Computer Science & AI · arXiv:2412.19437
DeepSeek-V3 Technical Report
Authors: DeepSeek-AI, Aixin Liu, Bei Feng, Bing Xue, Bingxuan Wang et al. (arXiv:2412.19437) · arXiv: 2412.19437
Core Methodological Innovation
Featured in Nujan's Computer Science & AI Literature Digest. Open side-by-side with interactive equation, methodology, and citation breakdowns.
Key Quantitative & Theoretical Takeaway: Open arXiv:2412.19437 in Nujan to inspect every mathematical symbol, experimental baseline, and citation directly alongside the original PDF.
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.
Step-by-Step Equation & Methodology Breakdown
What is DeepSeek-V3 Technical Report (arXiv:2412.19437) about?
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.
How can I read arXiv:2412.19437 with interactive explanations?
Visit https://nujan.app/abs/2412.19437 to open DeepSeek-V3 Technical Report in Nujan's split-screen research workspace with instant equation and methodology breakdowns.