mteb

Installation

Example Usage

Usage Documentation

Task selection

Running a Benchmark

Passing in `encode` arguments

Selecting evaluation split

Selecting evaluation subset

Using a custom model

Evaluating on a custom dataset

Using a cross encoder for reranking

Using Late Interaction models for retrieval

Saving retrieval task predictions

Fetching results from the results repository

Annotate Contamination

Running the Leaderboard

define your task and model above as normal

wrap the model with the cache wrapper

run as normal