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

50
examples/pipelines/all_configs/Cjeopardy_train.json Normal file
View file

@ -0,0 +1,50 @@
[
{
"n_min": 30,
"n_max": 100,
"a_min": 10000,
"a_max": 10000000,
"m_min": 10,
"m_max": 30
},
{
"n_min": 20,
"n_max": 100,
"a_min": 5000,
"a_max": 10000000,
"m_min": 5,
"m_max": 20
},
{
"n_min": 5,
"n_max": 50,
"a_min": 100,
"a_max": 100000,
"m_min": 2,
"m_max": 30
},
{
"n_min": 5,
"n_max": 50,
"a_min": 100,
"a_max": 1000000,
"m_min": 3,
"m_max": 15
},
{
"n_min": 1,
"n_max": 10,
"a_min": 1,
"a_max": 1000,
"m_min": 1,
"m_max": 5
},
{
"n_min": 1,
"n_max": 100,
"a_min": 1,
"a_max": 10000000,
"m_min": 1,
"m_max": 30
}
]