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

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

View file

@ -0,0 +1,22 @@
[
{
"min_n": 1,
"max_n": 200000,
"d_prob": 0.3
},
{
"min_n": 200,
"max_n": 50000,
"d_prob": 0.6
},
{
"min_n": 5,
"max_n": 1000,
"d_prob": 0.5
},
{
"min_n": 10,
"max_n": 5000,
"d_prob": 0.7
}
]