hlibbabii
/
datasets
mirror of https://github.com/giganticode/datasets


  
1

	
2

	
3

	
4

	
5

	
6

	
7

	
8

	
9

	
10

	
11

	
12

	
13

	
14

	
15

	
16

	
17

	
18

	
19

	
20

	
21

	
22

	
23

	
24

	
25

	
            md5: fafaeb49b8b72dfab33ecc8142993f6b
cmd: scripts/extract-corpus.sh data/gigatoken-corpus.tar.gz script-data/25k-vocab-corpus-projects/train.txt
  script-data/25k-vocab-corpus-projects/valid.txt script-data/25k-vocab-corpus-projects/test.txt
  Clara/clara/src/main/java/org/vaadin/teemu/clara/Clara.java data/25k-vocab-corpus
wdir: ..
deps:
- md5: f23195d351918f103c01930427230207
  path: scripts/extract-corpus.sh
- md5: 5ad5ab1f45baa6eb502066df96d00380
  path: data/gigatoken-corpus.tar.gz
- md5: b501d6377a596022e5bec91ca057485e
  path: script-data/25k-vocab-corpus-projects/train.txt
- md5: b62ed5a3d3624b9ea572d29dedc0c472
  path: script-data/25k-vocab-corpus-projects/valid.txt
- md5: ff6c3e364155e331a6e3b39c46b90a21
  path: script-data/25k-vocab-corpus-projects/test.txt
- path: params/25k-vocab-corpus.yml
  params:
    demo-file: Clara/clara/src/main/java/org/vaadin/teemu/clara/Clara.java
outs:
- md5: ca2e8d6be677c14bd408fca1ad2c08cc.dir
  path: data/25k-vocab-corpus
  cache: true
  metric: false
  persist: false