Unverified50% confidenceFactExact time
Modern embedding models are usually based on the Transformer architecture (such as BERT and its variants), encoding text into fixed-dimensional dense vectors (common dimensions are 768, 1024 or higher).
1
Sources
50%
Confidence
Long-term
Relevance
10/13/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedThe Transformer architecture underlying large language models does not directly process raw characters; instead, it first uses a tokenizer to split text into subword units, which are then mapped to high-dimensional vectors for computation.77% similarUnverifiedTransformer模型只能处理数值张量，需要分词器将文本转换为整数ID序列后通过嵌入层映射为连续向量76% similarUnverifiedCLIP's text encoder is based on the Transformer architecture and maps input text to 512-dimensional or 768-dimensional embedding vectors.75% similarVerifiedLarge language models are based on the Transformer architecture and are trained on massive amounts of text data.73% similarUnverifiedMultimodal large language models typically map image/speech features into the same embedding space as text via projection layers or adapters, which are then processed uniformly by the Transformer decoder.73% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1016082API
curl https://kongchang.com/api/v1/knowledge/claims/1016082MCP
get_claim(id=1016082)