[KongchangAI]
ModelE5-large-instruct

multilingual-e5-large-instruct

A multilingual text embedding model in the E5 series. The instruct variant requires a task description prefix to be added before the input, so that the model encodes the input according to the specified retrieval intent rather than as a generic embedding.

Timeline (last 90 days)

Nov 10

The authors' reproduced scores for multilingual-e5-large-instruct and BGE-M3 deviate from published MTEB results by no more than 2.4 percentage points.

Unverified50%
Nov 10

XLM-RoBERTa is a multilingual pre-trained language model released by Facebook AI, with the large version having about 560 million parameters; BGE-M3 is a multilingual embedding model released by the Beijing Academy of Artificial Intelligence with about 570 million parameters; multilingual-e5-large-instruct is a multilingual instruction-tuned version of Microsoft's E5 series with about 560 million parameters.

Unverified50%
Nov 3

Saidzoda-Tajik-E5-Large is a Tajik text embedding model built on multilingual-e5-large-instruct (560M parameters).

Unverified50%
Nov 3

The instruct variant of multilingual-e5-large-instruct requires a task description prefix (such as 'retrieve relevant passages for the question') to be added before the input.

Unverified50%

All Facts (4)

Source Articles