dongg18/CODETASK
收藏Hugging Face2026-04-13 更新2026-04-12 收录
下载链接:
https://hf-mirror.com/datasets/dongg18/CODETASK
下载链接
链接失效反馈官方服务:
资源简介:
---
dataset_info:
- config_name: BFP
features:
- name: task
dtype: string
- name: split
dtype: string
- name: id
dtype: string
- name: input
dtype: string
- name: output
dtype: string
- name: outputs
sequence: string
- name: definition
sequence: string
- name: positive_examples
dtype: string
- name: negative_examples
dtype: string
splits:
- name: train
num_bytes: 27287918
num_examples: 46680
- name: validation
num_bytes: 591299
num_examples: 1000
- name: test
num_bytes: 2908099
num_examples: 5000
download_size: 0
dataset_size: 30787316
- config_name: CONCODE
features:
- name: task
dtype: string
- name: split
dtype: string
- name: id
dtype: string
- name: input
dtype: string
- name: output
dtype: string
- name: outputs
sequence: string
- name: definition
sequence: string
- name: positive_examples
dtype: string
- name: negative_examples
dtype: string
splits:
- name: train
num_bytes: 128595740
num_examples: 100000
- name: validation
num_bytes: 1220098
num_examples: 1000
- name: test
num_bytes: 2551494
num_examples: 2000
download_size: 0
dataset_size: 132367332
- config_name: CoST
features:
- name: task
dtype: string
- name: split
dtype: string
- name: id
dtype: string
- name: input
dtype: string
- name: output
dtype: string
- name: outputs
sequence: string
- name: definition
sequence: string
- name: positive_examples
dtype: string
- name: negative_examples
dtype: string
splits:
- name: train
num_bytes: 6483122
num_examples: 12645
- name: validation
num_bytes: 138772
num_examples: 272
- name: test
num_bytes: 214087
num_examples: 410
download_size: 0
dataset_size: 6835981
- config_name: CodeSearchNet
features:
- name: task
dtype: string
- name: split
dtype: string
- name: id
dtype: string
- name: input
dtype: string
- name: output
dtype: string
- name: outputs
sequence: string
- name: definition
sequence: string
- name: positive_examples
dtype: string
- name: negative_examples
dtype: string
splits:
- name: train
num_bytes: 19364182
num_examples: 24927
- name: validation
num_bytes: 779341
num_examples: 1000
- name: test
num_bytes: 1013762
num_examples: 1261
download_size: 8405735
dataset_size: 21157285
- config_name: CodeTrans
features:
- name: task
dtype: string
- name: split
dtype: string
- name: id
dtype: string
- name: input
dtype: string
- name: output
dtype: string
- name: outputs
sequence: string
- name: definition
sequence: string
- name: positive_examples
dtype: string
- name: negative_examples
dtype: string
splits:
- name: train
num_bytes: 8583354
num_examples: 10300
- name: validation
num_bytes: 441429
num_examples: 500
- name: test
num_bytes: 823734
num_examples: 1000
download_size: 0
dataset_size: 9848517
- config_name: KodCode
features:
- name: task
dtype: string
- name: split
dtype: string
- name: id
dtype: string
- name: input
dtype: string
- name: output
dtype: string
- name: outputs
sequence: string
- name: definition
sequence: string
- name: positive_examples
dtype: string
- name: negative_examples
dtype: string
splits:
- name: train
num_bytes: 253354125
num_examples: 100000
- name: validation
num_bytes: 2555495
num_examples: 1000
- name: test
num_bytes: 12615666
num_examples: 5000
download_size: 0
dataset_size: 268525286
- config_name: RunBugRun
features:
- name: task
dtype: string
- name: split
dtype: string
- name: id
dtype: string
- name: input
dtype: string
- name: output
dtype: string
- name: outputs
sequence: string
- name: definition
sequence: string
- name: positive_examples
dtype: string
- name: negative_examples
dtype: string
splits:
- name: train
num_bytes: 8747809
num_examples: 10000
- name: validation
num_bytes: 851444
num_examples: 972
- name: test
num_bytes: 852782
num_examples: 1000
download_size: 0
dataset_size: 10452035
- config_name: TheVault_Csharp
features:
- name: task
dtype: string
- name: split
dtype: string
- name: id
dtype: string
- name: input
dtype: string
- name: output
dtype: string
- name: outputs
sequence: string
- name: definition
sequence: string
- name: positive_examples
dtype: string
- name: negative_examples
dtype: string
splits:
- name: train
num_bytes: 117191536
num_examples: 100000
- name: validation
num_bytes: 975710
num_examples: 1000
- name: test
num_bytes: 6759404
num_examples: 5000
download_size: 0
dataset_size: 124926650
configs:
- config_name: BFP
data_files:
- split: train
path: BFP/train-*
- split: validation
path: BFP/validation-*
- split: test
path: BFP/test-*
- config_name: CONCODE
data_files:
- split: train
path: CONCODE/train-*
- split: validation
path: CONCODE/validation-*
- split: test
path: CONCODE/test-*
- config_name: CoST
data_files:
- split: train
path: CoST/train-*
- split: validation
path: CoST/validation-*
- split: test
path: CoST/test-*
- config_name: CodeSearchNet
data_files:
- split: train
path: CodeSearchNet/train-*
- split: validation
path: CodeSearchNet/validation-*
- split: test
path: CodeSearchNet/test-*
- config_name: CodeTrans
data_files:
- split: train
path: CodeTrans/train-*
- split: validation
path: CodeTrans/validation-*
- split: test
path: CodeTrans/test-*
- config_name: KodCode
data_files:
- split: train
path: KodCode/train-*
- split: validation
path: KodCode/validation-*
- split: test
path: KodCode/test-*
- config_name: RunBugRun
data_files:
- split: train
path: RunBugRun/train-*
- split: validation
path: RunBugRun/validation-*
- split: test
path: RunBugRun/test-*
- config_name: TheVault_Csharp
data_files:
- split: train
path: TheVault_Csharp/train-*
- split: validation
path: TheVault_Csharp/validation-*
- split: test
path: TheVault_Csharp/test-*
---
# Dataset Card for "CODETASK"
[More Information needed](https://github.com/huggingface/datasets/blob/main/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards)
提供机构:
dongg18



