Spaces:
Running
Running
| <html> | |
| <head> | |
| <meta charset="utf-8"> | |
| <meta name="description" content="DeepSeek Papers: Advancing Open-Source Language Models"> | |
| <meta name="keywords" content="DeepSeek, LLM, AI, Research"> | |
| <meta name="viewport" content="width=device-width, initial-scale=1"> | |
| <title>DeepSeek Papers: Advancing Open-Source Language Models</title> | |
| <link href="https://fonts.googleapis.com/css?family=Google+Sans|Noto+Sans|Castoro" rel="stylesheet"> | |
| <link rel="stylesheet" href="https://cdnjs.cloudflare.com/ajax/libs/bulma/0.9.3/css/bulma.min.css"> | |
| <link rel="stylesheet" href="https://cdnjs.cloudflare.com/ajax/libs/font-awesome/6.0.0/css/all.min.css"> | |
| <style> | |
| .publication-title { | |
| color: #363636; | |
| } | |
| .paper-card { | |
| margin-bottom: 2rem; | |
| transition: transform 0.2s; | |
| } | |
| .paper-card:hover { | |
| transform: translateY(-5px); | |
| } | |
| .coming-soon-badge { | |
| background-color: #3273dc; | |
| color: white; | |
| padding: 0.25rem 0.75rem; | |
| border-radius: 4px; | |
| font-size: 0.8rem; | |
| margin-left: 1rem; | |
| } | |
| .paper-description { | |
| color: #4a4a4a; | |
| margin-top: 0.5rem; | |
| } | |
| .release-date { | |
| color: #7a7a7a; | |
| font-size: 0.9rem; | |
| } | |
| </style> | |
| </head> | |
| <body> | |
| <section class="hero is-light"> | |
| <div class="hero-body"> | |
| <div class="container is-max-desktop"> | |
| <div class="columns is-centered"> | |
| <div class="column has-text-centered"> | |
| <h1 class="title is-1 publication-title">DeepSeek Papers</h1> | |
| <h2 class="subtitle is-3">Advancing Open-Source Language Models</h2> | |
| </div> | |
| </div> | |
| </div> | |
| </div> | |
| </section> | |
| <section class="section"> | |
| <div class="container is-max-desktop"> | |
| <div class="content"> | |
| <div class="columns is-centered"> | |
| <div class="column is-10"> | |
| <!-- DeepSeekLLM --> | |
| <div class="card paper-card"> | |
| <div class="card-content"> | |
| <h3 class="title is-4"> | |
| DeepSeekLLM: Scaling Open-Source Language Models with Longer-termism | |
| <span class="coming-soon-badge">Deep Dive Coming Soon</span> | |
| </h3> | |
| <p class="release-date">Released: November 29, 2023</p> | |
| <p class="paper-description"> | |
| This foundational paper explores scaling laws and the trade-offs between data and model size, | |
| establishing the groundwork for subsequent models. | |
| </p> | |
| </div> | |
| </div> | |
| <!-- DeepSeek-V2 --> | |
| <div class="card paper-card"> | |
| <div class="card-content"> | |
| <h3 class="title is-4"> | |
| DeepSeek-V2: A Strong, Economical, and Efficient Mixture-of-Experts Language Model | |
| <span class="coming-soon-badge">Deep Dive Coming Soon</span> | |
| </h3> | |
| <p class="release-date">Released: May 2024</p> | |
| <p class="paper-description"> | |
| Introduces a Mixture-of-Experts (MoE) architecture, enhancing performance while reducing | |
| training costs by 42%. Emphasizes strong performance characteristics and efficiency improvements. | |
| </p> | |
| </div> | |
| </div> | |
| <!-- DeepSeek-V3 --> | |
| <div class="card paper-card"> | |
| <div class="card-content"> | |
| <h3 class="title is-4"> | |
| DeepSeek-V3 Technical Report | |
| <span class="coming-soon-badge">Deep Dive Coming Soon</span> | |
| </h3> | |
| <p class="release-date">Released: December 2024</p> | |
| <p class="paper-description"> | |
