मुख्य सामग्री पर जाएँ

DeepSeek-R1

तर्क-श्रृंखला पर RL से प्रशिक्षित तर्क मॉडल, भार MIT लाइसेंस के तहत खुले

DeepSeek मॉडल खुले वेट
इनपुटटेक्स्टटेक्स्ट

यह पृष्ठ अंग्रेज़ी में प्रस्तुत है; शीर्षक और सारांश का स्थानीयकरण किया गया है।

यह क्या है

DeepSeek-R1 is a reasoning model DeepSeek released in January 2025 that produces a long chain of thought before answering. It trains the model with reinforcement learning to generate reasoning steps on its own, rather than relying on large sets of human-labelled rationales. R1 shares the architecture scale of the V3 family, releases its weights under the MIT licence and publishes a technical report on its training method. After release, many distilled versions of R1 appeared, transferring its reasoning ability into smaller models.

यह क्यों महत्वपूर्ण है

It fully open-sourced the weights of a frontier reasoning model under the MIT licence and published a reproducible RL training recipe; the wave of distilled versions that followed changed the cost structure of building one’s own reasoning capability.

मुख्य विशिष्टताएँ

Parameters
671B (MoE, 37B active)
Context window
128K tokens
Open weights
Yes (MIT licence)
Type
Reasoning model

संबंधित क्षमताएँ

संबंधित अवधारणाएँ

समान उत्पाद