- 1、本文档共53页,可阅读全部内容。
- 2、原创力文档(book118)网站文档一经付费(服务费),不意味着购买了该文档的版权,仅供个人/单位学习、研究之用,不得用于商业用途,未经授权,严禁复制、发行、汇编、翻译或者网络传播等,侵权必究。
- 3、本站所有内容均由合作方或网友上传,本站不对文档的完整性、权威性及其观点立场正确性做任何保证或承诺!文档内容仅供研究参考,付费前请自行鉴别。如您付费,意味着您自己接受本站规则且自行承担风险,本站不退款、不进行额外附加服务;查看《如何避免下载的几个坑》。如果您已付费下载过本站文档,您可以点击 这里二次下载。
- 4、如文档侵犯商业秘密、侵犯著作权、侵犯人身权等,请点击“版权申诉”(推荐),也可以打举报电话:400-050-0827(电话支持时间:9:00-18:30)。
DeepSeek-V3TechnicalReport
DeepSeek-AI
research@
Abstract
WepresentDeepSeek-V3,astrongMixture-of-Experts(MoE)languagemodelwith671Btotal
parameterswith37Bactivatedforeachtoken.Toachieveefficientinferenceandcost-effective
training,DeepSeek-V3adoptsMulti-headLatentAttention(MLA)andDeepSeekMoEarchitec-
tures,whichwerethoroughlyvalidatedinDeepSeek-V2.Furthermore,DeepSeek-V3pioneers
anauxiliary-loss-freestrategyforloadbalancingandsetsamulti-tokenpredictiontraining
objectiveforstrongerperformance.Wepre-trainDeepSeek-V3on14.8trilliondiverseand
high-qualitytokens,followedbySupervisedFine-TuningandReinforcementLearningstagesto
fullyharnessitscapabilities.ComprehensiveevaluationsrevealthatDeepSeek-V3outperforms
otheropen-sourcemodelsandachievesperformancecomparabletoleadingclosed-source
models.Despiteitsexcellentperformance,DeepSeek-V3requiresonly2.788MH800GPUhours
foritsfulltraining.Inaddition,itstrainingprocessisremarkablystable.Throughouttheentire
trainingprocess,wedidnotexperienceanyirrecoverablelossspikesorperformanyrollbacks.
Themodelcheckpointsareavailableat/deepseek-ai/DeepSeek-V3.
DeepSeek-V3DeepSeek-V2.5Qwen2.5-72B-InstLlama-3.1-405B-InstGPT-4o-0513Claude-3.5-Sonnet-1022
100
90.2
80.0
8078.078.3
75.9
74.774.6
73.372.6
文档评论(0)