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

41
examples/pipelines/puzzle_configs/korLogicStatisticalReasoning_train.json
View file

@ -1,41 +0,0 @@
[
{
"min_n": 8,
"max_n": 30,
"attribute_descriptions": [
"top scorer",
"perfect health",
"satisfied customer",
"damaged goods",
"active lifestyle",
"excessive noise",
"full recovery"
]
},
{
"min_n": 3,
"max_n": 20,
"attribute_descriptions": [
"excellent performance",
"no diseases",
"content with product",
"faulty goods",
"consistent work",
"high pollution",
"successful surgery"
]
},
{
"min_n": 5,
"max_n": 50,
"attribute_descriptions": [
"math score above 90",
"healthy",
"satisfied with facilities",
"defective",
"daily exercise",
"speeding behavior",
"positive response"
]
}
]