Verified65% confidenceFactTime unknown
Modern large models (such as the GPT series, Qwen, and DeepSeek) generally adopt the Decoder-only variant of the Transformer
3
Sources
65%
Confidence
Long-term
Relevance
5/31/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedGPT系列、LLaMA、Gemini等主流模型均基于Transformer的解码器（Decoder-only）变体84% similarVerified当前所有主流大模型（GPT、BERT、LLaMA等）都基于Transformer架构80% similarUnverifiedTransformer 取代了此前主流的 RNN/LSTM 序列模型，成为 GPT、LLaMA、Claude 等主流大模型的基础结构79% similarVerifiedModern LLMs (such as the GPT series, Claude, and Llama) are all based on the Transformer architecture, and their decoding process is essentially a Markov chain.78% similarVerifiedThe GPT series uses the Decoder-only variant of the Transformer, predicting the next Token autoregressively.77% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/14939API
curl https://kongchang.com/api/v1/knowledge/claims/14939MCP
get_claim(id=14939)