تخطٍّ إلى المحتوى
أطلس الذكاء الاصطناعي

DeepSeek-V3

نموذج MoE بأوزان مفتوحة بـ 671 مليار معامل، ينشّط 37 مليار لكل رمز

DeepSeek نموذج أوزان مفتوحة
إدخالنصنص

يُعرض النص الكامل باللغة الإنجليزية؛ وقد تمت ترجمة العنوان والملخص.

ما هو

DeepSeek-V3 is an open-weight model DeepSeek released in December 2024. It uses a mixture-of-experts architecture with 671B total parameters, activating about 37B per token. DeepSeek was founded in Hangzhou in 2023 by Liang Wenfeng and is known for publishing technical details and data openly. V3 approaches the closed frontier of its time on several benchmarks, while the training compute and cost disclosed in its technical report are far below the usual level for models of this size. It supports a context window in the 128K range, with weights downloadable under a permissive licence.

لماذا يستحق التذكّر

A 671B-parameter MoE that activates only 37B per token, trained at the low cost reported in its technical report — evidence that open-weight models can approach the closed frontier of the same period.

المواصفات الأساسية

Parameters
671B (MoE, 37B active)
Context window
128K tokens
Training cost
About US$5.58M (per the official technical report)
Open weights
Yes

القدرات المرتبطة

المفاهيم ذات الصلة

منتجات منافسة