- DeepSeek | 深度求索
基于自研训练框架、自建智算集群和万卡算力等资源，深度求索团队仅用半年时间便已发布并开源多个百亿级参数大模型，如DeepSeek-LLM通用大语言模型、DeepSeek-Coder代码大模型，并在2024年1月率先开源国内首个MoE大模型（DeepSeek-MoE），各大模型在公开评测榜单及
- DeepSeek - AI Chat Online
DeepSeek is a Chinese AI company founded in 2023, focused on advancing artificial general intelligence (AGI) It develops AI systems capable of human-like reasoning, learning, and problem-solving across diverse domains
- DeepSeek - Free AI Chat
Chat with DeepSeek AI for free Get instant help with writing, coding, math, research, and more No signup required
- DeepSeek · GitHub
DeepSeek has 31 repositories available Follow their code on GitHub
- DeepSeek官网 - DeepSeek网页版入口
DeepSeek专注于研究世界领先的通用人工智能底层模型与技术的公司，已开源多个百亿级参数大模型，如 DeepSeek-LLM、DeepSeek-Coder、DeepSeek-MoE等。 DeepSeek提供免费的AI助手、网页版、APP和API服务，其产品矩阵覆盖了从个人用户到企业开发者的全场景需求。
- deepseek-ai DeepSeek-V3 · Hugging Face
We introduce an innovative methodology to distill reasoning capabilities from the long-Chain-of-Thought (CoT) model, specifically from one of the DeepSeek R1 series models, into standard LLMs, particularly DeepSeek-V3
- DeepSeek AI Fan Hub | Independent Guides, Tutorials Resources
Independent community resource for DeepSeek AI Expert guides on R1 reasoning, API integration, and local deployment Not affiliated with the official DeepSeek company
- DeepSeek-V3 Technical Report - arXiv. org
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
|