| Discusses the scaling of sparse MoE networks to 671 billion parameters, utilizing mixed precision | |
| training and high-performance computing (HPC) co-design strategies. | |
| </p> | |
| </div> | |
| </div> | |
| <!-- DeepSeek-R1 --> | |
| <div class="card paper-card"> | |
| <div class="card-content"> | |
| <h3 class="title is-4"> | |
| DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning | |
| <span class="coming-soon-badge">Deep Dive Coming Soon</span> | |
| </h3> | |
| <p class="release-date">Released: January 20, 2025</p> | |
| <p class="paper-description"> | |
| The R1 model builds on previous work to enhance reasoning capabilities through large-scale | |
| reinforcement learning, competing directly with leading models like OpenAI's o1. | |
| </p> | |
| </div> | |
| </div> | |
| <!-- DeepSeekMath --> | |
| <div class="card paper-card"> | |
| <div class="card-content"> | |
| <h3 class="title is-4"> | |
| DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models | |
| <span class="coming-soon-badge">Deep Dive Coming Soon</span> | |
| </h3> | |
| <p class="release-date">Released: April 2024</p> | |
| <p class="paper-description"> | |
| This paper presents methods to improve mathematical reasoning in LLMs, introducing the | |
| Group Relative Policy Optimization (GRPO) algorithm during reinforcement learning stages. | |
| </p> | |
| </div> | |
| </div> | |
| <!-- DeepSeek-Prover --> | |
| <div class="card paper-card"> | |
| <div class="card-content"> | |
| <h3 class="title is-4"> | |
| DeepSeek-Prover: Advancing Theorem Proving in LLMs through Large-Scale Synthetic Data | |
| <span class="coming-soon-badge">Deep Dive Coming Soon</span> | |
| </h3> | |
| <p class="paper-description"> | |
| Focuses on enhancing theorem proving capabilities in language models using synthetic data | |
| for training, establishing new benchmarks in automated mathematical reasoning. | |
| </p> | |
| </div> | |
| </div> | |
| <!-- DeepSeek-Coder-V2 --> | |
| <div class="card paper-card"> | |
| <div class="card-content"> | |
| <h3 class="title is-4"> | |
| DeepSeek-Coder-V2: Breaking the Barrier of Closed-Source Models in Code Intelligence | |
| <span class="coming-soon-badge">Deep Dive Coming Soon</span> | |
| </h3> | |
| <p class="paper-description"> | |
| This paper details advancements in code-related tasks with an emphasis on open-source | |
| methodologies, improving upon earlier coding models with enhanced capabilities. | |
| </p> | |
| </div> | |
| </div> | |
| <!-- DeepSeekMoE --> | |
| <div class="card paper-card"> | |
| <div class="card-content"> | |
| <h3 class="title is-4"> | |
| DeepSeekMoE: Advancing Mixture-of-Experts Architecture | |
| <span class="coming-soon-badge">Deep Dive Coming Soon</span> | |
| </h3> | |
| <p class="paper-description"> | |
| Discusses the integration and benefits of the Mixture-of-Experts approach within the | |
| DeepSeek framework, focusing on scalability and efficiency improvements. | |
| </p> | |
| </div> | |
| </div> | |
| </div> | |
| </div> | |
| </div> | |
| </div> | |
| </section> | |
| <footer class="footer"> | |
| <div class="container"> | |
| <div class="content has-text-centered"> | |
| <p> | |
| This website is licensed under a <a rel="license" href="http://creativecommons.org/licenses/by-sa/4.0/"> | |
| Creative Commons Attribution-ShareAlike 4.0 International License</a>. | |
| </p> | |
| </div> | |
| </div> | |
| </footer> | |
| </body> | |
| </html> |