InternLM/InternBootcamp
1
0
Fork 0
mirror of https://github.com/InternLM/InternBootcamp.git synced 2026-04-23 16:55:02 +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

44
examples/pipelines/all_configs/Enecklace_test.json Normal file
View file

@ -0,0 +1,44 @@
[
{
"min_n": 2,
"max_n": 15,
"min_ai": 2,
"max_ai": 8,
"max_total": 20000
},
{
"min_n": 2,
"max_n": 10,
"min_ai": 2,
"max_ai": 5,
"max_total": 1000
},
{
"min_n": 1,
"max_n": 5,
"min_ai": 1,
"max_ai": 3,
"max_total": 100
},
{
"min_n": 1,
"max_n": 26,
"min_ai": 1,
"max_ai": 10,
"max_total": 100000
},
{
"min_n": 1,
"max_n": 10,
"min_ai": 1,
"max_ai": 5,
"max_total": 500
},
{
"min_n": 5,
"max_n": 20,
"min_ai": 3,
"max_ai": 10,
"max_total": 2000
}
]