InternLM/InternBootcamp
1
0
Fork 0
mirror of https://github.com/InternLM/InternBootcamp.git synced 2026-04-19 12:58:04 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

refactor(data_pipeline): optimize data generation pipeline; add multiple preset configurations for data generation

Browse source
This commit is contained in:
chenyongkang 2025-08-26 18:40:21 +08:00
parent 1a8477c8d8
commit 8d493b35a0
2160 changed files with 69199 additions and 154 deletions
Download patch file Download diff file Expand all files Collapse all files

82
examples/pipelines/all_configs/korPuzzleWordBrainTeasers_test.json Executable file
View file

@ -0,0 +1,82 @@
[
{
"num_words": 5,
"nouns": [
"sun",
"flower",
"pine",
"apple",
"butter",
"fly",
"news",
"paper",
"cat",
"fish",
"history",
"building",
"ball",
"room",
"fire",
"place",
"water",
"fall",
"door",
"knob",
"light",
"house",
"tooth",
"paste",
"book",
"case",
"cup",
"board",
"air",
"port",
"rail",
"road",
"sea",
"shell",
"snow",
"ball"
]
},
{
"num_words": 4,
"nouns": [
"tree",
"leaf",
"bud",
"branch",
"bark",
"root",
"seeds",
"fruit",
"bloom",
"sapling",
"forest",
"grove",
"orchard",
"jungle"
]
},
{
"num_words": 5,
"nouns": [
"rain",
"storm",
"wind",
"cloud",
"lightning",
"thunder",
"fog",
"hail",
"sleet",
"snow",
"sunshine",
"dawn",
"dusk",
"twilight",
"moonlight"
]
}
]