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 +1,30 @@
[
{
"finite_prob": 0.8,
"interval_prob": 0.1,
"special_prob": 0.1,
"max_size": 6,
"element_type": "letter"
},
{
"finite_prob": 0.6,
"interval_prob": 0.3,
"special_prob": 0.1,
"max_size": 4,
"element_type": "number"
},
{
"finite_prob": 0.9,
"interval_prob": 0.05,
"special_prob": 0.05,
"max_size": 3,
"element_type": "number"
},
{
"finite_prob": 0.7,
"interval_prob": 0.2,
"special_prob": 0.1,
"max_size": 5,
"element_type": "mixed"
}
]