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

42
examples/pipelines/all_configs/Dtopsecrettask_train.json Normal file
View file

@ -0,0 +1,42 @@
[
{
"min_n": 10,
"max_n": 100,
"min_k": 5,
"max_k": 100,
"min_s": 10,
"max_s": 1000,
"q_min": 10,
"q_max": 10000
},
{
"min_n": 3,
"max_n": 50,
"min_k": 1,
"max_k": 50,
"min_s": 1,
"max_s": 500,
"q_min": 1,
"q_max": 1000
},
{
"min_n": 3,
"max_n": 50,
"min_k": 1,
"max_k": 50,
"min_s": 1,
"max_s": 500,
"q_min": 1,
"q_max": 100
},
{
"min_n": 50,
"max_n": 150,
"min_k": 10,
"max_k": 150,
"min_s": 500,
"max_s": 1000,
"q_min": 100,
"q_max": 100000
}
]