codenet_mlm.yaml

# Copyright 2021 The MLX Contributors
#
# SPDX-License-Identifier: Apache-2.0
id: codenet-mlm
name: CodeNet - MLM
description: A small subset of the Project CodeNet dataset, containing 55,000 samples in the C programming language to demonstrate the use of a Masked Language Model for tokenization tasks.
version: 1.0.0
created: 2021-05-05
updated: 2021-05-05
format:
  - type: C
    url: https://en.wikipedia.org/wiki/The_C_Programming_Language
domain: Solutions to Programming Problems

# Information about the entity that makes the data set available
provider:
  name: Data Asset eXchange
  url: https://developer.ibm.com/exchanges/data/all/project-codenet/

# identifies where the data set is stored and how it is stored (REQUIRED)
repository:
  type: HTTP
  url: https://dax-cdn.cdn.appdomain.cloud/dax-project-codenet/1.0.0/Project_CodeNet_MLM.tar.gz
  mime_type: application/x-tar
  sha_512: 
  size: 51K

# REQUIRED; data set license information
license:
  commercial: false
  name: CDLA Permissive v2.0
  url: https://cdla.dev/permissive-2-0/

# REQUIRED; describes relevant files in the data set archive
content:
  - pattern: train, test
    description: The dataset comprises 55,000 submissions in the C programming language.
    records: 55000
    size: 51K
    type: file
    format: C
    mime_type: text/plain

# OPTIONAL; Identifies where the data set was obtained from
source:
  name: Data Asset eXchange
  url: https://developer.ibm.com/exchanges/data/all/project-codenet/

# OPTIONAL; but recommended
seo_tags:
  - Solutions to Programming Problems
  - Text

# OPTIONAL; assets that complement this data set, e.g. notebooks
related_assets:
  - name: Project CodeNet Masked Language Model
    description: Experiment investigates whether a popular attention model to construct a masked language model (MLM) can be used for source code instead of natural language sentences
    mime_type: application/x-ipynb+json
    url: https://github.com/machine-learning-exchange/katalog/blob/main/notebook-samples/src/codenet/Project_CodeNet_MLM.ipynb
    application:
      name: MLX
      asset_id: notebooks/project-codenet-mlm

# OPTIONAL; url for the markdown file which describes the asset
readme_url: https://raw.githubusercontent.com/machine-learning-exchange/katalog/main/dataset-samples/codenet_mlm/codenet_mlm.md