E5
Text embedding model family trained on weakly supervised pairs.
Обзор
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.
Граф технологий
Как E5 связана с остальным стеком.
Альтернативы
-
BGE
model
Альтернатива для E5 · source
-
Cohere Embed
model
Альтернатива для E5 · source
-
GTE
model
Альтернатива для E5 · source
-
Instructor
model
Альтернатива для E5 · source
-
Jina Embeddings
model
Альтернатива для E5 · source
-
Nomic Embed
model
Альтернатива для E5 · source
-
OpenAI Text Embedding 3
model
Альтернатива для E5 · source
Сравнения
Подробные сопоставления с альтернативами выше.