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: 8d9954e04df7cd63c0afcae467d2eee4
cmd: scripts/extract-corpus.sh data/gigatoken-corpus.tar.gz script-data/devanbu-split/train.txt
  script-data/devanbu-split/valid.txt script-data/devanbu-split/test.txt Clara/clara/src/main/java/org/vaadin/teemu/clara/Clara.java
  data/devanbu-small-corpus
wdir: ..
deps:
- md5: f23195d351918f103c01930427230207
  path: scripts/extract-corpus.sh
- md5: 5ad5ab1f45baa6eb502066df96d00380
  path: data/gigatoken-corpus.tar.gz
- md5: d8ad66a2776c92db40eab46bf8ca5c5c
  path: script-data/devanbu-split/train.txt
- md5: 149a4e1d43239e947eac8cacdefbf31b
  path: script-data/devanbu-split/valid.txt
- md5: 386e217730117c7276d72d0dc21a2740
  path: script-data/devanbu-split/test.txt
- path: params/25k-vocab-corpus.yml
  params:
    demo-file: Clara/clara/src/main/java/org/vaadin/teemu/clara/Clara.java
outs:
- md5: fbfc6bc25a11e40705a235b12e9f0637.dir
  path: data/devanbu-small-corpus
  cache: true
  metric: false
  persist: false