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

39
examples/pipelines/all_configs/Crandomevents_test.json Normal file
View file

@ -0,0 +1,39 @@
[
{
"max_n": 100,
"max_m": 50,
"prefix_shuffle_ratio": 0.8
},
{
"max_n": 50,
"max_m": 20,
"case_type_ratio": {
"sorted": 0.2,
"unsorted": 0.7,
"boundary": 0.1
}
},
{
"max_n": 1,
"max_m": 0
},
{
"max_n": 10,
"max_m": 5
},
{
"max_n": 1000,
"max_m": 500,
"seed": 42
},
{
"max_n": 5000,
"max_m": 2500,
"seed": 123,
"case_type_ratio": {
"sorted": 0.1,
"unsorted": 0.8,
"boundary": 0.1
}
}
]