E5
Text embedding model family trained on weakly supervised pairs.
Visão geral
E5 is an embedding model family trained on large collections of weakly supervised text pairs, with the task described in the input so one model serves queries, passages and classification. It solves the problem that an embedding model trained on one kind of pair transfers poorly to another. It exists because describing the task in the text is a cheap way to make one model cover several retrieval settings.
Grafo de tecnologias
Como E5 se liga ao resto do stack.
Alternativas
-
BGE
model
Uma alternativa a E5 · source
-
Cohere Embed
model
Uma alternativa a E5 · source
-
GTE
model
Uma alternativa a E5 · source
-
Instructor
model
Uma alternativa a E5 · source
-
Jina Embeddings
model
Uma alternativa a E5 · source
-
Nomic Embed
model
Uma alternativa a E5 · source
-
OpenAI Text Embedding 3
model
Uma alternativa a E5 · source
Comparações
Comparações detalhadas com as alternativas acima.