276.7% and 50.7% over TD3 at 300k and 5M time steps, respectively.
  arXiv  Detail & Related papers  (2023-06-04T19:47:46Z)
• Geometry Uncertainty Projection Network for Monocular 3D Object Detection [138.24798140338095]
  We propose a Geometry Uncertainty Projection Network (GUP Net) to tackle the error amplification problem at both inference and training stages. Specifically, a GUP module is proposed to obtains the geometry-guided uncertainty of the inferred depth. At the training stage, we propose a Hierarchical Task Learning strategy to reduce the instability caused by error amplification.
  arXiv  Detail & Related papers  (2021-07-29T06:59:07Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.