zeta-alpha-ai/NanoMSMARCO

---
language:
- en
license: cc-by-4.0
multilinguality:
- monolingual
source_datasets:
- MSMARCO
task_categories:
- text-retrieval
task_ids:
- document-retrieval
tags:
- text-retrieval
dataset_info:
- config_name: corpus
features:
- name: _id
dtype: string
- name: text
dtype: string
splits:
- name: train
num_bytes: 1745074
num_examples: 5043
download_size: 1115821
dataset_size: 1745074
- config_name: qrels
features:
- name: query-id
dtype: string
- name: corpus-id
dtype: string
splits:
- name: train
num_bytes: 1065
num_examples: 50
download_size: 2095
dataset_size: 1065
- config_name: queries
features:
- name: _id
dtype: string
- name: text
dtype: string
splits:
- name: train
num_bytes: 2328
num_examples: 50
download_size: 3219
dataset_size: 2328
configs:
- config_name: corpus
data_files:
- split: train
path: corpus/train-*
- config_name: qrels
data_files:
- split: train
path: qrels/train-*
- config_name: queries
data_files:
- split: train
path: queries/train-*
---