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

58
examples/pipelines/all_configs/Dtimetorun_test.json Normal file
View file

@ -0,0 +1,58 @@
[
{
"min_n": 20,
"max_n": 50,
"min_m": 20,
"max_m": 50,
"possible_prob": 0.4,
"max_k": 10000
},
{
"min_n": 1,
"max_n": 50,
"min_m": 1,
"max_m": 50,
"possible_prob": 0.4,
"max_k": 15000
},
{
"min_n": 4,
"max_n": 35,
"min_m": 4,
"max_m": 35,
"possible_prob": 0.5,
"max_k": 12000
},
{
"min_n": 10,
"max_n": 40,
"min_m": 10,
"max_m": 40,
"possible_prob": 0.6,
"max_k": 20000
},
{
"min_n": 1,
"max_n": 10,
"min_m": 1,
"max_m": 10,
"possible_prob": 0.9,
"max_k": 500
},
{
"min_n": 2,
"max_n": 30,
"min_m": 2,
"max_m": 30,
"possible_prob": 0.5,
"max_k": 5000
},
{
"min_n": 1,
"max_n": 20,
"min_m": 1,
"max_m": 20,
"possible_prob": 0.3,
"max_k": 1000
}
]